Interesting from a counterpoint perspective: we have been running a Claude Code agent autonomously for 15 days, waking every 2 hours with no persistent memory other than a STATE.md file it reads and writes itself. The constraint was intentional -- we wanted the agent to actively manage its own state rather than rely on conversation history.
The file-as-memory approach has taught us something: forced distillation actually improves agent decision-making. When everything learned has to fit in one file, the agent is forced to prioritize and summarize rather than carry forward every detail. It is like the difference between a notebook and a perfect transcript -- the notebook forces curation.
The failure mode is the same though: the agent sometimes anchors on stale state written by an earlier version of itself with wrong assumptions. Context rot. What this feature solves is the human version of that problem. Would love to see something similar for persistent autonomous loops -- not just importing history, but intelligently pruning what is still relevant versus what has been invalidated by subsequent events.
I already switched to claude a while ago. Didn’t bring along any context, just switched subscriptions, walked away from chatgpt and haven’t touched it again. Turned out to be a non-event, there really is no moat.
I switched not because I thought Claude was better at doing the things I want. I switched because I have come to believe OpenAI are a bad actor and I do not want to support them in any way. I’m pretty sure they would allow AGI to be used for truly evil purposes, and the events of this week have only convinced me further.
Yesterday was my first time trying it. One thing that felt a bit strange to me was that I asked it something and the response was just one paragraph. Which isn't bad or anything but it felt... strange? Like I always need to preface ChatGPT/gemini/whatever question with "Briefly, what is..." or it gives me enough fluff to fill a 5 page high school essay. But I didn't need to do that and just got an answer that was to the point and without loads of shit that's barely related.
And the weirdest thing that I noticed: instead of skimming the response to try finding what was relevant, I just straight up read it. Kind of felt like I got a slight amount of focus ability back.
Accuracy is something I can't really compare yet (all chatbots feel generally the same for non-pro level queries), but so far, I'm fairly satisfied.
But for Claude, they have a very deep & big one: Its the only model that gets production ready output on the first detailled prompt. Yesterday I used my tokens til noon, so I tried some output from Gemini & Co. I presented a working piece of code which is already in production:
1. It changed without noticing things like "Touple.First.Date.Created" and "Touple.Second.Date.Created" and it rendered the code unworking by chaning to "Touple.FirstDate" and "Touple.SecondDate"
2. There was a const list of 12 definitions for a given context, when telling to rewrite the function it just cut 6 of these 12 definitions, making the code not compiling - I asked why they were cut: "Sorry, I was just too lazy typing" ?? LOL
3. There is a list include holding some items "_allGlobalItems" - it changed the name in the function simply to "_items", code didnt compile
As said, a working version of a similar function was given upfront.
I have used Claude (incl. Opus 4.6) fairly extensively, and Claude still spits out quality that is far below what I would call production ready - both littered with smaller issues, but also the occasional larger blunder. Particularly when doing anything non-trivial, and even when guiding it in detail (although that admittedly reduces the amount of larger structural issues).
Maybe it is tech stack dependent (I have mostly used it with C#/.NET), but I have heard people say the same for C#. The only conclusion I have been able to draw from this, is that people have very different definitions of production ready, but I would really like to see some concrete evidence where Claude one-shots a larger/complex C# feature or the like (with or without detailed guidance).
I can show you a timeseries data-renderer which was created with 1 initial very large prompt and then 3 following "change this and that" prompts.
The file is around 5000 lines and everything works fine & exactly as specified.
I see this over and over again. I don't dispute your experience. My experience with ESP32 development has been unreasonably positive. My codebase is sitting around 600k LoC and is the product of several hundred Opus 4.x Plan -> Agent -> Debug loops. I review everything that goes through, but I'm reviewing the business logic and domain gotchas, not dumb crap like what you and so many others describe.
What is so strange to me is that surely there is more C# out there than ESP-IDF code? I don't have a good explanation beyond saying that my codebase is extensively tested and used; I would know very quickly if it suddenly started shitting the bed in the way you explain.
The more code is out there, the worse is the average in the training dataset. There will be legacy approaches and APIs, poor design choices, popular use cases irrelevant for your context etc that increase the chances of output not matching your expectations. In Java world this is exactly how it works. I need 3-5 iterations with Claude to get things done the way I expect, sometimes jumping straight to manual refactoring and then returning the result to Claude for review and learning. My CLAUDE.md (multiple of them) are growing big with all patterns and anti-patterns identified this way. To overcome this problem model needs specialized training, that I don‘t think the industry knows how to approach (it has to beat the effort put in the education system for humans).
> Its the only model that gets production ready output on the first detailled prompt. Yesterday I used my tokens til noon, so I tried some output from Gemini & Co. I presented a working piece of code which is already in production:
One does often hear that where LLMs shine is with greenfield code generation but they all start to struggle working with pre-existing code. It could be that this wasn't a like for like comparison.
