Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?
Max Woolf walks through a timeline of OpenAI and Anthropic model launches since June 2026, showing input, output and cache prices falling by up to 80%, and weighs possible reasons including competition from open-weight models, compute capacity and upcoming IPOs, concluding that cheaper LLMs are good for users.
11 min · 2,568 words
The State of Context Engineering
Drew Breunig shares the slides and lightly edited transcript of his AGNTCon talk “Context Fails & Fixes”, tracing how context engineering emerged, the failures new model capabilities create for harness builders, and his argument that the job is choosing where to be deterministic and where to be probabilistic.
22 min · 5,114 words
Drew Silcock walks through a week of severe vulnerabilities and incidents, from the PHP2Shell CVEs and a compromised eMudhra intermediate CA to GitLab, musl, LiteLLM and leaked Linux kernel bugs, then asks whether AI-accelerated bug discovery makes this the new normal and what teams can do about it.
19 min · 4,290 words
Amrut Joshi explains why agent designers should not trust confidence scores or probabilities generated by an LLM, and argues for rules built from your own measured records of whether replies were correct instead.
7 min · 1,673 words
Putting Linux on my RTX Spark laptop because I don't have a Microsoft account
Josephine Pfeiffer gets Arch Linux ARM running on the Windows-only ASUS ProArt P16 with NVIDIA's N1X chip, publishing a bootable installer and patches, comparing CPU performance against Windows in 7-Zip, explaining the 116 GiB unified memory split, and benchmarking local Qwen inference.
6 min · 1,453 words
I built a programming language that LLMs can't use
Dominik Picheta introduces KillSwitch, an esoteric language designed to confound coding agents, and reports how frontier models fare on a small human-solvable task set.
3 min · 803 words
Hyper Optimizing Kimi K3 in vLLM: Moving Fast and Responsibly
The vLLM team and NVIDIA describe using coding agents to build a unified CuTe DSL decode path for Kimi K3 on NVIDIA GB300, reaching over 840 tokens/s at batch 1 on 16 GPUs, and the guardrails (isolated changes, correctness tests, reproducible benchmarks) used to land agent-written kernels responsibly.
10 min · 2,277 words
Doug Turnbull experiments with treating search queries as a "bag of decisions": an LLM generates query-specific yes/no relevance questions, Jev answers them per document, and the results are combined into a reranker, with code and evaluation results.
2 min · 561 words
I gave Opus 5.5 one prompt and six hours to visualize Invisible Cities
Piotr Migdał asks Claude Opus 5.5 to turn Italo Calvino's Invisible Cities into interactive visualizations in a single long session, reflecting on what 'vibe designing' can and cannot do for explorable explanations.
3 min · 609 words
Armin Ronacher explains why Pi 1.0 added MCP support through Codemode despite his long preference for bash and scripts: bash can only compose programs that run in the execution environment, while Codemode lets the model orchestrate harness-side tools like image reads and sub agents in a sandboxed QuickJS/WASM runtime, plus the open problems that remain.
12 min · 2,672 words
One vector is too few. One per token is too many.
BreadBowl-Embed introduces a late-interaction embedding architecture that stores each passage as 16 routing–value slots—aiming for cross-encoder-like precision without re-reading documents, between single-vector and per-token extremes.
15 min · 3,524 words
One month coding with GLM 5.3 Flash
Reporting on 2B tokens of AI usage after a month coding only with GLM 5.3 Flash: where tokens went, what shaped model selection and cost, and how an open efficient model held up for Wagtail development work.
3 min · 735 words
Spring AI Modular RAG and TypeSafe Jev: Retrieve More, Keep Only What Answers
Christian Tzolov walks through Spring AI modular RAG plus TypeSafe Jev: rewrite/expand the query before retrieval, then keep only chunks that actually answer—contrasting naive QuestionAnswerAdvisor RAG with a live demo pipeline.
6 min · 1,487 words
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
How we built long-term memory for Alyx: why we chose a file over a knowledge graph
Arize engineer Priyan Jindal recounts building long-term memory for the Alyx AI engineering agent: after weeks on vectors and knowledge graphs, they shipped one structured 8,000-character text file per user/space, read on every request—and how they update, compact, and test it.
23 min · 5,269 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