Kürzlich aktualisierte Kanäle

Wählen, um nur diesen Kanal zu sehenAlle Kanäle →
Matthew Bermanheute +239AI Engineerheute +6The Buildersheute +120VC with Harry Stebbingsgestern +350Jane Streetgestern +119Y Combinatorgestern +1硅谷101vorgesternPragerUvor 3 Tagena16zvor 4 Tagen +1SemiAnalysisvor 4 Tagen

Ergebnisse

10 Artikel
Sortieren
ThemaReinforcement LearningPersonMatthew BermanSpracheEnglisch
1:03EN
Matthew Berman· 9. Mai 2026Why 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.AgentenReinforcement LearningMulti-agent systems+1
4 Folien18:09EN
Matthew Berman· 15. Dez. 2025Training a GPT-OSS 2048 Strategy With Verifiable RewardsMatthew Berman · Forward FutureMatthew Berman walks through a local Unsloth notebook, reward checks and one 2048 training run on an RTX 5090.Reinforcement LearningPost-trainingOpen-weight models+2
5 Folien19:38EN
Matthew Berman· 20. Okt. 2025Andrej Karpathy’s AGI Timeline, Learning Ideas and Critique of Coding AgentsMatthew Berman · Forward FutureMatthew Berman examines Karpathy’s 2025 arguments for a decade of agents, new learning approaches and closer human oversight of AI coding.AGI TimelinesAI agentsReinforcement Learning+2
4 Folien2:01:29EN
Matthew Berman· 27. Sept. 2025AI Investing, Coding Competitions and the Future Economy: Forward Future LiveMatthew Berman, Nick Wentz, Mike Maples, Ahmed El-Kishky, Emad Mostaque · Forward FutureMike Maples, Ahmed El-Kishky and Emad Mostaque join Matthew Berman and Nick Wentz for a September 2025 discussion of AI startups, reasoning research and economic change.Venture CapitalCoding-AgentenReinforcement Learning+2
7 Folien15:13EN
Matthew Berman· 10. Mai 2025Absolute Zero: Training a Reasoner on Self-Generated Coding TasksMatthew Berman · Forward FutureMatthew Berman examines a 2025 paper in which a pretrained language model proposes and solves code tasks using verifiable feedback.Reinforcement LearningSynthetic dataReasoning & test-time compute+2
2 Folien17:20EN
Matthew Berman· 23. Feb. 2025Vibe Coding a Login Page and an AI Tetris PlayerMatthew Berman · Forward FutureMatthew Berman experiments with AI-written code, iterates through failures and trains a basic game-playing agent.Vibe CodingCoding-AgentenReinforcement Learning+1
3 Folien21:10EN
Matthew Berman· 11. Feb. 2025Sam Altman’s 2025 AI Coding Forecast and Three ObservationsMatthew Berman, Sam Altman · Forward FutureMatthew Berman examines predictions about reasoning models, software agents and AI economics, distinguishing competitive-programming results from broader work.Coding-AgentenScaling LawsReinforcement Learning+2
5 Folien10:01EN
Matthew Berman· 5. Feb. 2025DeepSeek R1 Code Optimization and a $3 Visual Counting ExperimentMatthew Berman · Forward FutureMatthew Berman examines a human-guided coding improvement and a small reinforcement-learning experiment, then considers their implications for AI research.Reinforcement LearningGPU programming & kernelsAI research+2
2 Folien30:29EN
Matthew Berman· 3. Jan. 2025How 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.Reinforcement LearningModelle & TrainingAI research+1
4 Folien21:00EN
Matthew Berman· 23. Jan. 2024Jim Fan's Foundation Agent Vision: Skills, Robot Bodies, and SimulationMatthew Berman, Jim Fan · Forward FutureMatthew Berman examines research on Minecraft agents, varied robot bodies, and simulation as steps toward more general embodied AI.RoboticsAgentenReinforcement Learning+2