The workflow/ultracode mode is absolutely unbelievable.
Claude Opus 4.8
761–770 of 1001 posts
Re: Claude Opus 4.8
#762First impression... this catches issues that 4.7 missed, which caught issues that 4.6 missed... which caught issues that 4.5 missed...
Seems like a step in the right direction. Doesn't seem like it uses tokens more than 4.7... the token usage jumped a bunch from 4.6 to 4.7, but this seems like 4.7 or maybe even a little less.
I'm happy with this release.
Re: Claude Opus 4.8
#763got a random pair up with this model on lmarena. it was outperformed by gemma-4-31b. suffice to say i'm not impressed (or maybe i am impressed with gemma?)
Re: Claude Opus 4.8
#764My 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,…
Wow that looks really impressive. Both the UI and the content looks good, the game is a bit buggy but still nice!
Re: Claude Opus 4.8
#765I 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...
It's pretty safe to say that AI will be used on the battlefield making real life and death decisions before it will be able to render a decent pelican on a bike in SVG.
I think that's a fair tradeoff. There's no way I'm going back to writing code by hand again. No one deserves that.
Re: Claude Opus 4.8
#766"Users will find Opus 4.8 to be a modest but tangible improvement on its predecessor." This is a refreshing attitude! I've also verified that you can now turn off adaptive thinking in the web UI, which is great. I've had a lot of problems with thinking not triggering and the model producing sub-par output. Glad we can finally turn it off. (I hope being able to turn off adaptive thinking is new, if I could have turned…
You act like they weren't fearmongering about Mythos literally 2 months ago. Do you think everyone is stupid, we know exactly what you are doing. Please.
Re: Claude Opus 4.8
#767It's more fast to response, but I really wanna it think more before response.
Re: Claude Opus 4.8
#768There is a hole in the boat's bottom due to Chinese models. They might not be as good but they are not bad either or at least I had hard time finding any issues with Deepseekv4 Flash and Pro variants. They get their job done sometimes rarely giving up till they are done what they are after. So even for enterprise deployments, as the dust settles down, CFO/CTOs might find out that deploying on an internal cluster of G…
Anybody know what the most capable Chinese model is that can be used in production and is cheaper than US frontier models? Would that still be Deepseek? My interest is getting as close to Gpt5.5 or Opus quality as I can get, but for less $.
Re: Claude Opus 4.8
#769I have try the 4.8. With Ultra coding. I think the output of the agent is more structured. Better than just filling all the thing.
Re: Claude Opus 4.8
#770There is a hole in the boat's bottom due to Chinese models. They might not be as good but they are not bad either or at least I had hard time finding any issues with Deepseekv4 Flash and Pro variants. They get their job done sometimes rarely giving up till they are done what they are after. So even for enterprise deployments, as the dust settles down, CFO/CTOs might find out that deploying on an internal cluster of G…
I had been saying this on HN repeatedly: people are going to use the smartest models for coding. They don't care how cheap your tokens are if they don't have the highest probability of solving your programming tasks. And I was dead wrong. Now I mostly use DeepSeek Pro myself.
You should try Composer 2.5 within cursor. It's so fast, shockingly fast. Going back to gpt/claude is like using dial-up. And it's great for code work. So far nothing has really tripped it up backend, frontend or reporting metabase dashboard stuff. It's nuts.