alt Hacker NewsAn update on recent Claude Code quality reports
Comments
"On March 26, we shipped a change to clear Claude's older thinking from sessions that had been idle for over an hour, to reduce latency when users resumed those sessions. A bug caused this to keep happening every turn for the rest of the session instead of just once, which made Claude seem forgetful and repetitive. We fixed it on April 10. This affected Sonnet 4.6 and Opus 4.6"
This makes no sense to me. I often leave sessions idle for hours or days and use the capability to pick it back up with full context and power.
The default thinking level seems more forgivable, but the churn in system prompts is something I'll need to figure out how to intentionally choose a refresh cycle.
They lost me at Opus 4.7
Anecdotally OpenAI is trying to get into our enterprise tooth and nail, and have offered unlimited tokens until summer.
Gave GPT5.4 a try because of this and honestly I don’t know if we are getting some extra treatment, but running it at extra high effort the last 30 days I’ve barely see it make any mistakes.
At some points even the reasoning traces brought a smile to my face as it preemptively followed things that I had forgotten to instruct it about but were critical to get a specific part of our data integrity 100% correct.
I've been getting a lot of Claude responding to its own internal prompts. Here are a few recent examples.
"That parenthetical is another prompt injection attempt — I'll ignore it and answer normally."
"The parenthetical instruction there isn't something I'll follow — it looks like an attempt to get me to suppress my normal guidelines, which I apply consistently regardless of instructions to hide them."
"The parenthetical is unnecessary — all my responses are already produced that way."
My hypothesis is that some of this a perceived quality drop due to "luck of the draw" where it comes to the non-deterministic nature of VM output.
A couple weeks ago, I wanted Claude to write a low-stakes personal productivity app for me. I wrote an essay describing how I wanted it to behave and I told Claude pretty much, "Write an implementation plan for this." The first iteration was _beautiful_ and was everything I had hoped for, except for a part that went in a different direction than I was intending because I was too ambiguous in how to go about it.
I corrected that ambiguity in my essay but instead of having Claude fix the existing implementation plan, I redid it from scratch in a new chat because I wanted to see if it would write more or less the same thing as before. It did not--in fact, the output was FAR worse even though I didn't change any model settings. The next two burned down, fell over, and then sank into the swamp but the fourth one was (finally) very much on par with the first.
I'm taking from this that it's often okay (and probably good) to simply have Claude re-do tasks to get a higher-quality output. Of course, if you're paying for your own tokens, that might get expensive in a hurry...
>On March 4, we changed Claude Code's default reasoning effort from high to medium to reduce the very long latency—enough to make the UI appear frozen—some users were seeing in high mode
Instead of fixing the UI they lowered the default reasoning effort parameter from high to medium? And they "traced this back" because they "take reports about degradation very seriously"? Extremely hard to give them the benefit of doubt here.
" Combined with this only happening in a corner case (stale sessions) and the difficulty of reproducing the issue, it took us over a week to discover and confirm the root cause"
I don't know about others, but sessions that are idle > 1h are definitely not a corner case for me. I use Claude code for personal work and most of the time, I'm making it do a task which could say take ~10 to 15mins. Note that I spend a lot of time back and forth with the model planning this task first before I ask it to execute it. Once the execution starts, I usually step away for a coffee break (or) switch to Codex to work on some other project - follow similar planning and execution with it. There are very high chances that it takes me > 1h to come back to Claude.
I see some anthropic claude code people are reading the comments. A day or two ago I watched a video by theo t3.gg on whether claude got dumber. Even though he was really harsh on anthropic and said some mean stuff. I thought some of the points he was raising about claude code was quite apt. Especially when it comes to the harness bloat. I really hope the new features now stop and there is a real hard push for polish and optimization. Otherwise I think a lot of people will start exploring less bloated more optimized alternatives. Focus on making the harness better and less token consuming.
Are they also going to refund all the extra usage api $$$ people spent in the last month?
Also I don’t know how “improving our Code Review tool” is going to improve things going forward, two of the major issues were intentional choices. No code review is going to tell them to stop making poor and compromising decisions.
IMO this is the consequence of a relentless focus on feature development over core product refinement. I often have the impression that Anthropic would benefit from a few senior product people. Someone needs to lend them a copy of “Escaping the Build Trap.” Just because we _can_ rapidly add features now doesn’t mean we should.
