Anthropic details unreleased Model 2 in AI risk report
Anthropic revealed it has developed an AI model more capable than Claude Mythos 5. The company detailed the algorithm in its latest AI alignment report, which outlines potential risks from its large language models.
First seen 14 Aug, 23:31 UTC on SiliconANGLE2 sourcesLast update 35d ago
AnthropicResearch · 14 Aug
Model 2
Research release
What the sources say
Linked, never rewritten. Official means the lab itself.
Official0
No word from Anthropic yet.
Coverage2
SiliconANGLE· 14 Aug, 23:31Anthropic details unreleased Model 2, new alignment concerns in latest AI risk reportThe Decoder· 20 Aug, 10:04Anthropic's most capable model, codenamed "Model 2," is for internal use onlyCommunity0
No community discussion picked up yet.
How it unfolded
Every source in the order it appeared. Times in UTC.