YoutuBlog (HackerTube): lee charlas y pódcasts de YouTube

Canales actualizados recientemente

Elige uno para ver solo ese canalVer todos los canales →

Theo - t3․gghoy +1AI Engineerhoy +3Reid Hoffmanhoy +1Matthew Bermanayer +1GOTO Conferencesayer +2a16zayer +2Latent Spaceayer +2Chris Williamsonayer +2SemiAnalysisayer +1Everyayer +1

Resultados

46 artículosFiltros1

Ordenar

Más recientes

 Más recientesMás antiguosMás cortos

CanalNathan Lambert

2 diapositivas16:48EN

Nathan Lambert· 2 nov 2026Nathan Lambert on How Open Models Can Compete With Frontier LabsNathan Lambert · Allen Institute for AIOpen models are gaining use and closing capability gaps, but their builders need a sustainable economy and advantages beyond price.Open-weight modelsAI cost & performanceAI Strategy+1

3 diapositivas48:04EN

Nathan Lambert· 26 oct 2026Nathan Lambert on Open Language Models: History, Competition and RiskNathan Lambert · Allen Institute for AIA tour of open weights, research infrastructure, distillation, adoption and the choices facing model developers.Open-weight modelsAI researchAI Safety+2

46:42EN

Nathan Lambert· 25 oct 2026Nathan Lambert and Florian Brand on Kimi K3.1, Cyber Risk and AI AgentsNathan Lambert, Florian Brand · Allen Institute for AIThe Interconnects hosts discuss mixed model evaluations, a wave of security disclosures, and what a personal agent can do in everyday life.Open-weight modelsCybersecurityEvaluaciones+1

3 diapositivas5:42EN

Nathan Lambert· 12 ago 2026Why the Shoggoth Became a Mascot for AI Post-TrainingNathan Lambert · Allen Institute for AINathan Lambert traces a creature from Lovecraft to a visual metaphor for language models, fine-tuning, and RLHF.Post-trainingAI HistoryAI Alignment

3 diapositivas32:56EN

Nathan Lambert· 6 ago 2026Nathan Lambert: An Introduction to AI Character TrainingNathan Lambert · Allen Institute for AIHow post-training shapes a model’s behavior, from constitutions and model specs to experiments with personality and activation steering.Post-trainingAI AlignmentModel Interpretability+1

3 diapositivas32:11EN

Nathan Lambert· 5 ago 2026Nathan Lambert on How Language Model Evaluation Has EvolvedNathan Lambert · Allen Institute for AIFrom few-shot prompts and pass@k to agent sandboxes, noisy scores and benchmark contamination.EvaluacionesIngeniería de agentesBenchmarks+1

3 diapositivas13:53EN

Nathan Lambert· 4 ago 2026Nathan Lambert Answers Six Questions About Post-Training RecipesNathan Lambert · Allen Institute for AIA practical discussion of specialist models, KL penalties, supervised data, reinforcement learning and business tradeoffs.Post-trainingReinforcement LearningDistillation+1

4 diapositivas37:47EN

Nathan Lambert· 30 jul 2026Nathan Lambert on Tool Use and Training Language-Model AgentsNathan Lambert · Allen Institute for AIFrom structured tool calls and harnesses to the data, sandboxes and stability challenges of agentic reinforcement learning.Ingeniería de agentesPost-trainingReinforcement Learning+1

5 diapositivas1:06:30EN

Nathan Lambert· 29 jul 2026Scott Geng and Nathan Lambert: Bringing DPO Research Into OLMo 3Nathan Lambert, Scott Geng · Allen Institute for AIA preference-learning result showed promise in small experiments. Turning it into a model stage required data, organizational and infrastructure work.Post-trainingReinforcement LearningAI research+1

4 diapositivas31:33EN

Nathan Lambert· 28 jul 2026Nathan Lambert on KL Regularization, RL and Supervised Fine-TuningNathan Lambert · Allen Institute for AIWhy policy updates need control, how KL direction shapes objectives, and what experiments suggest about generalization and forgetting.Reinforcement LearningPost-trainingMachine Learning+1

4 diapositivas23:34EN

Nathan Lambert· 25 jul 2026Nathan Lambert on Over-Optimization and RLHF’s ReputationNathan Lambert · Allen Institute for AIWhy reward-model scores can rise as real behavior worsens, and how preference tuning can still improve useful capabilities.Post-trainingReinforcement LearningReward hacking+1