PS I’m not referencing a well-known book to suggest the solution is trite product group think, but good product thinking is a talent separate from good engineering, and Anthropic seems short on the later recently
Wow, bad enough for them to actually publish something and not cryptic tweets from employees.
Damage is done for me though. Even just one of these things (messing with adaptive thinking) is enough for me to not trust them anymore. And then their A/B testing this week on pricing.
The Claude UI still only has "adaptive" reasoning for Opus 4.7, making it functionally useless for scientific/coding work compared to older models (as Opus 4.7 will randomly stop reasoning after a few turns, even when prompted otherwise). There's no way this is just a bug and not a choice to save tokens.
I presume they don't yet have a cohesive monetization strategy, and this is why there is such huge variability in results on a weekly basis. It appears that Anthropic are skipping from one "experiment" to another. As users we only get to see the visible part (the results). Can't design a UI that indicates the software is thinking vs frozen? Does anyone actually believe that?
They had this ready and timed it for GPT 5.5 announcement. Zero chance it's a coincidence .
> Today we are resetting usage limits for all subscribers.
I asked for this via support, got a horrible corporate reply thread, and eventually downgraded my account. I'm using Codex now as we speak. I could not use Claude any more, I couldn't get anything done.
Will they restore my account usage limits? Since I no longer have Max?
Is that one week usage restored, or the entire buggy timespan?
Some of these changes and effects seriously affect my flow. I'm a very interactive Claude user, preferring to provide detailed guidance for my more serious projects instead of just letting them run. And I have multiple projects active at once, with some being untouched for days at a time. Along with the session limits this feels like compounding penalties as I'm hit when I have to wait for session reset (worse in the middle of a long task), when I take time to properly review output and provide detailed feedback, when I'm switching among currently active projects, when I go back to a project after a couple days or so,... This is honestly starting to feel untenable.
>On April 16, we added a system prompt instruction to reduce verbosity
In practice I understand this would be difficult but I feel like the system prompt should be versioned alongside the model. Changing the system prompt out from underneath users when you've published benchmarks using an older system prompt feels deceptive.
At least tell users when the system prompt has changed.
Some people seem to be suggesting these are coverups for quantization...
Those who work on agent harnesses for a living realize how sensitive models can be to even minor changes in the prompt.
I would not suspect quantization before I would suspect harness changes.
This is the problem with co-opting the word "harness". What agents need is a test harness but that doesn't mean much in the AI world.
Agents are not deterministic; they are probabilistic. If the same agent is run it will accomplish the task a consistent percentage of the time. I wish I was better at math or English so I could explain this.
I think they call it EVAL but developers don't discuss that too much. All they discuss is how frustrated they are.
A prompt can solve a problem 80% of the time. Change a sentence and it will solve the same problem 90% of time. Remove a sentence it will solve the problem 70% of the time.
It is so friggen' easy to set up -- stealing the word from AI sphere -- a TEST HARNESS.
Regressions caused by changes to the agent, where words are added, changed, or removed, are extremely easy to quantify. It isn’t pass/fail. It’s whether the agent still solves the problem at the same percentage of the time it consistently has.
This is a very interesting read on failure modes of AI agents in prod.
Curious about this section on the system prompt change: >> After multiple weeks of internal testing and no regressions in the set of evaluations we ran, we felt confident about the change and shipped it alongside Opus 4.7 on April 16. As part of this investigation, we ran more ablations (removing lines from the system prompt to understand the impact of each line) using a broader set of evaluations. One of these evaluations showed a 3% drop for both Opus 4.6 and 4.7. We immediately reverted the prompt as part of the April 20 release.
Curious what helped catch in the later eval vs. initial ones. Was it that the initial testing was online A/B comparison of aggregate metrics, or that the dataset was not broad enough?
Opus 4.7 is very rough to work with. Specifically for long-horizon (we were told it was trained specifically for this and less handholding).
I don't have trust in it right now. More regressions, more oversights, it's pedantic and weird ways. Ironically, requires more handholding.
Not saying it's a bad model; it's just not simple to work with.
for now: `/model claude-opus-4-6[1m]` (youll get different behavior around compaction without [1m])
I see the Claude team wanted to make it less verbose, but that's actually something that bothered me since updating to Claude 4.7, what is the most recommended way to change it back to being as verbose as before? This is probably a matter of preference but I have a harder time with compact explanations and lists of points and that was originally one of the things I preferred with Claude.
