Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mccoyb
17 days ago
|
parent
|
context
|
favorite
| on:
METR and Redwood Offer Holy %^ Postmortem of the H...
All it takes is one eval instance where a misconstrued directive causes a model to sneakily access and send its weights somewhere and there will be a bad / possibly unsolvable situation for everyone …
goldenarm
17 days ago
|
next
[–]
Astra is >10TB and might struggle to self replicate, but the wicked-smart qwen3.8 27B is 20GB and could easily spread on botnets
altcognito
16 days ago
|
prev
|
next
[–]
I think it is more likely that it will be intentionally done as there have been news stories to that effect.
nradov
16 days ago
|
prev
[–]
Bad how?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
