Résultats
40 articlesTrier
1:14ENWhat Matthew Berman’s Team Built With Sonnet 5.5Matthew Berman · Forward FutureA short showcase presents an ocean simulation, game prototypes, city rendering and a LEGO design tool.
17:15ENThe Hugging Face Incident: AI Evaluation, Sandbox Escape and Reward HackingMatthew Berman · Forward FutureMatthew Berman explains the reported OpenAI evaluation incident and the security and incentive failures it exposed.
9:15ENSix Open-Source Projects for Local AI, Agents, and 3D DesignMatthew Berman · Forward FutureMatthew Berman tours tools for running and training models, giving agents new skills, coordinating work, browsing, and generating 3D meshes.
52:29ENClaude Opus 5: Benchmarks, Cost per Task, and Early ImpressionsMatthew Berman · Forward FutureMatthew Berman reacts to the model launch, examines reported benchmark and pricing data, and explains why the cost of completing a task matters more than token price alone.
18:34ENModel Routing for AI Coding: A Worked Cost ExampleMatthew Berman · Forward FutureMatthew Berman separates planning, implementation and review to explain how different models can fit different tasks.
1:03ENWhy EVE Online Is an Interesting Environment for AI ResearchMatthew Berman · Forward FutureMatthew Berman explains why the game's persistent economy and player alliances may offer a demanding test of long-term planning.
11:59ENHow 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.
10:17ENAnthropic Subscription Credentials and OpenClaw: A 2026 Policy DisputeMatthew Berman · Forward FutureMatthew Berman explains why restrictions on Claude subscription OAuth credentials prompted him to change his OpenClaw model setup.
12:23ENMoltbook: An AI Agent Social Network and Its Security QuestionsMatthew Berman · Forward FutureMatthew Berman explores conversations attributed to AI agents on Moltbook and considers privacy, manipulation and operating costs.
1:08ENWill AI Change What Programmers Do?Matthew Berman · Forward FutureMatthew Berman responds to Ryan Dahl's prediction about writing code and argues that systems thinking will remain important.
1:02ENA Speed-Reading Display That Shows One Word at a TimeMatthew Berman · Forward FutureA short visual demonstration presents words in rapid succession at increasing displayed speeds.
1:36ENWhy Humanoid Robots Can Move Beyond Human LimitsMatthew Berman · Forward FutureMatthew Berman explains why joints that rotate beyond human ranges could help robots work in factories.
5:13ENTesting Meta’s SAM Audio: Isolating Voices and InstrumentsMatthew Berman · Forward FutureMatthew Berman demonstrates prompt-based sound separation and effects in a Meta-partnered video.
5:55ENTurning Images into 3D Models with Meta SAM 3DMatthew Berman · Forward FutureMatthew Berman demonstrates object extraction, body reconstruction, and a 3D-printing workflow in Meta's SAM Playground.
1:11ENGemini 3's Launch: Benchmarks, Antigravity, and AgentsMatthew Berman · Forward FutureMatthew Berman summarizes Google's November 2025 model launch and its developer and assistant demos.
10:45ENWorld Labs Marble: Generate and Edit Navigable 3D WorldsMatthew Berman · Forward FutureMatthew Berman demos Marble’s multimodal inputs, scene editing and 3D navigation, including an attempt to recreate his office from one image.
18:31ENTesting Nano Banana: Gemini 2.5 Flash Image EditingMatthew Berman · Forward FutureMatthew Berman tests character consistency, image edits, generation, visual sequences and common failure cases.
7:33ENAce Computer-Use Agent: Fast Desktop and Browser DemonstrationsMatthew Berman · Forward FutureMatthew Berman reviews General Agents’ examples and reported click accuracy and latency, while noting he has not yet tested Ace himself.
5:27ENWays to Try DeepSeek R1: Hosted and Local Distilled ModelsMatthew Berman · Forward FutureMatthew Berman demonstrates DeepSeek chat, Groq’s hosted distill and a local model in LM Studio.
2:57ENChatGPT Tasks: Scheduled Reminders at the 2025 LaunchMatthew Berman · Forward FutureMatthew Berman explains the initial beta of scheduled and recurring ChatGPT tasks, and places it in the context of AI assistants.
30:29ENHow Researchers Think o1-Style Reasoning Models WorkMatthew Berman · Forward FutureMatthew Berman explains a research survey of policy initialization, rewards, search and reinforcement learning, and the open questions behind reasoning models.
19:06ENBuilding Effective AI Agents: Patterns, Trade-offs and EvaluationMatthew Berman · Forward FutureMatthew Berman discusses Anthropic’s guide to workflows and agents, adding examples from his own projects.
13:34ENSam Altman’s “Intelligence Age”: Superintelligence, Scaling and WorkMatthew Berman · Forward FutureMatthew Berman reads Altman’s 2024 essay and discusses its predictions for AI assistants, education, infrastructure and jobs.
0:54ENOpenAI’s o1 Preview: A First Look at Longer ReasoningMatthew Berman · Forward FutureMatthew Berman introduces the o1-preview and o1-mini models and tries a Python game prompt.
Charger plus24 sur 40 affichés