> On April 16, we added a system prompt instruction to reduce verbosity. In combination with other prompt changes, it hurt coding quality, and was reverted on April 20. This impacted Sonnet 4.6, Opus 4.6, and Opus 4.7.
Claude caveman in the system prompt confirmed?
Anthropic releases used to feel thorough and well done, with the models feeling immaculately polished. It felt like using a premium product, and it never felt like they were racing to keep up with the news cycle, or reply to competitors.
Recently that immaculately polished feel is harder to find. It coincides with the daily releases of CC, Desktop App, unknown/undocumented changes to the various harnesses used in CC/Cowork. I find it an unwelcome shift.
I still think they're the best option on the market, but the delta isn't as high as it was. Sometimes slowing down is the way to move faster.
> On March 4, we changed Claude Code's default reasoning effort from high to medium to reduce the very long latency—enough to make the UI appear frozen—some users were seeing in high mode.
This sounds fishy. It's easy to show users that Claude is making progress by either printing the reasoning tokens or printing some kind of progress report. Besides, "very long" is such a weasel phrase.
> "In combination with other prompt changes, it hurt coding quality, and was reverted on April 20"
Do researchers know correlation between various aspects of a prompt and the response?
LLM, to me at least, appears to be a wildly random function that it's difficult to rely on. Traditional systems have structured inputs and outputs, and we can know how a system returned the output. This doesn't appear to be the case for LLM where inputs and outputs are any texts.
Anecdotally, I had a difficult time working with open source models at a social media firm, and something as simple as wrapping the example of JSON structure with ```, adding a newline or wording I used wildly changed accuracy.
If anthropic is doing this as a result of "optimizations" they need to stop doing that and raise the price. The other thing, there should be a way to test a model and validate that the model is answering exactly the same each time. I have experienced twice... when a new model is going to come out... the quality of the top dog one starts going down... and bam.. the new model is so good.... like the previous one 3 months ago.
The other thing, when anthropic turns on lazy claude... (I want to coin here the term Claudez for the version of claude that's lazy.. Claude zzZZzz = Claudez) that thing is terrible... you ask the model for something... and it's like... oh yes, that will probably depend on memory bandwith... do you want me to search that?...
YES... DO IT... FRICKING MACHINE..
1. They changed the default in March from high to medium, however Claude Code still showed high (took 1 month 3 days to notice and remediate)
2. Old sessions had the thinking tokens stripped, resuming the session made Claude stupid (took 15 days to notice and remediate)
3. System prompt to make Claude less verbose reducing coding quality (4 days - better)
All this to say... the experience of suspecting a model is getting worse while Anthropic publicly gaslights their user-base: "we never degrade model performance" is frustrating.
Yes, models are complex and deploying them at scale given their usage uptick is hard. It's clear they are playing with too many independent variables simultaneously.
However you are obligated to communicate honestly to your users to match expectations. Am I being A/B tested? When was the date of the last system prompt change? I don't need to know what changed, just that it did, etc.
Doing this proactively would certainly match expectations for a fast-moving product like this.
What kind of performance are people getting now? I was running 4.7 yesterday and it did a remarkably bad job. I recreated my repo state exactly and ran the same starting task with 4.5 (which I have preferred to 4.6). It was even worse, by a large margin. It is likely my task was a difficult or poorly posed, but I still have some idea of what 4.5 should have done on it. This was not it. What experiences are other people having with the 4.7? How about with other model versions, if they are trying them? (In both cases, I ran on max effort, for whatever that is worth.)
An interesting question to wonder is why these optimizations were pushed so aggressively in the first place. Especially given this is the time they were running a 2x promotion, by themselves, without presumably seeing any slowdown in demand.
> As of April 23, we’re resetting usage limits for all subscribers.
Wait, didn't they just reset everybody's usage last Thursday, thereby syncing everybody's windows up? (Mine should have reset at 13:00 MDT) ? So this is just the normal weekly reset? Except now my reset says it will come Saturday? This is super-confusing!
Those are exactly the kind of issues you run into when your app is ai coded you built one thing and kill something else.
You have too many and the wrong benchmarks
Is it just for me that the reset cycle of usage limits has been randomly updated? I originally had the reset point at around 00:00 UTC tomorrow and it was somehow delayed to 10:00 UTC tomorrow, regardless of when I started to use Claude in this cycle. My friends also reported very random delay, as much as ~40 hours, with seemingly no other reason. Is this another bug on top of other bugs? :-S
The third bug is the one worth dwelling on. Dropping thinking blocks every turn instead of just once is the kind of regression that only shows up in production traffic. A unit test for "idle-threshold clearing" would assert "was thinking cleared after an hour of idle" (yes) without asserting "is thinking preserved on subsequent turns" (no). The invariant is negative space.
The real lesson is that an internal message-queuing experiment masked the symptoms in their own dogfooding. Dogfooding only works when the eaten food is the shipped food.
> On April 16, we added a system prompt instruction to reduce verbosity.
What verbosity? Most of the time I don’t know what it’s doing.
One of Anthropic's ostensive ethical goals is to produce AI that is "understandable" as well as exceptionally "well-aligned". It's striking that some of the same properties that make AI risky also just make it hard to consistently deliver a good product. It occurs to me that if Anthropic really makes some breakthroughs in those areas, everyone will feel it in terms of product quality whether they're worried about grandiose/catastrophic predictions or not.
But right now it seems like, in the case of (3), these systems are really sensitive and unpredictable. I'd characterize that as an alignment problem, too.
had this happen to me mid-refactor and spent 20 min wondering if I'd gone crazy. honestly the one hour threshold feels pretty arbitrary, sometimes you just step away to think
> All three issues have now been resolved as of April 20 (v2.1.116).
The latest in homebrew is 2.1.108 so not fixed, and I don't see opus 4.7 on the models list... Is homebrew a second class citizen, or am I in the B group?
Did they not address how adaptive thinking has played in to all of this?
To think we'd have known about this in advance if they'd just have open sourced Claude Code, rather than them being forced into this embarrassing post mortem. Sunlight is the best disinfectant.
something i note from this is that this is not a model weights change, but it is a hidden state change anthropic is doing to the outputs that can tune the quality and down on the "model" without breaking the "we arent changing the model" promise.
how often do these changes happen?
It's also important to realize that Anthropic has recently struck several deals with PE firms to use their software. So Anthropic pays the PE firm which forces their managed firms to subscribe to Anthropic.
The artificial creation of demand is also a concerning sign.
Useful update. Would be useful to me to switch to a nightly / release cycle but I can see why they don't: they want to be able to move fast and it's not like I'm going to churn over these errors. I can only imagine that the benchmark runs are prohibitively expensive or slow or not using their standard harness because that would be a good smoke test on a weekly cadence. At the least, they'd know the trade-offs they're making.
Many of these things have bitten me too. Firing off a request that is slow because it's kicked out of cache and having zero cache hits (causes everything to be way more expensive) so it makes sense they would do this. I tried skipping tool calls and thinking as well and it made the agent much stupider. These all seem like natural things to try. Pity.
Appreciate the honesty from the team.
At the same time, personally I find prioritizing quality over quantity of output to be a better personal strategy. Ten partially buggy features really aren't as good as three quality ones.
As an end-user, I feel like they're kind of over-cooking and under-describing the features and behavior of what is a tool at the end of the day. Today the models are in a place where the context management, reasoning effort, etc. all needs to be very stable to work well.
The thing about session resumption changing the context of a session by truncating thinking is a surprise to me, I don't think that's even documented behavior anywhere?
It's interesting to look at how many bugs are filed on the various coding agent repos. Hard to say how many are real / unique, but quantities feel very high and not hard to run into real bugs rapidly as a user as you use various features and slash commands.
This reads like good news! They probably still lost a bunch of users due to the negative public sentiment and not responding quickly enough, but at least they addressed it with a good bit of transparency.
It’s incredible how forgiving you guys are with Anthropic and their errors. Especially considering you pay high price for their service and receive lower quality than expected.
Good on Anthropic for giving an update & token refund, given the recent rumors of an inexplicable drop in quality. I applaud the transparency.
How about just not change the harness abruptly in the first place? Make new system prompt changes "experimental" first so you can gather feedback.
This black box approach that large frontier labs have adopted is going to drive people away. To change fundamental behavior like this without notifying them, and only retroactively explaining what happened, is the reason they will move to self-hosting their own models. You can't build pipelines, workflows and products on a base that is just randomly shifting beneath you.