Gary Marcus

Rank 13 of 47
|
Score 97
Gary Marcus
@GaryMarcus
·
67d
“a good set of challenges” for AGI from 2022
• none have been solved
• community accepted them as legit at the time
• goalposts haven’t moved

translation and lessons:
1. people are making shit up when they say I am moving my goalposts; they haven’t changed.
2. those with
7/20/2025, 6:53:58 PM
X
In reply to:
Gary Marcus
@GaryMarcus
·
67d
@groyfortin older but not oldest
boisselle
@seanboisselle
·
568d
@GaryMarcus Good tests, shall we call it the Marcus Test for AI?

By this other gentleman's first four points, this is clearly not AGI!

Funny how he says it is 🤔
Gary Marcus
@GaryMarcus
·
67d
@groyfortin another from yesterday
Anna
@annapanart
·
68d
The Gary Marcus benchmark is achieved.

—— AGI confirmed! ——
Gary Marcus
@GaryMarcus
·
67d
@groyfortin here’s someone from yesterday perhaps in jest but it goes back a few years
alz
@alz_zyd_
·
68d
OpenAI passed the Marcus test, July 19 2025 will henceforth be remembered as AGI day
Gary Marcus
@GaryMarcus
·
67d
@groyfortin don’t remember but you could find it here probably

more than one person has had the general idea
Guillaume Roy-Fortin
@groyfortin
·
67d
@GaryMarcus who named it that, then?
Gary Marcus
@GaryMarcus
·
67d
The “Marcus Test” for AGI (I didn’t name it that, but it means “no AGI til Marcus says it’s AGI”) is a pretty good test for AGI.* But don’t bullshit yourself about what it is.

• It’s not about achieving a single result—I have used the word impressive (or similar) to describe

The conversation revolves around the concept of Artificial General Intelligence (AGI) and the criteria for its achievement. It involves a discussion on the 'Marcus Test' for AGI, with various participants debating the validity and implications of recent AI developments. The tone is analytical and somewhat skeptical, focusing on the challenges and benchmarks for AGI.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The discussion is largely respectful and focused on the topic of AGI, avoiding personal attacks. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The conversation promotes understanding by discussing the criteria and challenges related to AGI. [+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.
    There is constructive criticism and dialogue, particularly around the validity of AGI claims and the criteria used to evaluate them. [+1]