LESSWRONG
LW

1368
gasteigerjo
280Ω231720
Message
Dialogue
Subscribe

Working on Alignment Science at Anthropic

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
AI Safety at the Frontier: Paper Highlights, December '24
gasteigerjo9mo10

This is normal. Workshops are non-archival and conferences only require that the work hasn't been submitted to any archival venues.

[edit to extend]: Researchers will often submit their work to a conference and one or even multiple workshops in parallel. Workshops are great at getting a more targeted audience and discussion. It's also a strategy to get more people to see your paper.

Reply
(The) Lightcone is nothing without its people: LW + Lighthaven's big fundraiser
gasteigerjo10mo10

I'll also give at least £5k if tax deductibility is set up in the UK.

Reply2
7AI Safety at the Frontier: Paper Highlights of October 2025
13d
0
49Training fails to elicit subtle reasoning in current language models
1mo
3
5AI Safety at the Frontier: Paper Highlights, September '25
2mo
0
12AI Safety at the Frontier: Paper Highlights, August '25
3mo
0
7AI Safety at the Frontier: Paper Highlights, July '25
3mo
0
4AI Safety at the Frontier: Paper Highlights, June '25
4mo
0
6AI Safety at the Frontier: Paper Highlights, May '25
5mo
0
4AI Safety at the Frontier: Paper Highlights, April '25
6mo
0
9AI Safety at the Frontier: Paper Highlights, March '25
7mo
0
44Automated Researchers Can Subtly Sandbag
Ω
8mo
Ω
0
Load More