Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

An update on recent Claude Code quality reports

anthropic.com

Post reply on HN
Print view View original

161–170 of 778 posts

Re: An update on recent Claude Code quality reports

#161

Post by thesz »

dataviz1000 wrote: post #38

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…

To have some confidence in consistency of results (p-value), one has to start from cohort of around 30, if I remember correctly. This is 1.5 orders of magnitude increase of computing power needed to find (absence of) consistent changes of agent's behavior.

Re: An update on recent Claude Code quality reports

#162

Post by dbeardsl »

bcherny wrote: post #124
6keZbCECT2uB wrote: post #61

"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 leav…

Hey, Boris from the Claude Code team here. Normally, when you have a conversation with Claude Code, if your convo has N messages, then (N-1) messages hit prompt cache -- everything but the latest message. The challenge is: when you let a session idle for >1 hour, when you come back to it and send a prompt, it will be a full cache miss, all N messages. We noticed that this corner case led to outsized token costs for u…

I appreciate the reply, but I was never under the impression that gaps in conversations would increase costs nor reduce quality. Both are surprising and disappointing.

I feel like that is a choice best left up to users.

i.e. "Resuming this conversation with full context will consume X% of your 5-hour usage bucket, but that can be reduced by Y% by dropping old thinking logs"

Re: An update on recent Claude Code quality reports

#163

Post by arkariarn »

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.

https://youtu.be/KFisvc-AMII?is=NskPZ21BAe6eyGTh

Re: An update on recent Claude Code quality reports

#164

Post by ankaz »

bcherny wrote: post #87
jpcompartir wrote: post #75

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/…

Boris from the Claude Code team here. We agree, and will be spending the next few weeks increasing our investment in polish, quality, and reliability. Please keep the feedback coming.

[dead]

Re: An update on recent Claude Code quality reports

#165

Post by whalesalad »

arkariarn wrote: post #163

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…

literally just `git reset --hard ` would fix this

Re: An update on recent Claude Code quality reports

#166

Post by hex4def6 »

Keeeeeeeks wrote: post #41
xlayn wrote: post #19

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 mont…

https://marginlab.ai/ (no affiliation) There are a number of projects working on evals that can check how 'smart' a model is, but the methodology is tricky. One would want to run the exact same prompt, every day, at different times of the day, but if the eval prompt(s) are complex, the frontier lab could have a 'meta-cognitive' layer that looks for repetitive prompts, and either: a) feeds the model a pre-written outp…

I think you could alter the prompt in subtle ways; a period goes to an ellipses, extra commas, synonyms, occasional double-spaces, etc.

Enough that the prompt is different at a token-level, but not enough that the meaning changes.

It would be very difficult for them to catch that, especially if the prompts were not made public.

Run the variations enough times per day, and you'd get some statistical significance.

The guess the fuzzy part is judging the output.

Re: An update on recent Claude Code quality reports

#167

Post by jpcompartir »

bcherny wrote: post #87
jpcompartir wrote: post #75

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/…

Boris from the Claude Code team here. We agree, and will be spending the next few weeks increasing our investment in polish, quality, and reliability. Please keep the feedback coming.

[flagged]

Re: An update on recent Claude Code quality reports

#169

Post by btown »

bcherny wrote: post #124
6keZbCECT2uB wrote: post #61

"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 leav…

Hey, Boris from the Claude Code team here. Normally, when you have a conversation with Claude Code, if your convo has N messages, then (N-1) messages hit prompt cache -- everything but the latest message. The challenge is: when you let a session idle for >1 hour, when you come back to it and send a prompt, it will be a full cache miss, all N messages. We noticed that this corner case led to outsized token costs for u…

Is there a way to say: I am happy to pay a premium (in tokens or extra usage) to make sure that my resumed 1h+ session has all the old thinking?

I understand you wouldn't want this to be the default, particularly for people who have one giant running session for many topics - and I can only imagine the load involved in full cache misses at scale. But there are other use cases where this thinking is critical - for instance, a session for a large refactor or a devops/operations use case consolidating numerous issue reports and external findings over time, where the periodic thinking was actually critical to how the session evolved.

For example, if N-4 was a massive dump of some relevant, some irrelevant material (say, investigating for patterns in a massive set of data, but prompted to be concise in output), then N-4's thinking might have been critical to N-2 not getting over-fixated on that dump from N-4. I'd consider it mission-critical, and pay a premium, when resuming an N some hours later to avoid pitfalls just as N-2 avoided those pitfalls.

Could we have an "ultraresume" that, similar to ultrathink, would let a user indicate they want to watch Return of the (Thin)king: Extended Edition?

Post reply on HN