Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
suttontom
3 months ago
|
parent
|
context
|
favorite
| on:
Claws are now a new layer on top of LLM agents
If all you're doing is telling an LLM to do something in all caps and hoping it follows your instructions then it's not a "security model" at all. What a bizarre thing to rely on. It's like people have literally forgotten how to program.
svnt
3 months ago
|
next
[–]
These people often never knew in the first place.
PlatoIsADisease
3 months ago
|
prev
|
next
[–]
Thank you for saying this. I read this and was like: wtf?
Love agents, but the security risk is insane.
PantaloonFlames
3 months ago
|
prev
[–]
“AI changes everything!”
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: