OpenForgeRL: Train Harness-native Agents in Any Environment 25 July 2026·3 mins Machine Learning AI Engineering Paper Notes Machine-Learning Arxiv Agents Reinforcement-Learning Harness Llm-Training
Classic of the Week — Ilya Sutskever: Sequence to Sequence Learning, a Decade Later 25 July 2026·5 mins Machine Learning Talk Notes Llm Deep-Learning History Scaling Seq2seq Classic
Recursive Model Improvement: How Cursor Trains Composer 18 July 2026·6 mins Machine Learning AI Engineering Talk Notes Llm Reinforcement-Learning Cursor Coding-Agents Reward-Hacking Training
Pretraining Data Can Be Poisoned through Computational Propaganda 18 July 2026·2 mins Machine Learning Security Paper Notes Llm Security Pretraining Adversarial Ai-Safety
Don't Ship Skills Without Evals 18 July 2026·6 mins AI Engineering Machine Learning Talk Notes Ai-Engineering Llm Evals Agents Skills Gemini
Understanding the Inner Thoughts of AI — DeepMind on Interpretability 11 July 2026·5 mins Machine Learning Talk Notes Llm Interpretability Alignment Deepmind Mechanistic-Interpretability Sparse-Autoencoders
Super Weights in LLMs and the Failure of Selective Training 11 July 2026·7 mins Machine Learning Paper Notes Machine-Learning Arxiv Llm Fine-Tuning Lora Interpretability
When Millions of AI Agents Meet — DeepMind on Multi-Agent Economies 27 June 2026·4 mins Machine Learning AI Engineering Talk Notes Llm Agents Multi-Agent Ai-Safety Deepmind Game-Theory
When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models 27 June 2026·6 mins Machine Learning Paper Notes Machine-Learning Arxiv Llm Ensembles Routing Mixture-of-Agents
Hallucination in World Models is Predictable and Preventable 27 June 2026·6 mins Machine Learning Paper Notes Machine-Learning Arxiv World-Models Reinforcement-Learning Hallucination Coverage
Cooking with OpenAI's Research Chief — Mark Chen on AGI, o1, Evals, and Scaling Laws 27 June 2026·4 mins AI Engineering Machine Learning Talk Notes Ai-Engineering Llm Openai Scaling-Laws Reinforcement-Learning Evals O1
Why AI Labs With Unlimited GPUs Still Fail — Anjney Midha on Culture, Mission, and Execution 20 June 2026·5 mins Machine Learning AI Engineering Talk Notes Llm Ai-Engineering Ai-Labs Research-Culture Industry
Sierra's Voice Agent Architecture — Zach Reneau-Wedeen on Modular Multi-Model Pipelines 20 June 2026·5 mins AI Engineering Machine Learning Talk Notes Ai-Engineering Agents Voice-Ai Llm Production-Systems
Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers 13 June 2026·4 mins Machine Learning Distributed Systems Paper Notes Distributed-Systems Machine-Learning Optimization Asynchronous-Sgd Federated-Learning Arxiv
You Only Index Once: Cross-Layer Sparse Attention with Shared Routing 6 June 2026·6 mins Machine Learning Paper Notes Machine-Learning Nlp Arxiv Llm Long-Context Inference Sparse-Attention
Text Diffusion — Brendon Dillon, Google DeepMind 6 June 2026·4 mins Machine Learning AI Engineering Talk Notes Llm Diffusion-Models Inference Deepmind Ai-Engineering Gemini
SWE-rebench: Lessons from Evaluating Coding Agents 6 June 2026·5 mins AI Engineering Machine Learning Talk Notes Evals Coding-Agents Swe-Bench Llm Ai-Engineering Claude-Code
Pretraining Recurrent Networks without Recurrence 6 June 2026·6 mins Machine Learning Paper Notes Machine-Learning Arxiv Rnn Sequence-Modeling Training-Methods
Reasoning in Memory: Latent Reasoning Without Autoregressive Thoughts 30 May 2026·3 mins Machine Learning Paper Notes Machine-Learning Llm Reasoning Latent-Reasoning Working-Memory Arxiv
On Language Generation in the Limit with Bounded Memory 30 May 2026·3 mins Machine Learning Paper Notes Machine-Learning Theory Learning-Theory Language-Generation Arxiv