Opus 4.7 was acting extremely stupid today. Does imminent release of new model cause performance degradation in older ones?
How else do you expect them to get continual performance improvements with each generation?
Claude Opus 4.8
111–120 of 1001 posts
Re: Claude Opus 4.8
#112I generated pelicans riding bicycles on both thinking level low and thinking level high: https://gist.github.com/simonw/68560eddb0b268a8417f80ceb7304... The high one is notably better - the bicycle frame is the correct shape, unlike thinking level low. For comparison, here's Opus 4.7: https://gist.github.com/simonw/afcb19addf3f38eb1996e1ebe749c...
Simon, is your pelican test really captures differences among models or should you at least try like 10 times or something to average the random effects
Re: Claude Opus 4.8
#113The smarter the model the better querybear gets. I'm happy with that.
Re: Claude Opus 4.8
#114> One of the most prominent improvements in Opus 4.8 is its honesty. We train all our models to be honest—for instance, to avoid making claims that they can’t support. But a general problem with AI models is that they sometimes jump to conclusions, confidently claiming to have made progress in their work despite the evidence being thin. Early testers report that Opus 4.8 is more likely to flag uncertainties about its…
In the context of Claude Code, "honest" usually means that the agent took a shortcut, skipped requirements, etc. It's the model giving itself credit for admitting to failing rather than actually doing what was requested.
Re: Claude Opus 4.8
#115A rambling comment: I think this is the first time we've had a third minor version bump on a frontier Anthropic model. (I count the 0.5s as major here, because they've been issued non-sequentially and also corresponded to massive capability leaps, eg, Sonnet 3.5, Opus 4.5). So now the Opus 4.5 family has successors 4.6, 4.7, and 4.8, each posting fairly modest claimed gains. My own experience w/ 4.6 and 4.7 are that…
4.7 was the first time I had to resort to using the previous version (4.6) for most use cases. Hoping 4.8 rectifies this.
Re: Claude Opus 4.8
#116when will we get anything for sonnet or haiku? the market for less-capable but cheaper models seems to be completely ignored nowadays
In the "What's next?" section, "There’s still more to be done: we’re working on developing and releasing models that provide many of the same capabilities as Opus at a lower cost."
Re: Claude Opus 4.8
#117Does anyone troll these releases and cherry pick random metrics other companies would cherry pick to show how amazing their models are? There's like 8 million benchmarks. Every release, every model randomly picks 5-10 where they win in everything except 1, to make it look like they aren't randomly cherry picking benchmarks they probably benchmaxxed for.
It's interesting they only included 6 metrics this time. Opus 4.7 had 12, and 4.6 had 13. Of the metircs they reported for 4.7, for 4.8 they excluded BrowseComp, CharXiv Reasoning, CyberGym, GPQA Diamond, MCP Atlas, MMMLU, SWE-bench Verified. The last 4 were almost always mentioned in previous Opus releases.
Gonna assume it's because they barely budged or moved downward and most of their reported benchmark results are probably within sampling errors...
Re: Claude Opus 4.8
#118I generated pelicans riding bicycles on both thinking level low and thinking level high: https://gist.github.com/simonw/68560eddb0b268a8417f80ceb7304... The high one is notably better - the bicycle frame is the correct shape, unlike thinking level low. For comparison, here's Opus 4.7: https://gist.github.com/simonw/afcb19addf3f38eb1996e1ebe749c...
Simon, is your pelican test really captures differences among models or should you at least try like 10 times or something to average the random effects
I've been meaning to do a "run 3 times and pick the best" version for quite a while, I should really pull the trigger on that one. Currently it's one-shot only.
Re: Claude Opus 4.8
#119A rambling comment: I think this is the first time we've had a third minor version bump on a frontier Anthropic model. (I count the 0.5s as major here, because they've been issued non-sequentially and also corresponded to massive capability leaps, eg, Sonnet 3.5, Opus 4.5). So now the Opus 4.5 family has successors 4.6, 4.7, and 4.8, each posting fairly modest claimed gains. My own experience w/ 4.6 and 4.7 are that…
> My own experience w/ 4.6 and 4.7 are that I don't firmly grasp any capabilities improvements over my memory of 4.5, but it's all so fuzzy that it's truly difficult to tell.
I've actually intentionally switched back to 4.5. I hated 4.7 so much that I decided to jump back all the way to 4.5.
Now that I've been using 4.5 for a few weeks, I find it significantly more reliable but a bit more forgetful than 4.6/4.7. I'm okay with that because it's really easy to identify this forgetfulness and nudge it.
I found 4.7's adaptive thinking to be extremely unreliable. It seems to overcorrect on the current message without considering the difficult of the overall problem. I wonder if 4.8 will improve on that.
Re: Claude Opus 4.8
#120A rambling comment: I think this is the first time we've had a third minor version bump on a frontier Anthropic model. (I count the 0.5s as major here, because they've been issued non-sequentially and also corresponded to massive capability leaps, eg, Sonnet 3.5, Opus 4.5). So now the Opus 4.5 family has successors 4.6, 4.7, and 4.8, each posting fairly modest claimed gains. My own experience w/ 4.6 and 4.7 are that…
Incremental gains compounds.
Exactly. Go back to Opus 4.5 and see how you like it.
You won't, really.