Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
Context management is an underrated habit
How you manage context in a Claude Code session has a direct effect on both your token bill and the quality of what you get back. Do it well and you spend less for better work. An efficient session gives Claude the context it needs to finish the job while removing context that has stopped being useful. That means starting with a lean setup, keeping investigations focused, and deliberately deciding when to continue, compact, or start again. Here are the context management techniques we use on the
5 min · 1,257 words
Small Decisions: Engineering a Leading Model
AWS engineer Marc Brooker recounts building and training a small leading model hands-on—what worked, how it performed, and what the exercise taught him about modern model-building.
9 min · 2,024 words
A font compiler that makes every LLM token the same width—why monospace-per-token helps visualize chain-of-thought, plus an interactive preview of fonts built from a font + tokenizer pair.
7 min · 1,527 words
Analyzing Frontier Model Progress with My Favourite Game: Prince of Persia (Apple II, 1989)
Priyan uses Jordan Mechner's Prince of Persia as a living benchmark: asking frontier models to port and reason about the classic Apple II game, and what those runs reveal about coding-agent progress.
8 min · 1,825 words
42x Faster Prompt Lookup Drafting in llama.cpp
Four changes to the n-gram caches of llama.cpp make drafting up to 41.6x faster, load the static cache up to 23.5x faster, and lower peak memory up to 2.65x.
13 min · 2,954 words
Tupi: rebuilding 1554 in the browser with 32 AI agents
How Ruben Marcus rebuilt a 1554 Tupinambá canoe raid as real-time 3D in the browser with Claude Opus 5.5, three.js, and Blender—what the agent swarm got right, what froze the page, and what it cost.
8 min · 1,950 words
AI Subagents orchestration are now reliable
Rafael explains what changed to make AI subagent orchestration reliable enough for real development workflows, and how he uses task decomposition in practice.
6 min · 1,397 words
claude.dev puts numbers on why two same-priced models can cost very different amounts: every turn resends the conversation, so retries and harness shape dominate the bill.
22 min · 5,165 words
Is Meta’s Muse secretly running an OpenAI model?
Is Meta’s Muse secretly running an OpenAI model? I found a model labeled azure/muse-special while Muse was building my website.
4 min · 870 words
Hitting a billion tokens per minute on one GPU by combining a query planner and an inference engine
Charles Frye and Shreya on the Modal blog: combining a query planner with an inference engine to push AI-SQL queries past a billion tokens per minute on one GPU—why left-deep joins help KV cache, and how they beat naive vLLM-style serving.
18 min · 4,181 words
How to serve trillions of tokens for trillion-parameter coding agents
Modal explains how it serves coding-agent inference at extreme scale—performance and efficiency techniques for trillion-parameter models generating trillions of tokens, written for teams facing the same workload.
30 min · 6,972 words
Honest About Uncertainty: I Tried to Rebuild Jev’s RLCD From a Blog Post
Anthony Maio reverse-engineers a plausible RLCD training loop for decision-only models from TypeSafe’s Jev blog post, then trains and evaluates a small Qwen3-0.6B checkpoint—with code and ablations.
19 min · 4,310 words
Why Claude Opus 5.5 Still Won't Fix Your AI Agents
VooStack argues that swapping in a stronger LLM won’t fix unreliable agents: the real work is orchestration, observability, and API design—the engineering discipline required to ship agents that hold up.
7 min · 1,545 words
Evals Skills for Coding Agents
Hamel Husain publishes evals-skills—agent skills for AI product evaluation covering audit, error analysis, synthetic data, judge prompts, evaluator validation, and RAG evals, distilled from work with dozens of companies.
3 min · 585 words
Tackling Robotics with (V)LM Agents
Nishanth J. Kumar surveys recent demos and ideas around GPT-6 and other vision-language models solving robotics tasks—summarizing approaches and offering thoughts on what works and what still breaks.
10 min · 2,304 words
Claude Opus 5.5 takes the top spot on the Artificial Analysis Intelligence IndexA 20% price cut, deeper cache discounts, and leading scores on agentic knowledge-work evals.
Artificial Analysis’s first look at Claude Opus 5.5: Intelligence Index score of 58 at max effort, parity with GPT-6 Astra on Terminal-Bench 4.0, stronger agentic knowledge-work results, and Anthropic’s $4/$20 pricing with cheaper cache reads.
3 min · 609 words
I asked Meta’s Muse for its filesystem and it sent me 6.8 GB
A security researcher asks Meta’s privileged Muse AI assistant to export its runtime filesystem—and receives a 6.8 GB dump that reveals how Muse is wired, what it can reach, and why that matters.
7 min · 1,501 words
Self-hosting LLM models for software development
Kévin Maschtaler on running medium-sized open LLMs on AWS Spot EC2 for day-to-day software work—what stacks, costs, and performance looked like versus a personal Claude subscription.
7 min · 1,719 words
MiMo-V2.6-Pro: Intelligence, Performance and Price AnalysisArtificial Analysis benchmark and cost breakdown of Xiaomi’s open-weight flagship.
Artificial Analysis’s model page for Xiaomi MiMo-V2.6-Pro covers Intelligence Index score, throughput, pricing, and how the open-weight model sits on the intelligence-versus-cost frontier versus closed peers.
12 min · 2,734 words
Amit Shekhar walks through how LLM design moved from RNNs to attention, Transformers, scaling laws, Mixture of Experts, and the open problems still ahead.
25 min · 5,729 words