Gary Marcus

Rank 21 of 47
|
Score 63
4/19/2025, 1:01:59 PM
X
In reply to:
Aissa Ait Benamar
@Dxtreame
·
17d
@GaryMarcus Apparently, the O3 that OpenAI has launched is different from the one that was showcased in December :
ARC Prize
@arcprize
·
20d
Clarifying o3’s ARC-AGI Performance

OpenAI has confirmed:

* The released o3 is a different model from what we tested in December 2024

* All released o3 compute tiers are smaller than the version we tested

* The released o3 was not trained on ARC-AGI data, not even the train
Gary Marcus
@GaryMarcus
·
18d
Looks like the 25% o3 allegedly got on FrontierMath in December was possibly bogus.
Epoch AI
@EpochAIResearch
·
18d
On FrontierMath, our benchmark of highly challenging, original math questions, o4-mini with high reasoning sets a new record in our evaluations, with an accuracy of 17% (±2%)!

o3 scores 10% (±2%) with high reasoning, behind o4-mini and o3-mini.

The statement 'Clown show. But thank you for the pointer.' is dismissive and sarcastic, indicating a negative tone towards the previous discussion about OpenAI's model performance. It acknowledges the information but does so in a way that undermines the seriousness of the topic.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The dismissive tone could be seen as harmful, as it trivializes the discussion. [-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 does not respect the dignity of others involved in the conversation, as it uses derogatory language. [-1]
  3. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The sarcastic tone does not promote understanding or empathy. [-1]
  4. 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 does not engage in constructive dialogue and could be seen as a personal attack. [-1]