Y
Hacker News
new
|
ask
|
show
|
jobs
user:
allenleee
created:
2014-11-05
karma:
7390
interpretability, rl, ai safety
https://fp8.vercel.app
submissions:
Meta's Infrastructure Team Needs a Culture Reset
4 points
|
0 comments
External Commentary on LLM Global Workspace Representations [pdf]
1 points
|
0 comments
Reflect Open – a new chapter for Reflect
2 points
|
0 comments
AirPosture – AirPods as AI posture coach (Open source)
2 points
|
0 comments
Show HN: AirPosture – Open-Source Posture Coach Using AirPods
4 points
|
1 comments
FPGA Development Deep Dive
2 points
|
0 comments
Looking for Backdoors in Jane Street LLMs
3 points
|
0 comments
0 points
|
0 comments
The West Is Losing Taiwan
2 points
|
4 comments
Measuring LLMs' ability to develop exploits
3 points
|
0 comments
From Open Source Software to Open Source Strategy
1 points
|
0 comments
RTX 5090 and M4 MacBook Air: Can It Game?
699 points
|
180 comments
Test your interpretability techniques by de-censoring Chinese models
2 points
|
0 comments
The state of AI safety in four fake graphs
3 points
|
0 comments
Modeling the AGI Economy
2 points
|
0 comments
Test your interpretability techniques by de-censoring Chinese models
2 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
Ask HN: What developer tool do you wish existed in 2026?
22 points
|
24 comments
0 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
YC's Formula for Startup Manufacturing
4 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments