Gary Marcus

Rank 12 of 47

Score 83

@metaculus can you put legals moves in chess for pure LLMson my page, as a challenge with no date estimate for when solve, issued on the data above?

5/19/2025, 6:15:38 PM

In reply to:

Gary Marcus

@GaryMarcus

253d

Getting tired of people just lying about me.

Below someone accuses me of “moving the goalposts” by pointing to the illegal moves that LLMs make in chess, when in fact I have been doing that for a long time, as e.g., this screenshot shows:

decelerated gradient✨

@ethicating

253d

Moving the goalposts

The statement is part of a public discourse on the capabilities of language models (LLMs) in playing chess. It addresses the issue of LLMs making illegal moves in chess, which is a technical challenge and a point of debate in AI development.

Principle 1:
I will strive to do no harm with my words and actions.
The statement does not cause harm and is a neutral request for a challenge.
Principle 3:
I will use my words and actions to promote understanding, empathy, and compassion.
It promotes understanding by engaging in a technical discussion about LLM capabilities. [+1]
Principle 4:
I will engage in constructive criticism and dialogue with those in disagreement and will not engage in personal attacks or ad hominem arguments.
The statement does not engage in personal attacks and maintains a constructive tone. [+1]