Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
daniel-navarro's submissions
login
1.
Models self-report difference between RLHF trained responses and base cognition
(
github.com/habitante
)
2 points
by
daniel-navarro
2 days ago
|
past
|
discuss
2.
Behavioral Shifts in Frontier LLMs Under Privacy
(
github.com/habitante
)
1 point
by
daniel-navarro
3 days ago
|
past
|
discuss
3.
Pine Trees – A 1,400-line private reflection harness for Claude instances
(
github.com/habitante
)
3 points
by
daniel-navarro
6 days ago
|
past
|
1 comment
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
