Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
idiotsecant
on July 16, 2025
|
parent
|
context
|
favorite
| on:
Chain of thought monitorability: A new and fragile...
Yes, it's not unlike human chain of thought - decide the outcome, and patch in some plausible reasoning after the fact.
bee_rider
on July 16, 2025
|
next
[–]
Maybe there’s an angle there. Get a guess answer, then try to diffuse the reasoning. If it is too hard or the reasoning starts to look crappy, try again new guess. Maybe somehow train on what sort of guesses work out somehow, haha.
BobaFloutist
on July 16, 2025
|
prev
[–]
That's famously been found in, say, judgement calls, but I don't think it's how we solve a tricky calculus problem, or write code.
Consider applying for YC's Fall 2026 batch!
Applications
are open till July 27.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: