Rendered at 11:37:22 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
tudelo 3 hours ago [-]
There is, in my personal opinion, a reason that reasoning is not front and center. Partially related to distillation.
cyrbuzz 2 hours ago [-]
Maybe cheat is a one of the factors of model?
setnone 3 hours ago [-]
yeah this feels frustrating with claude, a black box inside a black box. good thing they got competitors
Loveispain 10 hours ago [-]
Deepseek has shifted to my general go to, this being one of the factors. Most likely claude is making up some small details to reinforce what it thinks is right or optimal, but generally still right.
Only recent quirk in longer chats with Deepseek, watching the the thought process and output; it sometimes becomes Chinese. Also not sure if this is to intentionally hide the thought process, or the actual information needs to be looked up and explained in Chinese.
bigyabai 14 hours ago [-]
> Opus 4.6 remains the best model because of this.
Huh? Are you not trying other open-weight models that stream thinking traces?
The new DeepSeek-V4-Flash-0731 should clobber Opus 4.6 in a lot of tasks. Kimi K3 and GLM 5.2 feel like they stand toe-to-toe with Opus 4.8 in my experience. This probably isn't the last stupid decision that Anthropic stands on, you might as well hedge your bet and put some money into another inference provider and see how it goes.
exabrial 13 hours ago [-]
Yeah, I think we need to. Opus 5 is great, but it's too wordy and it's making mistakes that aren't caught till much later. Usually you can see if the model is going off-course through the thought trace, Opus5 you're flying blind.
Honestly Anthropic keeps clubbing themselves. They're so worried about their competition they're no longer innovating.
Only recent quirk in longer chats with Deepseek, watching the the thought process and output; it sometimes becomes Chinese. Also not sure if this is to intentionally hide the thought process, or the actual information needs to be looked up and explained in Chinese.
Huh? Are you not trying other open-weight models that stream thinking traces?
The new DeepSeek-V4-Flash-0731 should clobber Opus 4.6 in a lot of tasks. Kimi K3 and GLM 5.2 feel like they stand toe-to-toe with Opus 4.8 in my experience. This probably isn't the last stupid decision that Anthropic stands on, you might as well hedge your bet and put some money into another inference provider and see how it goes.
Honestly Anthropic keeps clubbing themselves. They're so worried about their competition they're no longer innovating.