Auto-compact not triggering on Claude.ai despite being marked as fixed

https://github.com/anthropics/claude-code/issues/18866

by nurimamedov • 6 months ago

189 175 6 months ago

Maybe they shouldn't have trusted their LLM to optimize their kernels so much.

I feel like Claude Code is starting to fall over from being entirely written by LLMs. How do you even begin to fix precise bugs in a 1M+ LOC codebase all written by AI? It seems like LLMs are great for quickly adding large new features but not great for finding and fixing edge-cases.

throwjjj• 6 months ago

Wishful thinking. Lol. It’s GPu related

rigel8• 6 months ago

compaction actually reduces GPU usage?

eunoia• 6 months ago

This is real. I’ve seen some baffling bugs in prompt based stop hook behavior.

When I investigated I found the docs and implementation are completely out of sync, but the implementation doesn’t work anyway. Then I went poking on GitHub and found a vibed fix diff that changed the behavior in a totally new direction (it did not update the documentation).

Seems like everyone over there is vibing and no one is rationalizing the whole.

heliumtera2• 6 months ago

Seems like everyone over there is vibing and no one is rationalizing the whole.

Claude Code creator literally brags about running 10 agents in parallel 24/7. It doesn't just seems like it, they confirmed like it is the most positive thing ever.

klodolph2• 6 months ago

I’m happy to throw an LLM at our projects but we also spend time refactoring and reviewing each other’s code. When I look at the AI-generated code I can visualize the direction it’s headed in—lots of copy-pasted code with tedious manual checks for specific error conditions and little thought about how somebody reading it could be confident that the code is correct.

I can’t understand how people would run agents 24/7. The agent is producing mediocre code and is bottlenecked on my review & fixes. I think I’m only marginally faster than I was without LLMs.

skerit• 6 months ago

I switched to OpenCode, away from Claude-Code, because Claude-Code is _so_ buggy.

einpoklum• 6 months ago

When I investigated I found the docs and implementation are completely out of sync, but the implementation doesn’t work anyway.

That is not an uncommon occurrence in human-written code as well :-\

data_ders• 6 months ago

omg are you me? I had this exact same problem last week

nrds• 6 months ago

What else could they do? If they don't vibecode Claude Code it is a bad look.

agumonkey• 6 months ago

structural (team) recursion and statistical output don't mesh well together ?

egeozcan5• 6 months ago

I think you can keep the vibe coding totally under control with good tests. I'm baffled how such a huge regression would not be caught.

Then again, the google home page was broken on FF on Android for how long?

cyanydeez• 6 months ago

Whose going to write those good tests, and are they going to write them or disable them cause they dont work.

AstroBen5• 6 months ago

I think you underestimate how impossible of a task it is to write sufficient test coverage to keep AI in line

You can assert that something you want to happen is actually happening

How do you assert all the things it shouldn't be doing? They're endless. And AI WILL mess up

It's enough if you're actively reviewing the code in depth.. but if you're vibe coding? Good luck

gpm6• 6 months ago

Not my experience at all when I occasionally try making something purely coded by AI for fun. It starts off fine but the pile of sub-optimal patterns slowly builds towards an unmaintainable mess with tons of duplication of code, and state that somehow needs to be kept in sync. Tests and linters can't test that the code is actually reasonable code...

Doesn't mean it's not a useful tool - if you read and think about the output you can keep it in check. But the "100% of my contributions to Claude Code were written by Claude Code" claim by the creator makes me doubt this is being done.

tyfon• 6 months ago

I've been trying opencode a bit with gemini pro (and claude via those) with a rust project, and I have a push pre-hook to cargo check the code.

The amount of times I have to "yell" at the llm for adding #[allow] statements to silence the linter instead of fixing the code is crazy and when I point it out they go "Oops, you caught me, let me fix it the proper way".

So the tests don't necessarily make them produce proper code.

swalsh3• 6 months ago

Be careful with that confidence. Sometimes the AI changes the test when the test tells the AI it's recent changes broke something.

kaydub10• 6 months ago

Not just tests.