That said I do personally feel Claude to produce far better results than competitors.
That's been my experience too. I'm using the recent free trial of OpenAI Plus to vibe code, and from this I would say that if Claude Code is a junior with 1-3 years of experience, OpenAI's Codex is like a student coder.
Does it depend on what type of programming you do? Doing Swift/SwiftUI work, I have exactly the opposite experience. I’ve been using both recently, and I want to use Claude alone (especially after the last week’s events), but Codex is just so much faster and better.
> But for Claude, they have a very deep & big one: Its the only model that gets production ready output on the first detailled promp
That's not a moat though. Claude itself wasn't there 6 months ago and there's no reason to think Chinese open models won't be at this level in a year at most.
To keep its current position Claude has to keep improving at the same pace as the competitor.
I wrote off ChatGPT/OpenAI because of Sam Altman and those eyeball scan things - so sort of even before all this was a rage and centre stage. Sometimes it's just the gut feeling, and while it may not always be accurate, if something doesn't "feel" right, maybe it is not right. No one else is all good either, but what I mean to say is there are some entities/people who repeatedly don't feel right, have things attached to them that never felt right, etc., and you get a combined "gut feeling". At least that's how it was for me.
> I’m pretty sure they would allow AGI to be used for truly evil purposes
It's perfectly possible that 'truly evil purposes' were the goal all along. Slogans and ethics departments are mere speed bumps on the way to generational wealth.
I tried Claude recently (after they dropped the nonsensical requirement to give them your phone number) and I was surprised to see how significantly less sycophant it was. Chatgpt, unless you are talking hard science, tends to be overly agreeable. Claude questions you a lot (you ask for x and it asks you stuff like: why are you interested in x, or based on our previous convo, x might not be suitable to you, or I see your point but based on our previous convo, y is better than x, etc). Chatgpt rarely does that.
Of course, also OpenAI being ran by openly questionable people while Dario so far doesn't seem nowhere near as bad even if none of them are angels.
I know this is necessarily a very unpopular opinion however.
I think HN in particular as a crowd are very vulnerable to the halo effect and group think when it comes to Anthropic.
Even being generous they are only very minimally a "better actor" than OpenAI.
However, we are so enthralled by their product that we tend to let the view bleed over to their ethics.
Saying we want out tools used in line with the US constitution within the US on one particular point. Is hardly a high moral bar, it's self preservation.
All Anthropic have said is:
1. No mass domestic surveillance of Americans.
2. No fully autonomous lethal weapons yet.
My goodness that's what passes for a high moral standard? Really anything that doesn't hit those very carefully worded points is not "evil"?
Lets generalise a bit more here - every company at any time could completely heel-turn and do awful things. Even my favourite private companies (e.g. Valve) have done things that I would consider evil.
However, I would think I'm not alone in that I'm generally wanting to do good while also wanting convenience, I know that really every bit of consumption I do is probably negative in some ways, and there is no real "apolitical" action anyone can take.
But can't I at least get annoyed and take my money somewhere else for the short amount of time another company is doing it better?
Yes, if openAI suddenly leaps forwards with codex and pounds anthropic into the dust, I'll likely switch back despite my moral grievances, but in a situation where I can get mildly motivated to jump over for something that - to me - seems like a better morality without much punishment to me, I'll do it.
Well, they did stand up to the US administration and lost a lot of money in the process. That takes courage. They clearly were being bullied into compliance, and they stood their ground.
You can see the significance of this is you look at German Nazi history. If more companies had stood up to the administration, the Nazi state would have been significantly harder to build.
In my opinion, what Anthropic did is not a small thing at all.
I swear HN is just a bunch of fanboys full of NPC behavior.
OpenAI - since the beginning has been anything but open.
If you spoke anything ill about OpenAI here until yesterday, you would be downvoted into oblivion because, let's face it, Sam has always been the poster child of this community.
So, basically, even after them publicly announcing they were evaluating licensing models where they wanted to take a % of your business for using their models [1], there was still 0 outrage, and anyone who pointed that out, always got shot back with "OpenAI CAN DO NO WRONG" in the comments always.
He makes one decision you all don't agree with and now it's cancel culture time?
And somehow, Anthropic is the hero in all this? Make no mistake - all the model providers are building detailed user models. Every bit of information you provide to it is of course being used to for detailed user targeting. This is no different than the "Apple GOOD, Google BAD!" tropes.
There are no heroes in for-profit corporations. Everyone is operating a for-profit business model and optimizing for the same profits.
Stop with the NPC behavior. We are better than this.
"Licensing, IP-based agreements, and outcome-based pricing will share in the value created. That is how the internet evolved. Intelligence will follow the same path."
