LLMs

Deterministic Core, Non-Deterministic Shell

Fourteen years after Functional Core, Imperative Shell, Outdata argues for a deterministic core with a non-deterministic shell—keeping pure logic testable while isolating AI and I/O uncertainty.

Essay · Programming · AI Agents · Software Architecture · LLMs

GenRec: Towards LLM-Native Recommendation at Netflix

Recommendations sit at the heart of the Netflix experience. Our current production models rely on thousands of hand‑crafted features over users, items, and interactions, along with specialized architectures for sequence modeling, feature interactions, and multi‑task objectives. This stack has evolved over many years to support diverse content types (movies, series, games, live, podcasts) and product surfaces, but its complexity makes it costly to onboard new use cases: adding a content type or surface can require significant feature engineering, architecture change,...

Blog post · AI · Machine Learning · LLMs · Engineering

Self-generated prompt injections in compaction summaries

Research on aligning AI with human values and intent, and reports documenting model failures.

Research · AI · AI Safety · Research · LLMs

Modern Engineering Values

Christoph Nakazawa updates his LLM workflow and names values that still matter with coding agents: ownership, taste, guardrails, repo context, owning your stack, and option value.

Essay · Engineering · LLMs · AI Agents · Software Engineering

AI Now Writes as Many Online Articles as HumansGraphite’s Common Crawl sample finds primarily AI-generated articles plateaued near 50%

Graphite’s Five Percent research averages three AI detectors across tens of thousands of English articles and finds primarily AI-generated pieces have plateaued near half of new articles since early 2025—after a steep rise following ChatGPT’s launch.

Research · AI · Writing · Research · LLMs

Harness engineering: leveraging Codex in an agent-first world

OpenAI engineer Ryan Lopopolo on harness engineering: how Codex and agent-first workflows reshape the scaffolding around models, from prompts and tools to evaluation and production loops.

Blog post · AI Agents · Engineering · LLMs · AI

Sparse Reward Subsystem in Large Language Models

Guowei Xu, Mert Yuksekgonul, and James Zou report a sparse reward subsystem in LLM hidden states: value neurons encode expected value, while dopamine neurons track reward-prediction error. The study finds these signals are robust across tasks and models and useful for confidence estimation and inference-time search.

Research · Research · Machine Learning · LLMs · AI

Your intellectual fly is open

Bryan Cantrill argues that LLM-generated LinkedIn posts are immediately recognisable to readers who have seen much AI content, and that using AI to write in your name undermines authenticity and signals to others that your stated views may not be genuine. He urges people to write in their own voice.

Opinion · LLMs · AI · Writing · Career

Cache-to-Cache: Direct Semantic Communication Between Large Language Models

Fu et al. propose Cache-to-Cache (C2C): multi-LLM systems exchange KV-cache semantics directly instead of text tokens, aiming for richer inter-model communication with lower latency and token cost.

Research · LLMs · Research · Machine Learning · AI