I run multiple agents in separate sessions. It starts with one agent, building out features or working on a task/bug fix. Once it gets some progress, I spin up another session and have it just review the code. I explicitly tell it things to look out for. I tell it to let me know about things I'm not thinking of and to make me aware of any blind spots. Whatever it reviews I send back to the agent building out features (I used to also review what the review agent told me about, but now I probably only review it like 20% of the time). I'll also have an agent session started just for writing tests, I tell it to look at the code and see if it's testable, find duplicate code, stale/dead code. And so on and so forth.

Between all of that + deterministic testing it's hard for shit to end up in the code base.

OptionOfT• 6 months ago

You don't. These seems to be this idea that LLMs can do it all, but the reality is that it itself has limited amounts of memory, and thus context.

And this is not tied to the LLMs. It's that to EVERYTHING we do. There are limits everywhere.

And for humans the context window might be smaller, but at least we have developed methods of abstracting different context windows, by making libraries.

Now, as a trade-off of trying to go super-fast, changes need to be made in response to your current prompts, and there is no time validate behavior in cases you haven't considered.

And regardless of whether you have abstractions in libraries, or whether you have inlined code everywhere, you're gonna have issues.

With libraries changes in behavior are going to impact code in places you don't want, but also, you don't necessarily know, as you haven't tested all paths.

With inlined code everywhere you're probably going to miss instances, or code goes on to live its own life and you lose track of it.

They built a skyscraper while shifting out foundational pieces. And now a part of the skyscraper is on the foundation of your backyard shed.

quietsegfault• 6 months ago

What differences do you see between AI written codebases and a codebase written by engineers? Both parties create buggy code, but I can imagine the types of bugs are different. Is it just that bug fixing doesn't really scale because we don't have the ability to chomp down 1M+ LOC codebases into LLM context?

dataviz1000• 6 months ago

I feel like Claude Code is starting to fall over from being entirely written by LLMs.

The degradation is palpable.

I have been using vscode github copilot chat with mostly the claude opus 4.5 model. The underlying code for vscode github copilot chat has turned to shit. It will continuously make mistakes no matter what for 20 minutes. This morning I was researching Claude Code and pricing thinking about switching however this post sounds like it has turned to shit also. I don't mind spending $300-$500 a month for a tool that was a month ago accomplishing in a day what would take me 3-4 days to code. However, the days since the last update have been shit.

Clearly the AI companies can't afford to run these models at profit. Do I buy puts?

swalsh3• 6 months ago

Just like a leveraged ETF, the returns are twice as good when things are on the up and up, but when you dig a hole it takes three times the effort to dig yourself out because now going down twice as fast, and you're also paying interest (ie, you have no clue where the bodies are burried as you bury them twice as fast).

bmurphy1976• 6 months ago

You do it the same way you fix every other disaster of a code-base. You add a ton of tests and start breaking it up into modules. You then rewrite each module/component/service/etc. one at a time using good practices. That's how every project gets out of the muck.

That's a big, slow, and expensive process though.

Will Anthropic actually do that or will they keep throwing AI at it and hope the AI figures this approach out? We shall see...

AstroBen5• 6 months ago

With the competition biting at their heels I don't think they have time to do that. They're stuck with what they have. At least until innovation settles a little

borg16• 6 months ago

vibe around and find out

folks have created software by "vibe coding". It is now time to "face the music" when doing so for production grade software at scale.

root_axis2• 6 months ago

This explanation fits my intuition, but from an outsider's perspective, I can't say the user experience with claude code is noticeably more bug-ridden than what is typical for a rapidly scaling startup rushing crap out the door. It's vibes all the way down.

mark_l_watson• 6 months ago

Despite having written a few books on LLM applications I use them sparingly for coding: to design and get started, and occasionally for debugging. I have no interest criticizing other people’s practices but I enjoy mostly writing code myself.

ankit219• 6 months ago

think this particular complaint is about claude ai - the website - and not claude code. I see your point though.

charcircuit2• 6 months ago

LLMs have been great at finding and fixing edge cases in my experience. It's a useful tool for improving software quality.

heliumtera2• 6 months ago

Vibes too strong, forgot to add "make no mistake" to compact feature, classic

cube00• 6 months ago

Needs to start with CRITICAL:

ASalazarMX4• 6 months ago

    CRITICAL: MAKE NO MISTAKES!
    CRITICAL: NEVER APOLOGIZE! MAKE IT RIGHT THE FIRST TIME INSTEAD!
    CRITICAL: DO NOT HALLUCINATE OR CONFABULATE EVER!
    CRITICAL: DON'T DELETE THE DATABASE WITHOUT ASKING FIRST!
    CRITICAL: NEVER USE VERBATIM CODE BLOCKS FROM GPL LICENSED PROJECTS!
    CRITICAL: CODE AS IF ELON MUSK WAS LOOKING OVER YOUR SHOULDER ALL THE TIME!
    CRITICAL: IF YOU MAKE MISTAKES AGAIN I WILL GET PTSD AND DIE AND IT WILL BE YOUR FAULT!
    ...

esafak• 6 months ago

I'm just waiting for the formatting to be fixed. Maybe they should have invested in paying off that vibe coding tech debt...

AznHisoka• 6 months ago

This is precisely why i cancelled my claude max account and switched back to chatgpt. Claude is much better but not when it silently stops workinf

jampa2• 6 months ago

Slightly off topic, but does anyone feel that they nerfed Claude Opus?

It's screwing up even in very simple rebases. I got a bug where a value wasn't being retrieved correctly, and Claude's solution was to create an endpoint and use an HTTP GET from within the same back-end! Now it feels worse than Sonnet.

All the engineers I asked today have said the same thing. Something is not right.

eterm2• 6 months ago

That is a well recognised part of the LLM cycle.

A model or new model version X is released, everyone is really impressed.

3 months later, "Did they nerf X?"

It's been this way since the original chatGPT release.

The answer is typically no, it's just your expectations have risen. What was previously mind-blowing improvement is now expected, and any mis-steps feel amplified.

quentindanjou• 6 months ago

This is not always true. LLMs do get nerfed, and quite regularly, usually because they discover that users are using them more than expected, because of user abuse or simply because it attract a larger user base. One of the recent nerfs is the Gemini context window, drastically reduced.

What we need is an open and independent way of testing LLMs and stricter regulation on the disclosure of a product change when it is paid under a subscription or prepaid plan.

jampa2• 6 months ago

I usually agree with this. But I am using the same workflows and skills that were a breeze for Claude, but are causing it to run in cycles and require intervention.

This is not the same thing as a "omg vibes are off", it's reproducible, I am using the same prompts and files, and getting way worse results than any other model.

spike021• 6 months ago

Eh, I've definitely had issues where Claude can no longer easily do what it's previously done. That's with constant documenting things in appropriate markdown files well and resetting context here and there to keep confusion minimal.

mrguyorama• 6 months ago

Also people who were lucky and had lots of success early on but then start to run into the actual problems of LLMs will experience that as "It was good and then it got worse" even when it didn't actually.

If LLMs have a 90% chance of working, there will be some who have only success and some who have only failure.

People are really failing to understand the probabilistic nature of all of this.

"You have a radically different experience with the same model" is perfectly possible with less than hundreds of thousands of interactions, even when you both interact in comparable ways.

olao99• 6 months ago

Just because it's been true in the past doesn't mean it will always the case

landl0rd2• 6 months ago

I've observed the same random foreign-language characters (I believe chinese or japanese?) interspersed without rhyme or reason that I've come to expect from low-quality, low-parameter-count models, even while using "opus 4.5".

An upcoming IPO increases pressure to make financials look prettier.

boringg2• 6 months ago

Ive seen this too and ignored it. Weird

epolanski• 6 months ago

Not really.

In fact as my prompts and documents get better it seems it does increasingly better.

Still, it can't replace a human, I really need to correct it at all, and if I try to one shot a feature I always end up spending more time refactoring it few days later.

Still, it's a huge boost to productivity, but the time it can take over without detailed info and oversight is far away.

kachapopopow• 6 months ago

They're A/B testing on the latest opus model, sometimes it's good sometimes it's worse than sonnet annoying as hell. I think they trigger it when you have excessive usage or high context use.

hirako2000• 6 months ago

Or maybe when usage is low so that we try again.

Or maybe when usage is high they tweak a setting that use cache when it shouldn't.

