Recently updated channels

Pick one to see only that channelBrowse all channels →
Theo - t3․ggyesterday +43AI Engineeryesterday +1Matthew Berman2 days ago +478a16z2 days ago +1The Builders2 days ago +1硅谷1012 days ago +1SemiAnalysis2 days ago +1Chris Williamson2 days agoCheeky Pint2 days agoInvest Like The Best2 days ago

Results

85 articles
Sort
TopicBenchmarksPersonMatthew BermanLengthUnder 15 min
2 slides0:21EN
Matthew Berman· Oct 24, 2026An AI-Generated Kimi Benchmark Chart Used Invented ScoresMatthew Berman · Forward FutureMatthew Berman asks for a graph of Kimi K3.1 Pro benchmarks, then discovers that the displayed figures are illustrative placeholders.BenchmarksEvalsGenerative media
5 slides12:14EN
Matthew Berman· Oct 14, 2026Gemini 4 Argon Tested: 3D Demos, a Spreadsheet Prototype and Benchmark ResultsMatthew Berman · Forward FutureMatthew Berman tests Google’s model on games and visual projects, then compares reported coding and agent benchmarks.GeminiBenchmarksCoding agents+1
5 slides10:36EN
Matthew Berman· Oct 13, 2026Meta Muse Wonder Tested: Strong Benchmarks, Mixed Demos and Quota FrictionMatthew Berman · Forward FutureMatthew Berman tests Meta’s models on browser demos and reviews their published benchmark scores, availability and cost.Models & trainingBenchmarksAI cost & performance+1
5 slides7:26EN
Matthew Berman· Sep 23, 2026GPT-6 Sol and Luna: Price and Benchmark Trade-offsMatthew Berman · Forward FutureMatthew Berman examines OpenAI’s September 2026 launch, comparing API prices and reported agent benchmarks with larger models.OpenAIAI cost & performanceBenchmarks+2
10 slides13:31EN
Matthew Berman· Sep 4, 2026Matthew Berman Tests GPT-6 Astra with Games and Browser TasksMatthew Berman · Forward FutureAn early-access tour shows playable prototypes, computer-use demonstrations and a sponsor’s enterprise evaluation, alongside observations about visual style and limitations.Coding agentsComputer useAI cost & performance+2
9 slides13:09EN
Matthew Berman· Aug 14, 2026AI News: Ultrafast Inference, Claude Watermarks and New ModelsMatthew Berman · Forward FutureMatthew Berman reviews an ultrafast coding preview, text watermarking, Grok Bot, open-weight models and Computer History.InferenceOpen-weight modelsCoding agents+2
7 slides12:12EN
Matthew Berman· Jul 18, 2026Kimi K3: Coding Benchmarks, Cost and the Open-Weight AI RaceMatthew Berman · Forward FutureMatthew Berman examines Kimi K3’s early benchmark results, its cost per task and a Rubik’s Cube simulator, while weighing their limits.Open-weight modelsBenchmarksAI cost & performance+2
Slides0:25EN
Matthew Berman· Jul 17, 2026Kimi K3 Leads a Front-End Coding RankingMatthew Berman · Forward FutureMatthew Berman highlights Moonshot AI’s 2.8-trillion-parameter model and its early Arena result. The ranking covers one task, and the model weights followed after the video.Open-weight modelsBenchmarksCoding agents+1
Slides1:58EN
Matthew Berman· Apr 8, 2026Anthropic Restricts Claude Mythos Preview for Cybersecurity WorkMatthew Berman · Forward FutureMatthew Berman reacts to the April 2026 announcement of Project Glasswing and Anthropic's claims about its new model's security capabilities.AI securitySecurity & safetyAnthropic+1
5 slides9:47EN
Matthew Berman· Apr 3, 2026Gemma 4: Smaller Open-Weight Models for Local AIMatthew Berman · Forward FutureMatthew Berman reviews Google’s model sizes, multimodal features and reported benchmarks, with an eye toward local agents.Open-weight modelsLocal inferenceFoundation Models+2
1:56EN
Matthew Berman· Mar 28, 2026Matthew Berman Ranks AI Models: A Personal Tier List from March 2026Matthew Berman · Forward FutureClaude tops Berman’s list, while his views on open-weight models and Llama 4 reflect his own experience and the moment in which he recorded them.Models & trainingBenchmarksOpen-weight models
5 slides11:15EN
