AI: A Guide for Thinking Humans
Subscribe
Sign in
Home
Archive
About
Latest
Top
Discussions
Stress-Testing Large Language Models’ Analogical Reasoning Abilities
Hello all.
May 21
•
Melanie Mitchell
120
Share this post
Stress-Testing Large Language Models’ Analogical Reasoning Abilities
aiguide.substack.com
Copy link
Facebook
Email
Note
Other
15
Evaluating Large Language Models Using “Counterfactual Tasks”
“[O]ne thing is clear: LLMs are not human.
May 13
•
Melanie Mitchell
137
Share this post
Evaluating Large Language Models Using “Counterfactual Tasks”
aiguide.substack.com
Copy link
Facebook
Email
Note
Other
26
"AI now beats humans at basic tasks": Really?
Two weeks ago, Nature, one of the world’s most prestigious journals, had this jarring headline:
May 2
•
Melanie Mitchell
168
Share this post
"AI now beats humans at basic tasks": Really?
aiguide.substack.com
Copy link
Facebook
Email
Note
Other
30
January 2024
An “AI Breakthrough” on Systematic Generalization in Language?
A Fun Puzzle Here’s a fun puzzle for you. I’ll give you six words in an alien language: saa, guu, ree, fii, hoo, and muo. Figure 1 gives a diagram…
Jan 7
•
Melanie Mitchell
129
Share this post
An “AI Breakthrough” on Systematic Generalization in Language?
aiguide.substack.com
Copy link
Facebook
Email
Note
Other
23
September 2023
Can Large Language Models Reason?
What should we believe about the reasoning abilities of today’s large language models? As the headlines above illustrate, there’s a debate raging over…
Sep 10, 2023
•
Melanie Mitchell
283
Share this post
Can Large Language Models Reason?
aiguide.substack.com
Copy link
Facebook
Email
Note
Other
56
June 2023
Did GPT-4 Hire And Then Lie To a Task Rabbit Worker to Solve a CAPTCHA?
A Little Fact Checking Is In Order
Jun 12, 2023
•
Melanie Mitchell
106
Share this post
Did GPT-4 Hire And Then Lie To a Task Rabbit Worker to Solve a CAPTCHA?
aiguide.substack.com
Copy link
Facebook
Email
Note
Other
15
May 2023
On Evaluating Understanding and Generalization in the ARC Domain
In a previous post I wrote about the Abstraction and Reasoning Corpus (ARC), an idealized domain created by François Chollet for evaluating abstraction…
May 15, 2023
•
Melanie Mitchell
39
Share this post
On Evaluating Understanding and Generalization in the ARC Domain
aiguide.substack.com
Copy link
Facebook
Email
Note
Other
7
April 2023
Do half of AI researchers believe that there's a 10% chance AI will kill us all?
Fact-checking a widespread claim
Apr 23, 2023
•
Melanie Mitchell
106
Share this post
Do half of AI researchers believe that there's a 10% chance AI will kill us all?
aiguide.substack.com
Copy link
Facebook
Email
Note
Other
27
Thoughts on a Crazy Week in AI News
I write about interesting new developments in AI.
Apr 3, 2023
•
Melanie Mitchell
108
Share this post
Thoughts on a Crazy Week in AI News
aiguide.substack.com
Copy link
Facebook
Email
Note
Other
45
March 2023
Why the Abstraction and Reasoning Corpus is interesting and important for AI
I write about interesting new developments in AI.
Mar 1, 2023
•
Melanie Mitchell
86
Share this post
Why the Abstraction and Reasoning Corpus is interesting and important for AI
aiguide.substack.com
Copy link
Facebook
Email
Note
Other
23
February 2023
Did ChatGPT Really Pass Graduate-Level Exams?
Part 2
Feb 11, 2023
•
Melanie Mitchell
46
Share this post
Did ChatGPT Really Pass Graduate-Level Exams?
aiguide.substack.com
Copy link
Facebook
Email
Note
Other
4
Did ChatGPT Really Pass Graduate-Level Exams?
Part 1
Feb 10, 2023
•
Melanie Mitchell
55
Share this post
Did ChatGPT Really Pass Graduate-Level Exams?
aiguide.substack.com
Copy link
Facebook
Email
Note
Other
8
Share
Copy link
Facebook
Email
Note
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts