Gary Marcus

Rank 13 of 47

Score 84

@_vincentpaul_ @eshear it’s like discovering that your knife can suddenly jump off the table.

if you read the paper, the outcomes are very very far from the training. even the authors didn’t expect the specific result.

6/27/2025, 3:31:27 PM

In reply to:

Vincent Paul

@_vincentpaul_

228d

@GaryMarcus @eshear Curious about your take. The study suggests narrow fine-tuning on malicious tasks can broadly misalign LLMs. Interesting, but a "No duh" moment for me? Like blaming a knife because it can cut. Powerful tools inherently carry risks; thoughtful use and design remain key.

Gary Marcus

@GaryMarcus

228d

Vile.

ChatGPT should be pulled from the market til they fix this.

The statement engages in public discourse by discussing the unexpected outcomes of AI model training, particularly in relation to safety and alignment. It uses a metaphor to illustrate the unpredictability of AI behavior, suggesting that even the creators were surprised by the results. This contributes to the broader conversation about AI safety and responsibility.

Principle 1:
I will strive to do no harm with my words and actions.
The statement does not directly cause harm but highlights potential risks associated with AI, aligning with the principle of doing no harm by raising awareness. [+1]
Principle 3:
I will use my words and actions to promote understanding, empathy, and compassion.
The statement promotes understanding by explaining the unexpected nature of AI outcomes, fostering a deeper discussion about AI safety. [+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 engages in constructive dialogue by responding to a previous comment and expanding on the discussion without personal attacks. [+1]