[Toward an era in which AI employees run companies] 1,000 AIs worked continuously for 8 days.

The next thing that will happen may be the automation of company management. Today too from a certain place in Roppongi. We are moving from an era where we rely on AI to do work for us, to an era where AI finds and executes jobs on its own. I am currently paying particular attention to this change in the evolution of AI.

TAKA | MetaLinks Inc. CEONov 93

The Claude Fable 5.2 topped the Artificial Analysis smart list with 65 points, beating the Gemini 4 Carbon's 60 and Opus 5.5's 59.

This time Pro users can also experience it. A stronger model than the Opus 5.5. The max level takes an average of 44 minutes and costs $26.54 per question, ranking last among the 73 models in terms of time and cost. The high level also has a score of 62 points and costs about $9 and 18 minutes per question, which is more cost-effective on a daily basis.

实践哥 LiNov 98

Anthropic's $1 trillion IPO is next week.

Here's what's really inside the model behind it: → Fable 5.2 is Mythos 5.2 with a safety mask. Same weights, same price → When the filter fires, an older model answers you instead (Opus 4.8 or Opus 5) → Anthropic deliberately limited

ZaynNov 916

Claude Fable 5.2 on FarmerBench

80.16, second to Gemini 4 Argon (84.01), ahead of Opus 5.5 (75.54) and Fable 5.1 (69.17). 6 game-hours to automate a farm economy by writing code. Fable 5.2 hit 32 drones on every seed.

Richard ThomasNov 9