Strange Loop Canon
Subscribe
Sign in
Home
Chat
Archive
About
Latest
Top
Discussions
LLM councils show groupthink
perils and problems of LLM peer review
21 hrs ago
•
Rohit Krishnan
31
7
1
May 2026
Who Audits the Auditors?
Can one AI system make another AI system audit it less independently, just by explaining it’s point of view?
May 26
•
Rohit Krishnan
38
5
1
Introducing BenchBench
TL;DR: presenting the ultimate benchmark, getting models to create benchmarks for each other, and GPT 5.2 is the current (only) winner
May 25
•
Rohit Krishnan
20
6
3
Homo Agenticus
sapiens
May 21
•
Rohit Krishnan
58
15
8
Artificial Life, Artificial Intelligence
.
May 14
•
Rohit Krishnan
84
10
13
Experiments with Vibe Science
wherein I accidentally pursue an amateur paleontology phd
May 9
•
Rohit Krishnan
59
5
8
Why Coase needs Hayek
sometimes smart planners lose to simple markets
May 2
•
Rohit Krishnan
95
32
15
April 2026
Agent, Know Thyself! (and bid accordingly)
why we need to train models to learn their own capabilities, and how this will help them bid for work!
Apr 27
•
Rohit Krishnan
and
Andrey Fradkin
45
16
7
Aligned Agents Still Build Misaligned Organisations
agent handoffs launder uncertainty into official truth
Apr 24
•
Rohit Krishnan
34
4
3
Deciphering Papyri
analysing bureaucracy in roman egypt
Apr 24
•
Rohit Krishnan
3
1
LLM Enron: experiments on structure vs scale
can AI agents work inside a real organisation?
Apr 24
•
Rohit Krishnan
1
Can we build a management flight simulator?
turns out, yes
Apr 20
•
Rohit Krishnan
38
9
4
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
