Effective Altruism ForumTopics
EA Forum

Hide table of contents

AI benchmarks

EditHistory
Discussion (2)
EditHistory
Discussion (2)
Random Topic
Contributors
4MichaelA
1Toby Tremlett🔹
You are viewing revision 1.4.0, last edited by Toby Tremlett🔹

Benchmarks are tests which enable us to measure the progress of AI capabilities, and test for characteristics which might pose safety risks. 

...

(Read more)

Posts tagged AI benchmarks

Relevance
35
Trendlines in AIxBio evals
ljusten
· · 14m read
2
4
2
4
12
Open Phil releases RFPs on LLM Benchmarks and Forecasting
Lawrence Chan
·
0
3
0
3
193
Results from an Adversarial Collaboration on AI Risk (FRI)
Forecasting Research Institute
· · 11m read
25
2
25
2
127
Announcing Epoch’s dashboard of key trends and figures in Machine Learning
Jaime Sevilla
·
4
2
4
2
124
Long list of AI questions
NunoSempere
· · 103m read
14
2
14
2
96
A compute-based framework for thinking about the future of AI
Matthew_Barnett
· · 23m read
36
2
36
2
78
AI Forecasting Research Ideas
Jaime Sevilla
· · 1m read
1
2
1
2
59
Language models surprised us
Ajeya
· · 6m read
10
2
10
2
56
Prizes for ML Safety Benchmark Ideas
Joshc
· · 1m read
8
2
8
2
47
$250K in Prizes: SafeBench Competition Announcement
Center for AI Safety
· · 2m read
0
2
0
2
38
Survey on the acceleration risks of our new RFPs to study LLM capabilities
Ajeya
· · 10m read
1
2
1
2
38
Announcing Epoch's newly expanded Parameters, Compute and Data Trends in Machine Learning database
Robi Rahman
· · 1m read
1
2
1
2
37
XPT forecasts on (some) Direct Approach model inputs
Forecasting Research Institute
· · 10m read
0
2
0
2
51
Race to the Top: Benchmarks for AI Safety
isaduan
· · 2m read
8
1
8
1
50
Announcing the AI Forecasting Benchmark Series | July 8, $120k in Prizes
christian
· · 5m read
4
1
4
1