HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
1.
▲
Anthropic's circuit tracer is now open source
github.com/safety-research
discuss
a year ago
jlaneve
3 points
2.
▲
Anthropic's Petri
github.com/safety-research
2 comments
8 months ago
kordlessagain
2 points
3.
▲
Anthropic's Circuit Tracer
github.com/safety-research
1 comment
a year ago
michaelmarkell
2 points
4.
▲
Petri AI Testing 'Closes' possible solution without looking
github.com/safety-research
discuss
7 months ago
Utharian
2 points
5.
▲
An alignment auditing agent capable of quickly exploring alignment hypothesis
github.com/safety-research
discuss
8 months ago
JnBrymn
2 points
6.
▲
Show HN: Agent that refuses to run commands without human approval
github.com/few-sh
5 comments
2 months ago
hexer303
12 points
7.
▲
DeepSeek-R1 Exhibits Deceptive Alignment: AI That Knows It's Unsafe
5 comments
a year ago
JefferyNeilW
8 points
8.
▲
Show HN: Annotated Paper – Easily read, annotate, and understand research papers
annotatedpaper.khoj.dev
4 comments
a year ago
sabaimran
3 points