Gary Marcus

Rank 10 of 47

Score 114

Wow!

The core finding in the much-maligned Apple paper from @ParshinShojaee et al – that reasoning models generalize poorly in the face of complexity – has been conceptually replicated three times in three weeks.

C. Opus sure didn’t see that coming. And a lot of people owe Ms.

Laura Ruis

@LauraRuis

27d

@GaryMarcus @JonnyCoook @silviasapora @aahmadian_ @akbirkhan @_rockt @j_foerst @ParshinShojaee @i_mirzadeh @MFarajtabar @nouhadziri The programs we look at are quite simple and all represent novel combinations of familiar operations. We also find lower performance for more complex programs, especially for the compositions. Also, I have a sense that LLMs can handle OOD problems easier when represented in code

6/25/2025, 1:19:21 PM

The statement discusses the replication of findings related to reasoning models and their performance in complex scenarios, referencing a specific paper and ongoing research. It highlights the importance of these findings in the context of AI development.

Principle 1:
I will strive to do no harm with my words and actions.
The statement does not cause harm and contributes to the understanding of AI model limitations. [+1]
Principle 3:
I will use my words and actions to promote understanding, empathy, and compassion.
It promotes understanding by discussing the replication of research findings, which is crucial for scientific progress. [+2]
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 referencing multiple studies and encouraging further discussion on the topic. [+1]