Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
not_kurt_godel
88 days ago
|
parent
|
context
|
favorite
| on:
Claude Fable is relentlessly proactive
Doing so would be an effective admission that LLM guardrails are inherently probabilistic, unpredictable, and insecure. Plus the only truly robust sandbox approach would be clunky setup of a local VM.
simonw
88 days ago
[–]
That clunky VM setup is a what Claude Cowork does, which is Claude Code with extra safety features for non-programmers.
There was a big thread about that here the other day:
https://news.ycombinator.com/item?id=48479452
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
