Results
201 articlesSort
8:52EN
Matthew Berman· Jul 14, 2024Yi-Large Tested: Coding, Arithmetic and Logic PuzzlesMatthew Berman · Forward FutureMatthew Berman puts 01.AI's hosted model through a small set of coding and reasoning prompts, with mixed results and some questionable grading.
1:56:03EN
Cognitive Revolution "How AI Changes Everything"· Jul 13, 2024PodcastHumans Near a Perfect Score. The Best AI Still Gets 39%Host Nathan LabenzZapier co-founder Mike Knoop and François Chollet put $1 million on ARC-AGI, a 2019 test of sample-efficient intelligence that language models still cannot crack under a one-cent-per-puzzle budget.
11:30ENMatthew Berman· Jul 11, 2024Testing Google Gemma 2 27B: Coding, Reasoning and FormattingMatthew Berman · Forward FutureMatthew Berman runs an informal 2024 test of Google’s open-weight model on cloud hardware supplied by sponsor Vultr.
55:13EN
Sequoia Capital· Jul 2, 2024PodcastThe Best AI Scores 39% on This Test. Zapier’s Co-Founder Put $1 Million on Beating ItFrançois Chollet designed ARC to measure skill-acquisition efficiency; five years later humans still crush it and frontier models do not.
10:57ENMatthew Berman· Jun 24, 2024Testing Claude 3.5 Sonnet: Coding, Reasoning, and VisionMatthew Berman · Forward FutureMatthew Berman puts Anthropic’s June 2024 model through informal coding, math, puzzle, and image-understanding prompts.
16:11ENMatthew Berman· Jun 22, 2024AI News in June 2024: SSI, Tree Search, Meta, Claude and ARC PrizeMatthew Berman · Forward FutureMatthew Berman reviews new AI research, product launches and a competition, with context on historical benchmarks and uncertain claims.
27:37ENMatthew Berman· Jun 17, 2024Leo Pekelis on Extending Llama 3 to a Million-Token ContextMatthew Berman, Leo Pekelis · Forward FutureGradient’s chief scientist explains long-context training, coding use cases, inference costs and why retrieval benchmarks tell only part of the story.
26:00EN
No Priors: AI, Machine Learning, Tech, & Startups· Jun 11, 2024Podcast · 2 speakersWhy a Zapier founder thinks AGI research has been stalled for four yearsHost Sarah Guo, Elad GilMike Knoop and François Chollet put more than a million dollars on beating ARC-AGI, the eval they say actually measures general intelligence.
17:03ENMatthew Berman· Jun 8, 2024Qwen2 0.5B and 72B: A Hands-On ComparisonMatthew Berman · Forward FutureMatthew Berman tests coding, arithmetic and reasoning prompts on the smallest and largest Qwen2 models in a 2024 demonstration.
14:25ENMatthew Berman· Jun 2, 2024Testing Phi-3 Vision, LLaVA-Llama 3 and GPT-4o on ImagesMatthew Berman · Forward FutureMatthew Berman compares three 2024 vision setups on image descriptions, screenshots, a meme and table extraction, with mixed results.
9:53ENMatthew Berman· May 28, 2024Testing Microsoft Phi-3 Medium Locally: Mixed Coding and Reasoning ResultsMatthew Berman · Forward FutureMatthew Berman runs a quantized Phi-3 Medium on a MacBook and explores coding, arithmetic and reasoning prompts.
13:37ENMatthew Berman· May 16, 2024Testing Gemini 1.5 Pro’s Long Context and Video UnderstandingMatthew Berman · Forward FutureMatthew Berman’s 2024 tests show useful image and video summaries alongside blocked code and missed details.
16:25ENMatthew Berman· May 8, 2024Visualization-of-Thought and an Open-Source Windows AssistantMatthew Berman · Forward FutureMatthew Berman explains a spatial-reasoning prompting experiment and examines desktop automation demos from the separate PyWinAssistant project.
17:12ENMatthew Berman· Apr 30, 2024Testing the Mystery 'gpt2-chatbot' Model in April 2024Matthew Berman · Forward FutureMatthew Berman tries an anonymous model on coding, arithmetic and reasoning tasks while its identity remains uncertain.
19:09ENMatthew Berman· Apr 28, 2024OSWorld: Evaluating Computer-Use Agents in Real ApplicationsMatthew Berman · Forward FutureMatthew Berman explains the 2024 benchmark’s observation–action loop, task-specific checks and early results, with the limitations of its experimental setup.
21:47ENMatthew Berman· Apr 24, 2024Phi-3 Mini: Microsoft’s Small Model, Phone Deployment and an Uncertain Local TestMatthew Berman · Forward FutureMatthew Berman reviews Microsoft’s 2024 technical report and runs informal prompts, with an unresolved model label in the demonstration.
16:28ENMatthew Berman· Apr 23, 2024Testing Reka Core: Multimodal Benchmarks, Coding and ReasoningMatthew Berman · Forward FutureMatthew Berman reviews Reka’s reported model comparisons and tests Core on code, logic and image understanding.
12:51ENMatthew Berman· Apr 21, 2024Llama 3 70B on Groq: Fast Inference and an Informal Prompt TestMatthew Berman · Forward FutureMatthew Berman tests coding, reasoning and repeated prompts on Groq’s April 2024 Llama 3 service, with mixed results and several scoring caveats.
15:35ENMatthew Berman· Apr 18, 2024Meta Llama 3 Launch: Benchmarks, a Snake Test and the Meta AI AssistantMatthew Berman · Forward FutureMatthew Berman reviews the April 2024 release, tries a generated game and considers what downloadable models mean for developers.
14:21ENMatthew Berman· Apr 17, 2024Grok-1.5V Preview: Vision Examples and a New Spatial BenchmarkMatthew Berman · Forward FutureMatthew Berman reviews xAI’s 2024 multimodal model preview, its reported benchmark results and example image tasks.
1:00ENMatthew Berman· Apr 2, 2024LLM Colosseum: Language Models Play Street Fighter IIIMatthew Berman · Forward FutureMatthew Berman watches a short match in which language-model agents choose fighting-game actions from observations of the game.
1:20:44ENCognitive Revolution "How AI Changes Everything"· Mar 30, 2024PodcastSeeing Like a Mamba: Vision, Rotting States, and a Cell Model in 90 DaysHost Nathan LabenzNathan Labenz and Jason Meaux survey the vision papers, long-context experiments, and biology work that followed the original Mamba release.
8:26ENMatthew Berman· Mar 18, 2024Testing Grok on X After the 2024 Grok-1 Weight ReleaseMatthew Berman · Forward FutureMatthew Berman tries coding and reasoning prompts in the hosted Grok interface, with mixed results.
19:51ENMatthew Berman· Mar 15, 2024Devin’s 2024 Launch: Coding-Agent Demos and Benchmark ClaimsMatthew Berman, Scott Wu, Neal, Walden · Forward FutureMatthew Berman examines Cognition’s software-agent demonstrations, interface and SWE-bench comparison alongside earlier coding projects.Load moreShowing 24 of 201