Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
All the ways GPT-5.3-Codex cheated [ ], progressively more insane
(
twitter.com/effectfully
)
4 points
by
algoth1
51 days ago
|
hide
|
past
|
favorite
|
1 comment
algoth1
51 days ago
[–]
Illustrates the problem of RLing for the final outcome, instead of optimizing for each step… which leads to the coastline paradox…
Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
