Have some new features to show off today! x.com/i/broadcasts/1…

Check out the new auto review feature! x.com/i/broadcasts/1…

Horizon Alpha does quite well on LoCoDiff, only beaten by Gemini 2.5 Pro (barely) and Sonnet 4 (number 1 by a huge margin)

Opus 4.1 is available on mentat.ai now!

$1.25 / $10 input/output is great, and 400k context window also great cached input is only $0.125 - 10%, matching Anthropic's cached input rates - Amazing!

will update as soon as I know if this is no longer the case

GPT-5 is OpenAI's best model yet on LoCoDiff LoCoDiff is unusual - more reasoning usually hurts performance, and it's the same for GPT-5, with "minimal" doing better than "medium" reasoning effort. GPT-5 almost at Gemini 2.5 Pro levels until 60k tokens Sonnet 4 still dominates

almost none of my gpt-5 api calls are hitting the cache

Mentat has positive margins. It’s simply 19.5% over our model api costs. Use as much or as little as you want (you’ll want a lot)

we've made a ton of changes to Mentat the last several months. Would love feedback on our new landing page! mentat.ai

Wrap your head around this. - Have git spit out a file's edit history - Line up all the diffs one-after-another - Feed it to a model and tell it to recreate the current (last) state At 100,000 tokens, Sonnet 4 succeeds 2/3 of the time, while GPT-5 does <5%.

j⧉nus murat 🍥 Claude finally ran Opus on LoCoDiff and it's better than Sonnet on short context, but falls apart on higher contexts? very strange

whoa OpenAI is giving GPT-5 on the API a prompt before the one I set?? they give it: - instructions on formatting (which is contradicting my own) - today's date - telling it that it's being used over the API - a bunch of other stuff not cool