6 diapositivas35:53EN

Nathan Lambert· 20 jul 2026Nathan Lambert on Preference Data and the Foundations of RLHFNathan Lambert · Allen Institute for AIHow ideas from philosophy and control became preference models, and why collecting feedback remains difficult.Post-trainingReinforcement LearningData quality & curation+1

3 diapositivas14:55EN

Nathan Lambert· 1 jul 2026Nathan Lambert: Fixing RLHF Derivations and Reinforcement-Learning NotationNathan Lambert · Allen Institute for AIA reader-question roundup on KL estimates, reward-model losses, practical experiments and policy gradients.Post-trainingReinforcement LearningFundamentos de ML+1

4 diapositivas23:52EN

Nathan Lambert· 24 jun 2026Nathan Lambert: Machine-Learning Foundations for LLM Post-TrainingNathan Lambert · Allen Institute for AIA practical primer on token probabilities, masks, optimization, KL divergence and reinforcement learning.Post-trainingFundamentos de MLReinforcement Learning+2

6 diapositivas49:40EN

Nathan Lambert· 23 jun 2026Nathan Lambert on Synthetic Data and On-Policy DistillationNathan Lambert · Allen Institute for AIFrom teacher–student training and KL objectives to Constitutional AI, AI judges and rubric-based rewards.Post-trainingDistillationSynthetic data+2

3 diapositivas6:20EN

Nathan Lambert· 22 jun 2026Nathan Lambert on TMax: An Open Training Recipe for Terminal AgentsNathan Lambert · Allen Institute for AIWhy a release of terminal environments, model checkpoints and stable RL infrastructure matters for open agent research.AI agentsReinforcement LearningPost-training+2

2 diapositivas15:22EN

Nathan Lambert· 15 jun 2026Nathan Lambert Answers Questions on Teacher Models and PPONathan Lambert · Allen Institute for AIWhy the strongest teacher may not transfer best, and how PPO mathematics maps to language-model code.Post-trainingReinforcement LearningSynthetic data+1

6 diapositivas45:20EN

Nathan Lambert· 15 jun 2026Nathan Lambert on the Rise of Reasoning ModelsNathan Lambert · Allen Institute for AIA history of verifiable-reward training, reasoning-model releases and the implementation choices behind them.Reasoning & test-time computeReinforcement LearningPost-training+2

6 diapositivas42:44EN

Nathan Lambert· 15 jun 2026Nathan Lambert Explains DPO and Direct Preference OptimizationNathan Lambert · Allen Institute for AIThe derivation, practical limits and related algorithms behind a simpler way to train on preferences.Post-trainingReinforcement LearningAjuste fino+1

7 diapositivas46:10EN

Nathan Lambert· 14 abr 2026Nathan Lambert: An Overview of Post-Training and RLHFNathan Lambert · Allen Institute for AIFrom language-model pretraining and human preferences to the classic RLHF recipe and scaled reasoning.Post-trainingReinforcement LearningFoundation Models+2

3:35EN

Nathan Lambert· 14 abr 2026Nathan Lambert Introduces the RLHF Book Post-Training CourseNathan Lambert · Allen Institute for AIWhy the book and course document practical methods, mathematics and data used to train language models.Post-trainingReinforcement LearningEducation

8 diapositivas53:36EN

Nathan Lambert· 14 abr 2026Nathan Lambert on Implementing RL Algorithms for Language ModelsNathan Lambert · Allen Institute for AIA practical walkthrough of PPO, GRPO, distributed training and the loss-normalization choices that affect model behavior.Reinforcement LearningPost-trainingFundamentos de ML+1

8 diapositivas57:35EN

Nathan Lambert· 14 abr 2026Nathan Lambert Explains Policy Gradients for Language ModelsNathan Lambert · Allen Institute for AIFrom the policy-gradient theorem and variance reduction to PPO, GRPO and modern variants.Reinforcement LearningPost-trainingFundamentos de ML+1

7 diapositivas49:49EN

Nathan Lambert· 14 abr 2026Nathan Lambert on Instruction Tuning, Reward Models and Rejection SamplingNathan Lambert · Allen Institute for AIThe foundations of post-training, from chat templates and preference losses to selecting model-generated answers.Post-trainingAjuste finoReinforcement Learning+2

Cargar másMostrando 24 de 46