Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
Multi-agent LLM coordination in a Pokémon 2v2 environment
Oliver Grabner introduces an open environment where two LLM agents share a side in 4-player Pokémon Showdown battles and can talk before every turn, measuring whether natural-language coordination wins more battles and what it costs.
3 min · 737 words
Production-grade LLMs and agents: a field guide
Stack Overflow’s maturity map for taking LLM agents from demos to production: determinism, evaluation, confidence, safety, operability, and disciplined coding-agent builds.
3 min · 704 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
Publish stats, get cited: The tactic that put my data all over the web
Metehan Yesilyurt of Peec AI describes an experiment: a $50 site of 50,000 AI-generated, unverified statistics that Google quickly buried but ChatGPT kept citing, driving 10,000+ AI sessions and links from 330+ domains, with the fake numbers reaching an academic paper and bank research. He draws GEO lessons and an ethics caveat.
11 min · 2,588 words
ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks
Research write-up extending ELF continuous diffusion language models to math and code reasoning via representation alignment and entanglement (REPA+REG), plus early-stop generation for strong few-step performance without dedicated few-step training.
8 min · 1,875 words
Clojure in the Age of Language Models
Yogthos argues that as LLMs make writing code cheap, the valuable skill is high-level reasoning about data and design — and that Clojure's declarative, data-oriented, REPL-driven style fits both agents and humans, with Jolt potentially removing the remaining friction.
6 min · 1,283 words
Base Models Can Reason By Taking a Cue From Training Data
Sophie L. Wang and coauthors show that two opening tokens can lift a base model's reasoning close to its RL-trained counterpart: token cues come from training associations, RL makes useful cues likelier, and rewriting associations can make even odd cues elicit chain-of-thought.
6 min · 1,349 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
Why Isn't The Industry Freaking Out About DeepSeek 4.1 Flash?
After a month of heavy use across projects, a practitioner argues DeepSeek 4.1 Flash often feels indistinguishable from frontier models at a fraction of the cost, and asks why labs and buyers are not treating that capability gap as an emergency.
3 min · 691 words
GPT-6 and Intelligent UI for everyone
OpenAI rolls out a new GPT-6 model to all ChatGPT users with Intelligent UI, which lets answers include visuals, charts, forms, buttons and small interactive tools built from a streamable component library. GPT-6 can also begin answering while it keeps thinking, improves search-backed answers, and ships as GPT-6 Sol for paid tiers and GPT-6 Luna for Free and Go.
5 min · 1,152 words
Anthropic launches Claude Haiku 5.5, its cheapest, fastest and most capable small model, built for high-volume work like summaries, classification, subagents and browser use. It costs around 75% less to run than Haiku 4.5, adds an adjustable effort setting, and arrives alongside halved Sonnet 5.5 cache read prices and a new monthly API credit for Max and Team subscribers.
5 min · 1,045 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
Mistral launches a public API preview of Mistral Large 4 ("le Chonk"), a 1-trillion-parameter natively multimodal mixture-of-experts model with 49B active parameters, pitched as the strongest open-weight model from the US or Europe, with weights due at the end of the month and training funded by its €3B Series D.
10 min · 2,203 words
Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents
Microsoft Research paper on idea basins in long-horizon autoresearch agents, and a periodic fork-and-flush intervention that keeps the workspace but resets chat context—reporting +66% vs single-run under equal compute across 13 tasks.
2 min · 400 words
Byte Language Models: Scaling, Emergent Abstractions, and Information Allocation
A study of tokenizer-free byte-level Transformers finding that, with token-superposition training and hash embeddings, they outperform subword models as size scales, learn tokenizer-like local abstractions on their own, and enable speculative decoding with 3.4x more accepted tokens.
1 min · 164 words
Strands Decider: Why Not an Encoder?
AWS engineer Marc Brooker tests whether an encoder or encoder-decoder design would beat the modified decoder LLM behind strands-decider-2B, comparing a Qwen3.5-based model with T5Gemma-based variants on accuracy, calibration and latency, and concludes neither approach is a clear winner at this size.
3 min · 749 words
Jonas Schäfer argues that LLM quality has improved enough that “AI output is bad” no longer works as a blanket objection—quality arguments lost, so the harder fights are about labor, ecology, control, and what we still choose to do ourselves.
9 min · 2,037 words
Aleph Alpha Kolibri: How the Sovereign German LLM Works
Tejas Kumar explains Aleph Alpha's Kolibri, an open-weight German and English mixture-of-experts LLM with 78B parameters and about 3.5B active per token: how it works, how it was trained in Germany and Finland, where it is strong or weak, and when to use it.
13 min · 3,074 words
“Just Ask Claude” Is A Rare And Valuable Skill
Justis Mills on why, when someone asks you for help and you simply ask an AI, they usually couldn't have done it themselves: they avoid AI, don't pay for premium models, are behind the times, lack the latent knowledge you bring to the prompt, or simply want to connect with you.
2 min · 563 words
Of Mottes, Baileys, and Stochastic Parrots
Manoel Ribeiro argues the "stochastic parrots" metaphor often motte-and-baileys: it dismisses LLM capabilities, then retreats to the trivial claim that models predict the next token.
6 min · 1,470 words