Gary Marcus

Rank 12 of 47
|
Score 83
12/22/2024, 3:22:24 AM
X
In reply to:
Radhika Sharma
@radhika5kh
·
380d
@GaryMarcus François Chollet's blog states (in the first line) that they used the training set. https://arcprize.org/blog/oai-o3…

Yes "open"ai has never released a paper and is the most opaque lab; this is a huge breakthrough, irrespective of including the training set.
Gary Marcus
@GaryMarcus
·
380d
@radhika5kh see discussion here
Gary Marcus
@GaryMarcus
·
380d
The replies in this thread shows that there are lots of people *within the ML community* raising the same concerns re how OpenAI discussed ARC that I was making. (And more concerns, e.g, in important comments about how the graph was labeled).

Importantly, this an issue about…
Radhika Sharma
@radhika5kh
·
380d
@GaryMarcus What's your point? There's no cross contamination. The results have been verified by the arc foundation 🤔
Gary Marcus
@GaryMarcus
·
380d
@radhika5kh I am aware, thank you.
Radhika Sharma
@radhika5kh
·
380d
@GaryMarcus And they did eval on the private set..
Gary Marcus
@GaryMarcus
·
380d
Incredible video if you watch it a couple times and realize what they actually did, training on 75% of the public set.

Never trust Sam. Ever.

The statement engages in a discussion about the transparency and methodology of OpenAI's research, which is a public issue within the machine learning community. The tone is speculative and seeks to understand the implications of the research methods used by OpenAI.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does not cause harm and is neutral in tone, focusing on understanding rather than attacking. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The statement promotes understanding by questioning the transparency and implications of the research methods. [+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 engages in constructive dialogue by raising questions and considering different possibilities without resorting to personal attacks. [+1]