Gary Marcus

Rank 12 of 47
|
Score 83
4/22/2025, 9:32:46 PM
X
In reply to:
Juggalos For Context馃尨馃ゥ
@ebarcuzzi
路
273d
@GaryMarcus @colin_fraser Kind of cheating since I'm pretty sure it did this in Python in the background.
Gary Marcus
@GaryMarcus
路
273d
@colin_fraser @ebarcuzzi now try floating point numbers. and multiplication!
Colin Fraser
@colin_fraser
路
273d
@ebarcuzzi @GaryMarcus not quite 99.9 when we go higher than 40 digits
Colin Fraser
@colin_fraser
路
279d
Answer: 87%.

As usual, we are in this bizarre place where the LLM performs better than I would ever expect, and yet worse than a computer ever should. Not sure what to make of it.
Juggalos For Context馃尨馃ゥ
@ebarcuzzi
路
273d
@GaryMarcus @colin_fraser Addition and multiplication up to an ever expanding number of digits is one example.
Gary Marcus
@GaryMarcus
路
273d
@ebarcuzzi @colin_fraser on what is an LLM 99.9% accurate? source/link?
Juggalos For Context馃尨馃ゥ
@ebarcuzzi
路
273d
@colin_fraser @GaryMarcus Also no one really reports on break throughs in LLMs going from 99% accurate to 99.9% accurate on certain tasks. Not an attention grabbing headline.

The statement is part of a technical discussion about the capabilities of language models in performing mathematical operations. It addresses the use of tools like Python to enhance these capabilities, suggesting that reliable tool usage represents an advancement. The tone is analytical and focused on evaluating technological progress.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does no harm and is focused on technical evaluation.聽[+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    It promotes understanding by discussing advancements in technology.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.
    Engages in constructive dialogue without personal attacks.聽[+1]