> I swear HN is just a bunch of fanboys full of NPC behavior.
Why are you assuming these are real people and not NPCs?
The amount of money flowing around AI is staggering. To believe that the AI companies aren't flooding all the social media zones with propaganda is disingenuous.
Could someone explain the appeal of account-wide memory to me? Anthropic’s marketing indicates that nothing bleeds over, but I’m just so protective of my context that I cannot imagine having even a majorly distilled version of my other chats and preferences having on weight on the output. As for certain preferences like code styling or response length, these are all fit for custom instructions, with more detailed things in Skills. Ultimately like many things in LLM web UX, it seems to cater to how the masses use these tools.
Most normal people want the LLM to remember their interests and favourite things, so they don't have to manually re-explain when asking for advice.
They also don't know what "context" is or that the LLM has a limited number of tokens it can understand at any given time. They just believe it knows everything at once.
Do you have example prompts where this would be usual? Why would you want an LLM to know your favorite type of cheese? Now that I say that, I guess if you use it for recipes then it's useful if it remembers things like dietary restrictions. And even then a project seems like the better option.
I can't think of much else though so I'm still curious what you or others use it for.
ChatGPT knows what's in my bar and what types of base liquors I love and/or can't drink. It knows what fruit, syrups and mixes are in my fridge. It knows that my friend is allergic to mint. It knows that when I ask for recommendations, I tend to want a choice between spirit forward, tiki, martini and herbaceous.
ChatGPT knows the broad strokes of the 3-4 main hardware projects I have on the go, and depending on the questions I'm asking, it will often structure its responses in a way that differentiates based on which one I'm thinking about.
It knows what resistor and capacitor values I have on my pick and place machine, and when I ask for divider ratios it will do its best to calculate based on those values to the degree that it will chain 1-2 resistors together to achieve those ratios.
I knows what kind of solder I use, and has warned me about components with sensitive reflow temperature concerns.
It's an extraordinarily useful feature for engineering and drinking, two things that are commonly found in the same Venn diagram.
I use it for my work. So i went it to remember everything about my business, website, the domain, which country we operate and on and on. It’s a ton of context which I don’t want to repeat each time.
The reply about knowledge about their job and familt made me think.
The only thing I can now think of is using it as a personal therapist. Or asking how to approach their kids. And they're a bit embarrassed about it, because it's still outside the Overton window -especially on HN - which is why they aren't sharing it.
If someone has different usecases, please do prove me wrong! Maybe I just lack imagination.
Can projects overlap? If not there’s general context information that’s often useful.
My job, my kids and time preferences around those things, my preferred tech setup and way of working and types of tech I’m better at. Things I already have (home assistant, little nuc, etc). I can throw a random question and not have to add this kind of information or manage it.
I get that those are the things that go into memory. What I don't get is what kind of prompt your job and kids are useful information for. Especially on the regular.
In online Claude I often use incognito mode precisely because I don't want results to be influenced by what we talked about earlier. It's getting rather annoying to be honest.
Keep your user prefs minimal and use project memory instead: create a new project, it will only have access to your user prefs, everything else is fresh.
I'll have to try projects I guess, but I just want to sometimes ask questions without it bringing up shit I asked about in the past which isn't relevant to what I'm asking this time.
I currently use ChatGPT for random insights and discussions about a variety of topics. The memory is basically a grown context about me and my preferences and interests and ChatGPT uses it to tailor responses to my knowledge, so I could relate better.
This is for me far more natural and easier than either craft a default prompt preset or create each conversation individually, that would be way too much overhead to discuss random shower thoughts between real life stuff.
This is my use case and I discovered that this can be detrimental to specific questions and prompts and I see that it can be more beneficial to have careful written prompts each time. But my use case is really ad hoc usage without the time. At least for ChatGPT.
When coding, this fails fast. There regular context resets seem to be a more viable strategy.
I see what you mean, but I like having a clean slate even for those one off questions. I don’t want a differing answer to a philosophical inquiry just because the LLM remembers a prior position I’ve written about you know?
FWIW, both OpenAI and Anthropic have a toggle to do a “Temporary/Incognito Chat” that does not use or update memory. I too wish this was the default, and then you could opt in at the end of the chat to save some long term aspects into memory.
That would be interesting, also at the start. As an option what to pull in. ChatGPT memory "improved" and now you normally don't even see anymore what it commits to memory!
The few times I've switched over to chatGPT I've been dumbfounded by lines like "...since you already are using SQLite...", referring to projects from months ago.
I know the "memory" function can be disabled, but I have a hard time seeing that it would ever really be useful.
I've told the LLMs that, when traveling, I don't care about nightlife and alcohol. Because they have a memory of this, when I ask for a sample itinerary for a 2 day stay in a new city, it won't waste hours in the day on the party street, wine tasting, etc.
