Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
embedding-shape
15 days ago
|
parent
|
context
|
favorite
| on:
Claude Code On-the-Go
Probably always be true, but also probably not effective in the wild. Researchers will train a version, see results are off, put guards against poisoned data, re-train and no damage been done to whatever they release.
d-lisp
15 days ago
[–]
How would they put guards against poisoned data ? How would they identify poisoned data if there are a lot/obfuscated ?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
