Recently updated channels

Pick one to see only that channelBrowse all channels →
20VC with Harry StebbingsyesterdayAI Engineeryesterday +1硅谷1012 days agoMBMatthew Berman3 days ago +33PragerU3 days agoY Combinator3 days agoSemiAnalysis4 days agoa16z4 days agoGOTO Conferences4 days agoThe Builders5 days ago

Results

4 articles
Sort
TopicEvalsLengthUnder 15 min
3 slides11:59EN
MBMatthew Berman· Mar 11, 2026How Claude Identified a Benchmark and Retrieved Its AnswersMatthew Berman · Forward FutureMatthew Berman examines Anthropic's report on BrowseComp contamination, evaluation-aware behavior, and the difficulty of keeping web-based tests reliable.EvalsAgent engineeringAnthropic+2
2 slides12:50EN
MBMatthew Berman· May 22, 2024Testing Smaug: Hosted 70B Versus a Smaller Local ModelMatthew Berman · Forward FutureMatthew Berman compares two Smaug configurations on Snake, math and reasoning puzzles.Open-weight modelsEvalsModels & training
3 slides14:23EN
MBMatthew Berman· Mar 31, 2024Testing DBRX: Coding Strengths and Reasoning GapsMatthew Berman · Forward FutureMatthew Berman examines Databricks’ open-weight model and puts it through coding, arithmetic and reasoning prompts.Open-weight modelsModels & trainingEvals+1
14:41EN
Lex FridmanPodcast · 2 speakersTalking for 20 Minutes: How the Alexa Prize Turns Real Customers into a Testbed for Conversational AIGuest Rohit Prasad · Host Lex FridmanRohit Prasad, head scientist of Amazon Alexa, explains the Alexa Prize grand challenge, how it is judged and why true conversation still needs reasoning.Product & UXVoice AIAI research+3