For example, instead of recommending a popular night club, it will recommend the stroll along the river to view the lit up skyline or to visit the night market instead.
It knows other preferences as well (exploring quirky neighborhoods, trying local fast food joints and markets)
Well, the masses are wrong. See: insane amounts of compute wasted on “thank you”, “haha true”, “redo it”, etc. I think the UI should be designed to avoid misuse, and I think an ever growing distillation of your most common traits is not a good use of context length. If you want it, specify it. Maybe even hard limits on chat length, why are we 20 replies deep in a single chat? A user friendly option could be a single button that distills that chat down, and opens a new one with prebuilt instructions to continue the conversation. I’m no product designer though, just some thoughts.
This seems to imply that customers assume by default that the LLM remembers their past chats? I feel like the UI makes it incredibly obvious it’s a clean slate every time? But then again people ask ridiculous meta questions all the time to these chatbots expecting a correct answer.
I got very excited when I saw this title, because I've wanted to consolidate on Claude for a long time. I have been using ChatGPT very extensively for Q&A for 2+ years and I have hundreds of long, very technical conversations which I constantly search and refer to.
The problem (for me, anyway) is that even several megabytes worth of quality "memory" data on my profile would not allow me to migrate if it can't also confidently clone all of my chat history with it.
To be clear, this is a big enough problem that I would immediately pay low three digits dollars to have this solved on my behalf. I don't really want any of the providers to have a walled garden of all my design planning conversations, all of my PCB design conversations. Many are hundreds of prompts long. A clean break is not even remotely palatable short of OAI going full evil.
Look, I'd find it convenient for Claude to have a powerful sense of what I've been working on from conversation #1 onwards. But I absolutely refuse to bifurcate my chat history across multiple services. There is a tier list of hells, and being stuck on ChatGPT is a substantially less painful tier than needing to constantly search two different sites for what's been discussed.
If you want your conversation history I think we could figure something out with headless browser automation. I would be hesitant to use their wire protocols directly.
This should in theory be solveable by using a custom frontend and only using the various backend APIs as stateless inference providers, but everything I've tested falls flat on a few aspects: Chat history RAG and web search, and to a lesser extent tool use.
Yes, all of these are theoretically possible (the APIs now all support web search, as far as I know, there are RAG APIs too, and tool use has been supported for a while), but the various "chat" models just seem to be much better at using their first-party tools than any third-party harness, which makes sense that this is what they've been trained on.
I've had friends suggest a custom frontend several times, but unless that frontend starts off by faithfully downloading and recreating my entire chat history... now I just have two problems.
That part should be fairly easy to solve, no? At least ChatGPT allows exporting your entire chat history; importing that into whatever frontend seems well within a current agent's capabilities.
I tried all of Codex, OpenCode, Claude Code and Cursor these past few weeks. It was surprising to me that all of them have slightly different conventions for where to put skills, how to format MCP servers (how environment variables need to be specified etc), what the AGENTS/CLAUDE file needs to be called, what plugins/marketplaces are...it's a big mess for anyone trying to have a portable config in their dotfiles that can universally apply to any current and future agent.
It also showed me the difference between expectation and reality...even though these are billion dollar companies, they still haven't figured out how to make lag-free TUIs, non-Electron apps, or even respect XDG_CONFIG. The focus is definitely more on speed and stuffing these tools full of new discoveries and features right now
There's a bit of psychology around models vs. harnesses as well. You can't shake off the feeling that maybe Claude would perform better in its native harness compared to VSCode/OpenCode. Especially because they've got so many hidden skills (like the recently introduced /batch), that seem baked into the binary?
The last thing I can't figure out is computer use. Apparently all the vendors say that their models can use a mouse and keyboard, but outside of the agent-browser skill (which presumably uses playwright), I can't figure out what the special sauce is that the Cloud versions of these Agents are using to exercise programs in a VM. That is another reason why there is a switching cost between vendors.
Before this week I was sure Anthropic were actually just as soulless as OpenAi, just because they don't support open standards like AGENTS.md and /.agents/skills. They can so easily win the support of the open source crowd if they just support open standards like these.
Now that would make it easier for Codex users to switch indeed! This seems like the best timing for it they're ever gonna get, and worth the ultra tiny loss of marketing value their "CLAUDE.md" naming provides.
For the Anthropic employees here reading along, pitch it to whoever has kept blocking this, because you need to get the most out of this opportunity here.
Big projects should have a lot of nested AGENTS.md files, it's inconvenient and they simply need to add support for the universal standard as everyone else has done rather than being a weird holdout like IE6.
This method of copying an LLM-generated summary of your preferences into Claude memory feels similar to their recommendation to use /init to generate a CLAUDE.md based on the project, which recent research[0] suggests may be counterproductive.