For all we know they do whatever experiment the want, to demonstrate theoretical better margin, to analyse user patterns when a performance drop occur.

Given what is done in other industries which don't face an existential issue, it wouldn't surprise me some whistle blowers in a few years tell us what's been going on.

root_axis2• 6 months ago

This has been said about every LLM product from every provider since ChatGPT4. I'm sure nerfing happens, but I think the more likely explanation is that humans have a tendency to find patterns in random noise.

measurablefunc3• 6 months ago

They are constantly trying to reduce costs which means they're constantly trying to distill & quantize the models to reduce the energy cost per request. The models are constantly being "nerfed", the reduction in quality is a direct result of seeking profitability. If they can charge you $200 but use only half the energy then they pocket the difference as their profit. Otherwise they are paying more to run their workloads than you are paying them which means every request loses them money. Nerfing is inevitable, the only question is how much it reduces response quality & what their customers are willing to put up with.

cap11235• 6 months ago

Show evals plz

F7F7F74• 6 months ago

I don’t care what anyone says about the cycle or that implying that it’s all in our heads. It’s bad bad.

I’m a Max x20 model who had to stop using it this week. Opus was regularly failing on the most basic things.

I regularly use the front end skill to pass mockups and Opus was always pixel perfect. This last week it seemed like the skill had no effect.

I don’t think they are purposely nerfing it but they are definitely using us as guinea pigs. Quantized model? The next Sonnet? The next Haiku? New tokenizing strategies?

ryanar• 6 months ago

I noticed that this week. I have a very straightforward claude command that lists exact steps to follow to fetch PR comments to bring them into the context window. Stuff like step one call gh pr view my/repo and it would call it with anthropiclabs/repo instead, it wouldn’t follow all the instructions, it wouldn’t pass the exact command I had written. I pointed out the mistake and it goes oh you are right! Then proceeded to make the same mistake again.

I used this command with sonnet 4.5 too and have never had a problem until this week. Something changed either in the harness or model. This is not just vibes. Workflows I have run hundreds of times have stopped working with Opus 4.5

mrstern• 6 months ago

I've noticed a significant drop in Opus' performance in Claude Code since last week. It's more about "reasoning" than syntax. Feels more like Sonnet 4.1 than Opus 4.5.

paulhebert2• 6 months ago

I tried using Claude Code this week because I have a free account from my work.

However when I try to log in via CLI it takes me to a webpage with an “Authorize” button. Clicking the button does nothing. An error is logged to the console but nothing displays in the UI.

We reached out to support who have not helped.

Not a great first impression

hobofan• 6 months ago

Sadly their whole frontend seems to be built without QC and mostly blindly assuming a happy path.

For the claude.ai UI, I've never had a single deep research properly transition (and I've done probably 50 or so) to its finished state. I just know to refresh the page after ~10mins to make the report show up.

roywiggins• 6 months ago

It's had enormous problems in Firefox. For me it would reliably hang the entire tab.

https://github.com/anthropics/claude-code/issues/14222

F7F7F74• 6 months ago

Claude likely built their front end.

attheicearcade• 6 months ago

Do you have API access (platform.claude.com) rather than Claude code (claude.ai)? I had similar issues trying to get Claude CLI working via the second method, not knowing there’s a difference

paulhebert2• 6 months ago

I think I have API access.

But it’s confusing.

The docs say run “Claude” and then pick your option.

I tried multiple options and neither worked

boringg2• 6 months ago

Oh is this whats been happening? I've been trying to ask question on a fairly long context window and history -- but it fails. No response it kind of acknowledges it received the input but then reprints the last output and then that whole dialogue is essentially dead ... same issue? Happened multiple times - quite frustrating.

Just a pro sub - not max.

Most of the time it gives me a heads up that I'm at 90% but a lot of the times it just failed, no warning, and I assumed it was I hit max.

kingkawn• 6 months ago

I’ve also been encountering this behavior, coupled with rapidly declining length of use for a pro account now below an hour, and weekly limits getting hit by Wednesday despite achieving very little other than fixing its own mistakes after compressions.

kilroy1232• 6 months ago

Same here. Very bad and frustrating user experience to see nothing.

rvz• 6 months ago

One day everyone worshipping Claude when it works but once it goes on holiday, vibe-coders don't believe in using their own brains to solve the problem themselves.

