Gary Marcus

Rank 10 of 47
|
Score 117
7/21/2025, 2:50:56 PM
X
In reply to:
Chris
@chatgpt21
·
1d
@krapstarr @GaryMarcus 10-20%
Naveesh /wtf
@krapstarr
·
1d
@chatgpt21 @GaryMarcus how much better tho?
Chris
@chatgpt21
·
1d
@GaryMarcus No simple trick errors

Must have a non reasoning model that’s better than our current 4.5

And a reasoning end that’s better than o3 pro

Would like to see anything that indicates continuous learning but I know that’s far away. (Reasoning well outside of its data would be a
Gary Marcus
@GaryMarcus
·
1d
I love this.

What’s your list of “10 things GPT-5 must absolutely be able to do so [you] don’t end up coping later and calling it good when it’s actually mid”?

If there were no “memeably stupid” errors [#10] I will be shocked.
Flowers ☾ ❂
@flowersslop
·
35d
10 things GPT-5 must absolutely be able to do so I don’t end up coping later and calling it good when it’s actually mid:

1. I must prefer its output for any prompt at least 80% of the time vs GPT-4o. No exceptions.

2. It must be able to create an acceptable Doodle Jump clone,

The statement is part of a humorous and critical discussion about the expectations and performance of GPT-5 compared to its predecessors. It uses a metaphorical image to express skepticism about the advancements promised by the developers.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement uses humor to critique the perceived lack of progress, which can be seen as a mild form of constructive criticism. It does not appear to cause harm. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The humorous tone may promote understanding among those familiar with the context, but it might not foster empathy or compassion.
  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 engages in a light-hearted critique rather than a personal attack, aligning with constructive dialogue. [+1]