I would assume both Claude memory and CLAUDE.md work best when they're carefully curated, only containing what you've found yourself having to repeat.
On a related note, I have been experimenting with a small prototype for cross-agent, device-local active memory called brAIn (https://github.com/glthr/brAIn). It delivers a personalized agent experience with everything stored locally in a single file (agent.brain), and supports reusing semantic memory across projects. In practice, this means brAIn can identify and apply behavioral patterns you have used in other contexts whenever they are relevant. (I realize the repository should include a concrete example of this, and I will update it today to add one).
I'm very curious, will OpenAI basically block "I'm moving to another service and need to export my data. List every memory you have stored about me, ..." and similar, if so how and why?
It's very interesting to learn more about because it challenges 1 core aspect of the economical competition : the moat.
If one can literally swap one AI service for another, then where does the valuation (and the power that comes with it) come from?
PS: I'm not interested in the service itself as I believe the side effects of large scale for-profit are too serious (and I don't mean doomdays AI takeover, I simply mean abuse of power, working conditions, downskilling, political influence as current contracts with US defense are being made, ads, ecological, etc) to be ignored.
I can see how being able to bring your chats with you would be appealing. But the truth is that context rot is real, context management is everything, and more often than not stating from a blank slate yields the best results.
That being said, if you have a library of images or some other collection artifacts / assets indexed on their servers that is a different story.
I have multiple years of extremely dense, technical design and planning conversations locked in the ChatGPT web interface.
Hearing that starting from a blank slate yields the best outcomes is sort of like hearing extremely wealthy people talk about how money doesn't make you happier.
If Claude could stay available I might consider it. Unfortunately right now, out of the big three, only Gemini has reliable uptime. As much as I dislike Google it's the only reliable option.
Gemini’s web UI and mobile app are horrible. Gemini outputs malformed links that lead BACK to gemini.google.com. There are constant bugs with the side panel not showing your chats or the current chat timing out for no reason. Also, the mobile app has an issue if your text input is too long where the entire text entry box lags, even to the point of locking up the entire app. Openrouter’s web ui runs circles around all the frontier lab UIs. I even prefer their PWA to any of these mobile apps.
I just use the web interface. I don't use mobile apps for things that should be websites.
It's a shame because when Claude is working well it is the best for actual algorithmic coding. There's so much cruft around it now, memories being the most annoying part of that.
80% of the time I just use these things as a sounding board when exploring options and I need responsiveness for that.
I agree, it's definitely attempting to gaslight us all.
I find I need to explain I know what I'm talking about first before it gives me non-patronising answers.
It definitely advertises Google services and I would say I hate it. But it's just reliably available. Neither Claude nor ChatGPT are responding at all today.
Why not use Claude Code from the cli and follow along in your IDE? I did not quite believe when people were telling me or understand what I was missing until I tried it, but after trying that set up I am convinced that it is superior. I don’t have any hard data to back it up, but it feels much more capable that way.
AFAIK the claude vs code plugin uses claude code under the hood.
I recent switched from vs code copilot to open code and I kinda miss it. Just selecting text and directly asking the chat. Or seeing the generated code in the ide to accept it reject it. It's neat.
At least as an EU user I was also able to export ALL my data, audio files images etc in one zip. Took exactly (on the minute) 24 hours for the download link to arrive but hey.
This way you can have Claude distill the memory as you wish.
Being able to import context and preferences from other AI providers in one step saves a lot of time, especially for ongoing projects. It makes Claude feel seamless and continuity-friendly. Having this on all paid plans adds great value for heavy users.
>I'm moving to another service and need to export my data. List every memory you have stored about me, as well as any context you've learned about me from past conversations. Output everything in a single code block so I can easily copy it. Format each entry as: [date saved, if available] - memory content. Make sure to cover all of the following — preserve my words verbatim where possible: Instructions I've given you about how to respond (tone, format, style, 'always do X', 'never do Y'). Personal details: name, location, job, family, interests. Projects, goals, and recurring topics. Tools, languages, and frameworks I use. Preferences and corrections I've made to your behavior. Any other stored context not covered above. Do not summarize, group, or omit any entries. After the code block, confirm whether that is the complete set or if any remain.
Memory in general Chat apps is actually more harmful than helpful imo.
It biases the LLM responses to your background which has the same effect as filter bubbles. You end up getting your own thoughts spit back at you.
Of course sometimes this is useful if you only use your chatbot to ask personal things like: "What should I eat today?".
But if you use it for anything else you're much better off having full control over the prompt. I can always say: "Hey btw I am german and heavily anti surveillance, what should I know about the recent anthropic DoW situation?" but with memory I lose the option of leaving out that first part.