Matthew Berman· Mar 27, 2026ARC-AGI-3: Testing How AI Agents Learn the Rules of Unfamiliar GamesMatthew Berman · Forward FutureMatthew Berman explains ARC’s earlier grid puzzles and plays an interactive ARC-AGI-3 level, then examines early model results. The benchmark tests a specific form of adaptation rather than settling whether a system has general intelligence.AGIBenchmarksReasoning & test-time compute+2
2 slides0:25EN
Matthew Berman· Feb 20, 2026Gemini 3.1 Pro: Four Benchmark Results from Its 2026 LaunchMatthew Berman · Forward FutureMatthew Berman reviews reported academic, abstract-reasoning and coding scores; the chart distinguishes ARC-AGI-2 from GPQA Diamond.GeminiBenchmarksEvals
6 slides6:22EN
Matthew Berman· Feb 20, 2026Gemini 3.1 Pro: Benchmarks, Animated SVGs, and CAD DemosMatthew Berman · Forward FutureMatthew Berman reviews Google’s February 2026 model release, comparing reported benchmark results and examining examples of generated animations, an urban-planning app, and CAD code.GeminiBenchmarksGenerative media+2
Slides0:37EN
Matthew Berman· Feb 20, 2026Gemini 3.1 Pro: A Look at the Reported Benchmark ScoresMatthew Berman · Forward FutureMatthew Berman reacts to a Gemini 3.1 Pro comparison and highlights results on Humanity’s Last Exam.GeminiBenchmarksFoundation Models
9 slides11:49EN
Matthew Berman· Feb 17, 2026Matthew Berman Reviews Claude Sonnet 4.6: Benchmarks, Computer Use and SafetyMatthew Berman · Forward FutureA launch-day overview examines Anthropic’s reported knowledge-work and agent results, along with prompt-injection and capability evaluations.AnthropicFoundation ModelsBenchmarks+2
4 slides9:31EN
Matthew Berman· Feb 6, 2026GPT-5.3-Codex: Coding Agents, Speed and Computer Use at LaunchMatthew Berman · Forward FutureMatthew Berman reviews OpenAI’s February 2026 demonstrations and benchmarks, with a closer look at what the reported speedup and scores do—and do not—show.Coding agentsBenchmarksComputer use+2
8 slides14:20EN
Matthew Berman· Feb 5, 2026Claude Opus 4.6: Longer Context, Agent Teams and Early BenchmarksMatthew Berman · Forward FutureMatthew Berman reviews Anthropic's February 2026 model launch, its agent features, long-context results and historical pricing.AnthropicCoding agentsAgent orchestration+2
4 slides9:55EN
Matthew Berman· Dec 18, 2025Gemini 3 Flash: Speed, Coding Tests and the Cost of a Smaller ModelMatthew Berman · Forward FutureMatthew Berman examines visual coding demos and launch-era benchmarks, arguing that Google’s faster model could be useful for automation and everyday AI tasks.BenchmarksModels & trainingAI cost & performance+1
3 slides12:30EN
Matthew Berman· Dec 18, 2025AI News in December 2025: Gemini 3 Flash, Nemotron 3 and SAM AudioMatthew Berman · Forward FutureMatthew Berman reviews model releases, image generation, multi-model routing, data-center policy and reported AI investment talks.Foundation ModelsBenchmarksOpen-weight models+2
4 slides1:58EN
Matthew Berman· Dec 12, 2025GPT-5.2 at Launch: Benchmark Results, Demos and API PricingMatthew Berman · Forward FutureMatthew Berman reviews OpenAI’s December 2025 announcement, highlighting selected evaluations, product demos and the cost increase over GPT-5.1.OpenAIBenchmarksAI cost & performance+2
4 slides10:27EN
Matthew Berman· Nov 24, 2025Claude Opus 4.5: Launch Benchmarks, Pricing and Tool UseMatthew Berman · Forward FutureMatthew Berman reviews Anthropic’s November 2025 release, its coding benchmarks and developer tools, while comparing it with contemporary models.BenchmarksCoding agentsMCP & tools+1
8 slides12:47EN
Matthew Berman· Nov 20, 2025Gemini 3 Pro's Launch: Industry Reactions, Benchmarks and Google AntigravityMatthew Berman · Forward FutureMatthew Berman reviews early reactions to Gemini 3, from benchmark gains and coding demos to the economics of Google's AI stack.GeminiBenchmarksAI cost & performance+2
8 slides11:56EN
Matthew Berman· Nov 18, 2025Gemini 3 Pro: Benchmarks, Video Understanding and Google’s Agent ToolsMatthew Berman · Forward FutureMatthew Berman reviews Google’s November 2025 launch, exploring model benchmarks, a video demonstration, Search interfaces, Antigravity and Gemini Agent.GeminiBenchmarksMultimodal AI+2
Load moreShowing 24 of 85