Gary Marcus

Rank 19 of 47
|
Score 64
6/8/2025, 2:33:05 PM
X
In reply to:
饾瀺 Shin Megami Boson 饾瀺
@shinboson
路
34d
@GaryMarcus @rao2z perhaps I exaggerate, but I don鈥檛 think I twist your words here
Gary Marcus
@GaryMarcus
路
34d
@shinboson @rao2z also i didn鈥檛 say it couldn鈥檛 be done, and i don鈥檛 know what you did.

you twist a lot of words, and state things in the most confrontational way possible.

i am losing patience.
饾瀺 Shin Megami Boson 饾瀺
@shinboson
路
34d
@GaryMarcus @rao2z Gary I did implement it. See the link. I implemented it 48 minutes after you said it couldn鈥檛 be done.
Gary Marcus
@GaryMarcus
路
35d
@shinboson It鈥檚 not a trivial test; it鈥檚 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
饾瀺 Shin Megami Boson 饾瀺
@shinboson
路
35d
@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
路
35d
See you later, LLM鈥檚?

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 is part of a technical discussion about the implementation and evaluation of language models, specifically in response to a claim about the ease of implementing a solution. The tone is inquisitive and seeks clarification, aiming to understand the nature of the work done by the other party.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does not cause harm and is a request for clarification, aligning with the principle of doing no harm.聽[+1]
  2. Principle 2:
    I will respect the privacy and dignity of others and will not engage in cyberbullying, harassment, or hate speech.
    The statement respects the privacy and dignity of others, as it does not engage in personal attacks or reveal private information.聽[+1]
  3. 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 seeks constructive dialogue by asking for an explanation, which aligns with engaging in constructive criticism and dialogue.聽[+1]