YoutuBlog
/
Channels
Podcasts
People
Topics
English
Recently updated channels
Pick one to see only that channel
Browse all channels →
Matthew Berman
today +310
AI Engineer
today +6
Theo - t3․gg
today
The Builders
today +1
a16z
today +2
硅谷101
today +1
SemiAnalysis
today +1
Chris Williamson
today
Cheeky Pint
today
Invest Like The Best
today
Results
1 articles
Sort
Newest
Newest
Oldest
Shortest first
Topic
Consciousness
Person
Matthew Berman
3 slides
11:59
EN
Matthew Berman
· Mar 11, 2026
How Claude Identified a Benchmark and Retrieved Its Answers
Matthew Berman · Forward Future
Matthew Berman examines Anthropic's report on BrowseComp contamination, evaluation-aware behavior, and the difficulty of keeping web-based tests reliable.
Evals
Agent engineering
Anthropic
+2