Claude's 4.6 - 4.7 transition made me discover codex, and with gpt 5.5 there is no way i'm going back
[flagged]
if you go this route don't hold your thoughts on the casino itself
Claude Opus 4.8
471–480 of 1001 posts
Re: Claude Opus 4.8
#472A 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…
I won't be surprised if the next gen frontier models are the last. There's orders of magnitude of low hanging juice to squeeze out of smaller models. It is almost guaranteed that a 60-90B model can outperform current SOTA in coding tasks within 2-3 years (design not certain, probably unlikely). It is far less clear that a 1.2T model will be meaningfully better enough to justify training it. As far as reasoning is con…
So, then I guess the big three are never going to make their money back.
Re: Claude Opus 4.8
#473A 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…
I won't be surprised if the next gen frontier models are the last. There's orders of magnitude of low hanging juice to squeeze out of smaller models. It is almost guaranteed that a 60-90B model can outperform current SOTA in coding tasks within 2-3 years (design not certain, probably unlikely). It is far less clear that a 1.2T model will be meaningfully better enough to justify training it. As far as reasoning is con…
I effectively distill the frontier models by building whole sets of skills, personas, and other artifacts that I can then run on smaller models and get 10% even 20% improvements on models like haiku or local models.
There's a lot of room for improving the smaller models at many levels of the stack.
Re: Claude Opus 4.8
#4744.8 also seems like a regression and using it from the chat GUI results in 4.6 no longer showing up. If someone from anthropic is here, is it possible to readd 4.6 in the "other models" dropdown ? I feel like I got a bit baited/switched here.
Yeah, I was using 4.6 way more than 4.7. Pulling 4.6 from the web chat also means we lose access to Extended Thinking there. So they're saving on compute. It's hard not to assume this was part of the motivation behind the 4.8 release timing.
On web and mobile I can still select Opus 4.6, after a chat using 4.8, listed under other models. Extended thinking is a toggle in the effort menu
When I select 4.7 or 4.8 Extended thinking is replaced by adaptive thinking, but maybe I've understood the comment wrong and you meant 'when they pull 4.6 from web chat'?
Re: Claude Opus 4.8
#475Used it for a couple of long running prompts so far. Had to restart one that bonked on API errors. Of note, I really like the straight forward candor its using. 'More honest' than previous models is playing out in what its saying to me. Telling me straight up where it failed, where gaps are. I like it so far.
Re: Claude Opus 4.8
#476My fav coding benchmark for frontier models is to build a simple RTS game in one file (js/html/css). Claude Code with Opus 4.8 in ultracode mode nailed it, the best result so far: https://bsky.app/profile/senko.net/post/3mmwnrkwboc2v The prompt was: Create a simple but functional real time strategy (RTS) game similar to old WarCraft, StarCraft or Command & Conquer games. The player should be able to build buildings,…
Played it to the end. Pretty neat!
Re: Claude Opus 4.8
#477Given DeepSWE just blew apart the SWE-Bench Pro benchmark and handed a 14-point lead to GPT-5.5, it looks pretty bad that they've listed SWE-Bench first in the model release and no DeepSWE. Like, this isn't obviously an answer. Or maybe it is, but publish the DeepSWE numbers so we can see for ourselves.
I'm highly skeptical of DeepSWE. It rates GPT-5.4-mini as three times better than deepseek-v4-pro, but every time I use GPT-5.4-mini I find that it completely sucks at following directions.
I don't know if DeepSWE is genuinely a good benchmark. It's more important that their analysis demolished the validity of SWE-Bench Pro, objectively: it is being mismarked.
I think that buys enough credibility to propose an alternative.
I think there's a case to answer if Anthropic models underperform on a novel benchmark. I'd like to see more novel benchmarks to get a clearer picture.
Re: Claude Opus 4.8
#478Earlier quoted context omitted.
I won't be surprised if the next gen frontier models are the last. There's orders of magnitude of low hanging juice to squeeze out of smaller models. It is almost guaranteed that a 60-90B model can outperform current SOTA in coding tasks within 2-3 years (design not certain, probably unlikely). It is far less clear that a 1.2T model will be meaningfully better enough to justify training it. As far as reasoning is con…
Absolutely that’s why they’re rushing to IPO now to squeeze the last drop of the bubble they know this is a dead end.
I think we could run for at least a decade further with no model changes/improvements, just better harnesses and infra around this agentic way of developing.
Re: Claude Opus 4.8
#479Thinking on max is broken on 4.8 for me, getting many:
⎿ API Error: 400 messages.1.content.17: `thinking` or `redacted_thinking` blocks in the latest assistant message cannot be modified. These blocks must remain as they were in the original response.
From /code-review max.
Re: Claude Opus 4.8
#480The table comparing eval scores shows the following: Agentic Terminal Coding (Terminal-Bench 2.1) Opus 4.8 74.6% GPT 5.5 78.2% Then, when you scroll all the way down to the bottom Footnotes section it says "Terminal-Bench 2.1: We reported scores for all models using the Terminus-2 public harness. GPT-5.5’s reported score with the Codex CLI harness is 83.4%."
Seems reasonable? Presumably Claude also performs better under the Claude Code harness.