Zhu Liang
@paradite_
278 Following 5.2K Followers
this tb4 story keeps getting wilder.
both vals ai and aa use mini-swe-agent harness, but the ranking is completely different:
vals ai:
opus 5.5 > sonnet 5.5 > kimi k3.1 pro > gemini 4 carbon
aa:
kimi k3.1 pro > gemini 4 carbon> sonnet 5.5 > opus 5.5
you can't make this up.
Show more
@teortaxesTex lol jiumozhi is literally my favourite character in that show. you can't make this stuff up.
@teortaxesTex you know you can always join us.
i think anthropic is very much aligned with deepseek on a deeper level.
great. now it’s only anthropic who can deliver agi safely to the world.
anthropic against a misaligned world.
anthropic should continue focusing on its mission and ignore all the noise.
