LESSWRONG
LW

18
Wikitags

METR (org)

Edited by Ruby last updated 1st Jul 2024

Formerly ARC Evals

Subscribe
Discussion
Subscribe
Discussion
Posts tagged METR (org)
99METR's Observations of Reward Hacking in Recent Frontier Models
Daniel Kokotajlo
3mo
9
10Review of METR’s public evaluation protocol
nahoj, JaimeRV
1y
0
241METR: Measuring AI Ability to Complete Long Tasks
Ω
Zach Stein-Perlman
5mo
Ω
106
153ARC Evals new report: Evaluating Language-Model Agents on Realistic Autonomous Tasks
Ω
Beth Barnes
2y
Ω
12
139METR's Evaluation of GPT-5
Ω
GradientDissenter
1mo
Ω
15
108Clarifying METR's Auditing Role
Ω
Beth Barnes
1y
Ω
1
90Introducing METR's Autonomy Evaluation Resources
Megan Kinniment, Beth Barnes
2y
0
68Interpreting the METR Time Horizons Post
Ω
snewman
5mo
Ω
12
65METR is hiring!
Beth Barnes
2y
1
64CoT May Be Highly Informative Despite “Unfaithfulness” [METR]
Ω
GradientDissenter
1mo
Ω
3
59Reactions to METR task length paper are insane
Cole Wyeth
5mo
43
40ARC Evals: Responsible Scaling Policies
Zach Stein-Perlman
2y
10
20Improved visualizations of METR Time Horizons paper.
LDJ
6mo
4
20How far along Metr's law can AI start automating or helping with alignment research?
Q
Christopher King
6mo
Q
21
16METR: AI models can be dangerous before public deployment
UnofficialLinkpostBot
7mo
0
Load More (15/17)
Add Posts