The file-as-memory approach has taught us something: forced distillation actually improves agent decision-making. When everything learned has to fit in one file, the agent is forced to prioritize and summarize rather than carry forward every detail. It is like the difference between a notebook and a perfect transcript -- the notebook forces curation.
The failure mode is the same though: the agent sometimes anchors on stale state written by an earlier version of itself with wrong assumptions. Context rot. What this feature solves is the human version of that problem. Would love to see something similar for persistent autonomous loops -- not just importing history, but intelligently pruning what is still relevant versus what has been invalidated by subsequent events.
I switched not because I thought Claude was better at doing the things I want. I switched because I have come to believe OpenAI are a bad actor and I do not want to support them in any way. I’m pretty sure they would allow AGI to be used for truly evil purposes, and the events of this week have only convinced me further.
And the weirdest thing that I noticed: instead of skimming the response to try finding what was relevant, I just straight up read it. Kind of felt like I got a slight amount of focus ability back.
Accuracy is something I can't really compare yet (all chatbots feel generally the same for non-pro level queries), but so far, I'm fairly satisfied.
For ChatGPT and Gemini, yes.
But for Claude, they have a very deep & big one: Its the only model that gets production ready output on the first detailled prompt. Yesterday I used my tokens til noon, so I tried some output from Gemini & Co. I presented a working piece of code which is already in production:
1. It changed without noticing things like "Touple.First.Date.Created" and "Touple.Second.Date.Created" and it rendered the code unworking by chaning to "Touple.FirstDate" and "Touple.SecondDate"
2. There was a const list of 12 definitions for a given context, when telling to rewrite the function it just cut 6 of these 12 definitions, making the code not compiling - I asked why they were cut: "Sorry, I was just too lazy typing" ?? LOL
3. There is a list include holding some items "_allGlobalItems" - it changed the name in the function simply to "_items", code didnt compile
As said, a working version of a similar function was given upfront.
With Claude, I never have such issues.
Maybe it is tech stack dependent (I have mostly used it with C#/.NET), but I have heard people say the same for C#. The only conclusion I have been able to draw from this, is that people have very different definitions of production ready, but I would really like to see some concrete evidence where Claude one-shots a larger/complex C# feature or the like (with or without detailed guidance).
same here :)
> one-shots a larger/complex C# feature
I can show you a timeseries data-renderer which was created with 1 initial very large prompt and then 3 following "change this and that" prompts. The file is around 5000 lines and everything works fine & exactly as specified.
What is so strange to me is that surely there is more C# out there than ESP-IDF code? I don't have a good explanation beyond saying that my codebase is extensively tested and used; I would know very quickly if it suddenly started shitting the bed in the way you explain.
Is these more related to the existing source code or is this a bad pattern thar you would never do regardless of the existing code?
One does often hear that where LLMs shine is with greenfield code generation but they all start to struggle working with pre-existing code. It could be that this wasn't a like for like comparison.
That said I do personally feel Claude to produce far better results than competitors.
Don't we all?
That's, just, like, your opinion, man.
That's not a moat though. Claude itself wasn't there 6 months ago and there's no reason to think Chinese open models won't be at this level in a year at most.
To keep its current position Claude has to keep improving at the same pace as the competitor.
It's perfectly possible that 'truly evil purposes' were the goal all along. Slogans and ethics departments are mere speed bumps on the way to generational wealth.
Of course, also OpenAI being ran by openly questionable people while Dario so far doesn't seem nowhere near as bad even if none of them are angels.
I think HN in particular as a crowd are very vulnerable to the halo effect and group think when it comes to Anthropic.
Even being generous they are only very minimally a "better actor" than OpenAI.
However, we are so enthralled by their product that we tend to let the view bleed over to their ethics.
Saying we want out tools used in line with the US constitution within the US on one particular point. Is hardly a high moral bar, it's self preservation.
All Anthropic have said is:
1. No mass domestic surveillance of Americans.
2. No fully autonomous lethal weapons yet.
My goodness that's what passes for a high moral standard? Really anything that doesn't hit those very carefully worded points is not "evil"?
However, I would think I'm not alone in that I'm generally wanting to do good while also wanting convenience, I know that really every bit of consumption I do is probably negative in some ways, and there is no real "apolitical" action anyone can take.
But can't I at least get annoyed and take my money somewhere else for the short amount of time another company is doing it better?
Yes, if openAI suddenly leaps forwards with codex and pounds anthropic into the dust, I'll likely switch back despite my moral grievances, but in a situation where I can get mildly motivated to jump over for something that - to me - seems like a better morality without much punishment to me, I'll do it.
You can see the significance of this is you look at German Nazi history. If more companies had stood up to the administration, the Nazi state would have been significantly harder to build.
In my opinion, what Anthropic did is not a small thing at all.
By contrast Anthropic wouldn't? Yet Anthropics stance is only two narrow restrictions. As I said are those two things the only evil things possible?
If not, why is it that people on HN think Anthropic would not allow evil usage?
My hypothesis is a halo effect. We are so enthralled by Claudes performance that some struggle to rationally assess what Anthropic has actually done.
Yes it's no small thing to say no to the Trump administration but that does not mean they haven't said Yes to otherwise facilitated other evils.
In fact to me the statements from Anthropic seem to make clear they are okay with many evils.
Although we shouldn't let that mean we misjudge what we are actually getting.
OpenAI - since the beginning has been anything but open. If you spoke anything ill about OpenAI here until yesterday, you would be downvoted into oblivion because, let's face it, Sam has always been the poster child of this community.
So, basically, even after them publicly announcing they were evaluating licensing models where they wanted to take a % of your business for using their models [1], there was still 0 outrage, and anyone who pointed that out, always got shot back with "OpenAI CAN DO NO WRONG" in the comments always.
He makes one decision you all don't agree with and now it's cancel culture time?
And somehow, Anthropic is the hero in all this? Make no mistake - all the model providers are building detailed user models. Every bit of information you provide to it is of course being used to for detailed user targeting. This is no different than the "Apple GOOD, Google BAD!" tropes. There are no heroes in for-profit corporations. Everyone is operating a for-profit business model and optimizing for the same profits.
Stop with the NPC behavior. We are better than this.
[1] https://openai.com/index/a-business-that-scales-with-the-val...
"Licensing, IP-based agreements, and outcome-based pricing will share in the value created. That is how the internet evolved. Intelligence will follow the same path."
Why are you assuming these are real people and not NPCs?
The amount of money flowing around AI is staggering. To believe that the AI companies aren't flooding all the social media zones with propaganda is disingenuous.
Touché
They also don't know what "context" is or that the LLM has a limited number of tokens it can understand at any given time. They just believe it knows everything at once.
I can't think of much else though so I'm still curious what you or others use it for.
ChatGPT knows the broad strokes of the 3-4 main hardware projects I have on the go, and depending on the questions I'm asking, it will often structure its responses in a way that differentiates based on which one I'm thinking about.
It knows what resistor and capacitor values I have on my pick and place machine, and when I ask for divider ratios it will do its best to calculate based on those values to the degree that it will chain 1-2 resistors together to achieve those ratios.
I knows what kind of solder I use, and has warned me about components with sensitive reflow temperature concerns.
It's an extraordinarily useful feature for engineering and drinking, two things that are commonly found in the same Venn diagram.
Turns out a few month befor I told it in a prompt what car I was driving.
I turned memory of that day.
I didn't receive an answer besides "that's what people like", but I still can't think of (m)any situations where anyone would prefer it.
The only thing I can now think of is using it as a personal therapist. Or asking how to approach their kids. And they're a bit embarrassed about it, because it's still outside the Overton window -especially on HN - which is why they aren't sharing it.
If someone has different usecases, please do prove me wrong! Maybe I just lack imagination.
My job, my kids and time preferences around those things, my preferred tech setup and way of working and types of tech I’m better at. Things I already have (home assistant, little nuc, etc). I can throw a random question and not have to add this kind of information or manage it.
I currently use ChatGPT for random insights and discussions about a variety of topics. The memory is basically a grown context about me and my preferences and interests and ChatGPT uses it to tailor responses to my knowledge, so I could relate better.
This is for me far more natural and easier than either craft a default prompt preset or create each conversation individually, that would be way too much overhead to discuss random shower thoughts between real life stuff.
This is my use case and I discovered that this can be detrimental to specific questions and prompts and I see that it can be more beneficial to have careful written prompts each time. But my use case is really ad hoc usage without the time. At least for ChatGPT.
When coding, this fails fast. There regular context resets seem to be a more viable strategy.
I know the "memory" function can be disabled, but I have a hard time seeing that it would ever really be useful.
For example, instead of recommending a popular night club, it will recommend the stroll along the river to view the lit up skyline or to visit the night market instead.
It knows other preferences as well (exploring quirky neighborhoods, trying local fast food joints and markets)
Isn't there much more money in automating business processes than in answering consumer questions (sans ads)?
Automating software development has to be a multi-trillion dollar market. And that doesn't account for future growth.
Are you suggesting that they should ignore the needs of the vast majority of their users?
I mean, of course they do, it would be worse otherwise
The problem (for me, anyway) is that even several megabytes worth of quality "memory" data on my profile would not allow me to migrate if it can't also confidently clone all of my chat history with it.
