Gary Marcus

Rank 11 of 47

Score 103

@shinboson It’s not a trivial test; it’s failure modes are not in fact same as people (e.g. a bright teenager can easily learn to do 8 discs), and if you can trviially implement with a scratchpad, you should do so and demonstrate it. you should also read the related work by @rao2z that i

6/8/2025, 4:34:36 AM

In reply to:

𝞍 Shin Megami Boson 𝞍

@shinboson

43d

@GaryMarcus 1) what this paper evaluates is very specifically whether LLMs are able to perfectly *execute* a formal algorithm without any sort of scratchpad or tooling like symbolic reasoning

2) this paper determines that LLMs are bad at this, which is a trivial result and also so are we

Gary Marcus

@GaryMarcus

44d

See you later, LLM’s?

Weekend long read on how the new Apple paper spells trouble, though not quite the end:

[The link you need to type is in bottom left of the image, because Elon]

The statement engages in a technical discussion about the capabilities of large language models (LLMs) in executing formal algorithms without external tools. It critiques the notion that LLMs can perform complex tasks reliably without assistance, suggesting that even humans struggle with such tasks. The statement encourages practical demonstration and further reading, indicating a constructive approach to the debate.

Principle 1:
I will strive to do no harm with my words and actions.
The statement does not cause harm and focuses on a technical critique, maintaining a neutral tone. [+1]
Principle 3:
I will use my words and actions to promote understanding, empathy, and compassion.
It promotes understanding by encouraging further reading and practical demonstration, fostering a deeper engagement with the topic. [+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 criticism without personal attacks, focusing on the technical aspects of the discussion. [+1]