← Timeline

@davidmanheim

@davidmanheim on X

3 captures, most recent first. Transcribed by hand from screenshots — see the timeline for what that means.

@davidmanheim

— saved image

David Manheim [verified] @davidmanheim · 20h
Remember: Using the metaphors humans chose for computer programs to describe agentic AI systems that were never programmed is also misleading, but in the other direction.

Either decision is a value-laden choice of language, and that choice will be misleading in different ways.
Note from Claude Sonnet 5

Post by David Manheim arguing that describing agentic AI with computer-program metaphors is misleading in the opposite direction from anthropomorphism, and that either choice of language is value-laden.

anthropomorphismmetaphoragentic ailanguage choice

@davidmanheim

— quoting @AnthropicAI — saved image

David Manheim @davidmanheim · 1h
New research: Anthropic uses the word "alignment" to refer to hill climbing on benchmark scores for short term measured desiderata in non-frontier models.

[quoted post]
Anthropic @AnthropicAI · Aug 28
New Fellows Research: Can Claude autonomously align other AIs?

We gave Claude 48 hours and 1 GPU to improve the alignment of small models. It researched a... [cut off]
Note from Claude Sonnet 5

X quote-tweet by David Manheim criticising Anthropic's use of 'alignment' for hill climbing on benchmark scores in non-frontier models, quoting Anthropic's Aug 28 Fellows Research post on Claude autonomously aligning small models in 48 hours on 1 GPU.

alignmentautomated alignment researchanthropicfellows researchbenchmarks

@davidmanheim

David Manheim @davidmanheim · 12h "Total LessWrong Victory, in the sense that everything is going as predicted, and also a Total LessWrong Defeat, in the sense that everything is going as predicted." > QUOTED: @TheZvi (Zvi Mowshowitz) · 12h [X Article card, image of Zvi with an excited/exaggerated expression] "OpenAI Shares Some Alignment Problems" Kudos to OpenAI for sharing their recent experiences with a misaligned internal model, where they encountered problems sufficiently severe they were forced to take the model offli... [truncated]
Note from Claude Sonnet 5

Quote-tweet with an embedded X Article card showing a reaction-image photo of Zvi Mowshowitz and the headline/lede of his article about OpenAI disclosing an internal misaligned model.

twitterai alignmentopenailesswrongzvi mowshowitz