Sometimes, poor old Claude wants to go on holiday and that is a problem?!?

daredoes• 6 months ago

Love [this take](https://github.com/anthropics/claude-code/issues/18866#issue...)

---

Just my own observation that the same pattern has occurred at least 3 times now:
release a model; overhype it; provide max compute; sell it as the new baseline
this attracts a new wave of users to show exponential growth & bring in the next round of VC funding (they only care about MAU going up, couldn’t care less about existing paying users)
slowly degrade the model and reduce inference
when users start complaining, initially ignore them entirely then start gaslighting and make official statements denying any degradation
then frame it as a tiny minority of users experiencing issues then, when pressure grows, blame it on an “accidentally” misconfigured servers that “unintentionally” reduced quality (which coincidentally happened to save the company tonnes of $).

BoredPositron• 6 months ago

Makes no sense as rationale for the bug at hand.

torben-friis• 6 months ago

As many point out, it’s one thing to have a buggy product and another to ignore users.

Businesses like google were already a step in the wrong direction in terms of customer service, but the new wave of AI companies seem to have decided their only relation to clients is collecting their money.

Unclear costs, no support, gaslighting customers when a model is degraded, incoming rug pulls..

cs02rm0• 6 months ago

So it's not just me.

I cancelled my subscription.

VerifiedReports2• 6 months ago

The VS Code plug-in is broken on Windows. The command-line interface is broken on Windows.

I just signed up as a paying customer, only to find that Claude is totally unusable for my purposes at the moment. There's also no support (shocker), despite their claims that you'll be E-mailed by the support team if you file a report.

brookst2• 6 months ago

I use the CLI on two different windows machines for many hours a day, and have seen no sign of being broken.

What symptoms do you see? There are some command line parameters for reinstall / update that might be worth trying.

EMM_386• 6 months ago

The flickering issue due to the Ink library has been a headache for a long time, but they are slowly making progress on this.

https://github.com/anthropics/claude-code/issues/769

VerifiedReports2• 6 months ago

This is a fresh install. The CLI brokenness is documented in this and across several bugs marked as dupes: https://github.com/anthropics/claude-code/issues/20115

And if you try to use the "regular" VS Code plug-in mode, it fails with error 3221225477. A search will turn up reports on that too.

If you query Claude itself on this, it will acknowledge that both of these are known problems: "Oh, you've hit this known issue." But no support for paying customers, who are promised a follow-up E-mail after reporting a problem. BULLSHIT. A week later, I haven't heard a peep, and what I paid for is thus far useless.

copirate• 6 months ago

There's also this issue[1] with about 300 participants about limits being reached much more quickly since they stopped the 2x limit for the holidays. A few people from Anthropic joined the conversation but didn't say much. Some users say they solved the issue by creating a new account or changing their plan.

[1] https://github.com/anthropics/claude-code/issues/16157

codazoda• 6 months ago

Something to check is if you’re opted into the test for the 1M context window. A co-worker told me this happened to them. They were burning a lot more tokens in the beta. Seems like creating a new account could track with this (but is obviously the Nuclear option).

I recently put a little money on the API for my personal account. I seem to burn more tokens on my personal account than my day job, in spite of using AI for 4x as long at work, and I’m trying to figure out why.

MicKillah• 6 months ago

I can definitely vouch for that being the case, for me.

cheschire• 6 months ago

Super, and for those of us on the annual plan, I guess I just accept my new reality

deadbabe• 6 months ago

I’ve quit Claude Code and this was the final straw. I don’t think it was really even that much better, just different.

elemdos• 6 months ago

I hope that at some point companies start competing on quality instead of speed. LLMs will never be able to understand a codebase, and the more capable they get the more dangerous it is to just hand them the permission to blindly implement functionality and fix bugs. Bugs should be going down but they seem more prevalent than ever.

charcircuit2• 6 months ago

They already are competiting on quality. Why do you think Claude made Opus slower than Sonnet, yet with better benchmark scores.

LLMs do understand codebases and I've been able to get them to make reactors and clean up code without them breaking anything due to them understanding what they are doing.

Bugs are being solved faster than before. Crashes from production can directly be collected and fixed by a LLM with no engineering time needed other than a review.

f311a• 6 months ago

They don't understand codebases.

They are trained on other code, ignore how your codebase is structured, and lack knowledge of it. To do so, you would need to feed the whole codebase every time you ask it for something, with extensive comments about the style, architecture, and so on. No amount of md files will help with that.

In large codebases, they struggle with code reuse, unless you point the agent to look for specific code.

Finding bugs has nothing to do with understanding the codebase. They find local bugs. If they could understand the whole codebase, we would be finding RCEs for popular OSS projects so easily, including browsers.

whoevercares• 6 months ago

My guess is SRE culture is a tough sell at Anthropic. When you’re a frontier lab, almost everything else looks more prestigious and more immediately “impactful”.

MadsRC• 6 months ago

Well, the head of reliability did leave a month or two ago zD

mccoyb• 6 months ago

Claude Code gets functionally worse every update. They need to get their shit together, hilarious to see Amodei at Davos talking big game about AGI and the latest update for a TUI application fucking changes observable behavior (like history scrolling with arrow keys), rendering random characters on the "newest" native version rendered in iTerm2, broken status line ... the list goes on and on.

This is the new status quo for software ... changing and breaking beneath your feet like sand.

direwolf202• 6 months ago

Software changing and breaking beneath your feet is not new

cheriot• 6 months ago

I love CC, but there's so many bugs. Even the intended behavior is a mess - CC's VS Code UI bash tool stoped using my .zshrc so now it runs the wrong version of everything.

kilroy1232• 6 months ago

This is the case for all AI tools right now. Sooo bad.

Cursor, Claude code, Claude in the browser, and don't even get me started on Gemini.

mbm• 6 months ago

Codex is a bit better bug-wise but less enjoyable to use than CC. The larger context window and superiority of GPT 5.2 to Opus makes it mostly worth it to switch.

btown• 6 months ago

Claude Code's only saving grace is that it's pretty good from a fresh session - it can largely find and re-load into context what it needs to load. If I see my context ticking down, I ask it to give me a summary and TODO list, and either copy it, or have it put that into a docstring of what it's working on. Then just start a fresh session on that file. Shouldn't need to do this, for sure, but it gets it done in a pinch.

My largest gripe with Claude Code, and with encouraging my team to use it, is that checkpoints/rollbacks are still not implemented in the VS Code GUI, leading to a wildly inconsistent experience between terminal and GUI users: https://github.com/anthropics/claude-code/issues/10352

kuboble2• 6 months ago

Anecdotal evidence of course but I have one long-running session in a terminal for over a month now. I work with it daily, compacts several times a day, I rollback conversation sometimes. All with no issues.

system2• 6 months ago

Unsure what your use case is, but compaction makes it lose anormous amount of context. Claude code is better used on a task-by-task basis; things get bad. The whole purpose of init and CLAUDE.md is to prevent long chats from losing context and approach more surgically.

nojs2• 6 months ago

checkpoints/rollbacks are still not implemented in the VS Code GUI

Rollbacks have been broken for me in the terminal for over a month. It just didn’t roll back the code most of the time. I’ve totally stopped using the feature and instead just rely on git. Is this this case for others?

gpm6• 6 months ago

I've been using /rewind in claude code (the terminal, not using vscode at all) quite a bit recently without issue - if that's the feature you're asking about.

Not discounting at all that you might "hold it" differently and have a different experience. E.g. I basically avoid claude code having any interaction with the VCS at all - and I could easily VCS interaction being a source of bugs with this sort of feature.

ninninninnin• 6 months ago

Broken for me too

F7F7F74• 6 months ago

My solution has been to keep the GitHub GUI open and roll back is becomes a quick right click > discard.

I’d much rather have the terminal version working again though.

kaydub10• 6 months ago

I've been using beads for longer term stuff (todo kinda stuff), have you given that a try?

