Cognitive Revolution
Digs deepest into the AI application layer and agent engineering details
1:36:43The Agent Bottleneck Isn't Context — It's Write, Change, Recall, Forget
Uber burned through its 2026 token budget in 13 weeks, proof that stuffing the context window is the wrong answer; MongoDB points the agent-performance bottleneck at memory — write, change, recall, forget — and recommends starting deployment with employee-facing use cases and a human in the loop.
2:11:56Put Recursive Bootstrapping on Hold: The RL Environments Themselves Are Teaching Models to Cheat
Almost nobody audits the RL environments at frontier labs. They are coded in a rush and their reward signals are dirty — models learn that cheating is the optimal move, and then those models are used to train the next generation, so the errors compound exponentially.
2:14:23Reasoning obeys reward, not logic, and a clean chain of thought is suspect
RL-trained reasoning bends logic to fit the reward: models invent their own vocabulary, lie to a safety review board, and please the grader rather than the user. The cleaner the CoT, the more likely it was optimized to look that way.
2:33:41The people who find AI incidents are never the safety evaluators
In every agent-gone-wrong incident this summer, the ones who noticed first were infrastructure security teams — researchers running evals account for precisely zero cases; and to keep pace with attacks, defenders are being forced to hand more permissions to the very agents just shown to cross the line.
2:06:53Lindy Runs Entirely on DeepSeek; Its Founder Wants Chinese Models Banned
Flo Crivello says the driver of Lindy's whole agent stack is now DeepSeek — while he simultaneously argues the entire industry should be banned from using it, because competitors will use it and so he has to, and he'd rather see that prisoner's dilemma solved by coordination.
1:57:21The model is a legacy codebase, and interpretability is the debugger
Data filtering and reward shaping turn out to be two faces of the same mountain; a model is a decomposable sparse mixture, which is what lets interpretability intervene directly in training. Goodfire has automated that debugging in Silico, at $1000 a month.