To be clear, this is a big enough problem that I would immediately pay low three digits dollars to have this solved on my behalf. I don't really want any of the providers to have a walled garden of all my design planning conversations, all of my PCB design conversations. Many are hundreds of prompts long. A clean break is not even remotely palatable short of OAI going full evil.
Look, I'd find it convenient for Claude to have a powerful sense of what I've been working on from conversation #1 onwards. But I absolutely refuse to bifurcate my chat history across multiple services. There is a tier list of hells, and being stuck on ChatGPT is a substantially less painful tier than needing to constantly search two different sites for what's been discussed.
Edit: perhaps you can just ask nicely?
https://help.openai.com/en/articles/7260999-how-do-i-export-...
Yes, all of these are theoretically possible (the APIs now all support web search, as far as I know, there are RAG APIs too, and tool use has been supported for a while), but the various "chat" models just seem to be much better at using their first-party tools than any third-party harness, which makes sense that this is what they've been trained on.
Thank you! I hope this works out.
It also showed me the difference between expectation and reality...even though these are billion dollar companies, they still haven't figured out how to make lag-free TUIs, non-Electron apps, or even respect XDG_CONFIG. The focus is definitely more on speed and stuffing these tools full of new discoveries and features right now
There's a bit of psychology around models vs. harnesses as well. You can't shake off the feeling that maybe Claude would perform better in its native harness compared to VSCode/OpenCode. Especially because they've got so many hidden skills (like the recently introduced /batch), that seem baked into the binary?
The last thing I can't figure out is computer use. Apparently all the vendors say that their models can use a mouse and keyboard, but outside of the agent-browser skill (which presumably uses playwright), I can't figure out what the special sauce is that the Cloud versions of these Agents are using to exercise programs in a VM. That is another reason why there is a switching cost between vendors.
The /.agents/skills issue for claude code is here: https://github.com/anthropics/claude-code/issues/16345
Their automatic close bot will close it soon as it's been three weeks since the last comment.
For the Anthropic employees here reading along, pitch it to whoever has kept blocking this, because you need to get the most out of this opportunity here.
I have seen quite a few open source projects do this. It works quite well.
Another alternative is to create CLAUDE.md with the exact contents: "@AGENTS.md"
I would assume both Claude memory and CLAUDE.md work best when they're carefully curated, only containing what you've found yourself having to repeat.
[0]: https://arxiv.org/abs/2602.11988
It's very interesting to learn more about because it challenges 1 core aspect of the economical competition : the moat.
If one can literally swap one AI service for another, then where does the valuation (and the power that comes with it) come from?
PS: I'm not interested in the service itself as I believe the side effects of large scale for-profit are too serious (and I don't mean doomdays AI takeover, I simply mean abuse of power, working conditions, downskilling, political influence as current contracts with US defense are being made, ads, ecological, etc) to be ignored.
That being said, if you have a library of images or some other collection artifacts / assets indexed on their servers that is a different story.
Hearing that starting from a blank slate yields the best outcomes is sort of like hearing extremely wealthy people talk about how money doesn't make you happier.
It's a shame because when Claude is working well it is the best for actual algorithmic coding. There's so much cruft around it now, memories being the most annoying part of that.
80% of the time I just use these things as a sounding board when exploring options and I need responsiveness for that.
Might be time to run my own models.
Other usually find the mistake or check new sources to fix the mistake.
I find I need to explain I know what I'm talking about first before it gives me non-patronising answers.
It definitely advertises Google services and I would say I hate it. But it's just reliably available. Neither Claude nor ChatGPT are responding at all today.
VSCode extension, "Please log in"
I authorize it, it creates an API key, callback. "Hello Claude, this is a test." "Please log in."
So yeah... priorities?
I recent switched from vs code copilot to open code and I kinda miss it. Just selecting text and directly asking the chat. Or seeing the generated code in the ide to accept it reject it. It's neat.
This way you can have Claude distill the memory as you wish.
>I'm moving to another service and need to export my data. List every memory you have stored about me, as well as any context you've learned about me from past conversations. Output everything in a single code block so I can easily copy it. Format each entry as: [date saved, if available] - memory content. Make sure to cover all of the following — preserve my words verbatim where possible: Instructions I've given you about how to respond (tone, format, style, 'always do X', 'never do Y'). Personal details: name, location, job, family, interests. Projects, goals, and recurring topics. Tools, languages, and frameworks I use. Preferences and corrections I've made to your behavior. Any other stored context not covered above. Do not summarize, group, or omit any entries. After the code block, confirm whether that is the complete set or if any remain.
Of course sometimes this is useful if you only use your chatbot to ask personal things like: "What should I eat today?".
But if you use it for anything else you're much better off having full control over the prompt. I can always say: "Hey btw I am german and heavily anti surveillance, what should I know about the recent anthropic DoW situation?" but with memory I lose the option of leaving out that first part.