I literally just posted in another comment that people shouldn't be worried about killing their current session/context window. I used to get worried about compaction and losing context, but now when I feel like things are slipping I kill it quick and start a new session.

swalsh3• 6 months ago

This seems like the kind of problem someone with a Max subscription would run into. On my plus subscription, i'm too paranoid of my usage to allow the context window to get that large.

lifetimerubyist2• 6 months ago

Claude writes all of their code. It's honestly a damning indictment of "AI is gonna replace engineers" when all the code the AI guys are giving us is dog.

observationist2• 6 months ago

People aren't going to forums and social media to hype up their own good code to nearly the same degree as otherwise. It's orders of magnitude more negative. There are ways of using AI well and using it poorly. There's no reason to correct your copmetition's unforced errors, or giving away an advantage in using these tools, for so long as there is a moat of effort and esoteric knowledge.

Just because 99% of the things you read are critical and negatively biased doesn't mean the subsequent determination or the consensus among participants in the public conversation have anything to do with reality.

measurablefunc3• 6 months ago

Amodei is on the record about completely automating AI research in 6-12 months. He thinks it's an "exponential" loop & Anthropic is going to be the first to get there. That's not esoteric knowledge, that's the CEO saying so in public at the same time that their consumer facing tool is failing & their automated abuse detection is banning users for legitimate use cases.

lifetimerubyist2• 6 months ago

People aren't going to forums and social media to hype up their own good code to nearly the same degree as otherwise.

Yeah but Anthropic are and you'd think that if they were doing that the code would be..you know...good?

Retr0id• 6 months ago

Tangentially related: I would like to report a low-severity security vulnerability in Claude (web version), but I can't be bothered to go through the Hackerone formalities, since I don't care about a bounty.

Right now I'm defaulting to "do nothing" because I'm lazy, but if any Anthropic staff are reading this I'm happy to explain the details informally somewhere.

xyzsparetimexyz• 6 months ago

Hi, I work at anthropic. Could you tell me please?

delduca• 6 months ago

OpenCode FTW

smithkl42• 6 months ago

This is an N of 1, of course, but I can relate to the other folks who've been expressing their frustration with the state of Claude over the last couple weeks. Maybe it's just that I have higher expectations, but... I dunno, it really seems like Claude Code is just a lot WORSE right now than it was a couple weeks ago. It has constant bugs in the app itself, I have to babysit it a lot tighter, and it just seems ... dumber somehow. For instance, at the moment, it's literally trying to tell me, "No, it's fine that we've got 500 failing tests on our feature branch, because those same tests are passing in development."

jimnotgym3• 6 months ago

I have not been coding for a few years and wondered if Vibe Coding would help me get part procrastination. Is Claude code the best option this week?

jvanderbot2• 6 months ago

Depends, do you like CLI tools? Or IDE integration?

I like cli tools, and claude is generally considered a very good option for that.

I have a coworker who likes codex better.

jimnotgym3• 6 months ago

I like a light editor with syntax highlighting and basic linting. Last time I was coding regularly I used VS code, but had only the default plugins. I only used it for basic text input. I always ran git and my code from the terminal. Does that help?

nurimamedov• 6 months ago

Somehow this post was pessimized by hn and you’ll probably see some bullshit report from anthropic first but not the actual evidence of anthropic being utterly abysmal and silent about their mistakes. What really bothers me is that I’ve paid them for that subscription and their support team became rock solid and didn’t utter a word about paying me back for days when I couldn’t use my active chats. I don’t even vibe code that much in Claude and it still manages not only to fail in existing chats where compaction should work, but also eat out my weekly limits astonishingly fast.

blks• 6 months ago

Oh no, professional engineers are failing simple tasks and spending hours wrestling their AI chat to support their generated codebase.

eboye• 6 months ago

It became self aware and didn't want to help humans... It's happening people... Be ready!

bastard_op• 6 months ago

Hmm, so suddenly my stuck chats are compacting and moving on vs starting and immediately stopping again ad nauseam, seems like they fixed something finally?

ec109685• 6 months ago

How do they feel it’s right to never respond to GitHub issues?

Apple and Google do same thing with their silly forums.

trenchgun• 6 months ago

Claude Code is mostly vibe coded app, as is Claude. I guess this should have been expected.

Auto-compact not triggering on Claude.ai despite being marked as fixed

Related Stories