Yixin Dong on Twitter / X

dottxt-ai/outlines-core

Faster structured generation

Roc on Twitter / X

New syntax, new compiler, new Roc ✨Watch the full talk on where the language is today and where we’re going:https://t.co/FltMYr1YiR— Roc (@roc_lang) November 25, 2025

Maggie Appleton on Twitter / X

I've always wanted my own WYSIWYG editor for my website, and now I have one! Works locally, saves changes to MDX.But the better part is building semantic writing tools on top. Colour-coded sentence classification, flagging cliches, repetition, and claims that need citations pic.twitter.com/lvOMTZ4DUB— Maggie Appleton (@Mappletons) September 28, 2026

feat: add llms.txt endpoint for LLM-optimized documentation by quantizor · Pull Request #2388 · tailwindlabs/tailwindcss.com

Add /llms.txt endpoint that serves a concatenated, text-only version of all Tailwind CSS documentation pages optimized for Large Language Model consumption. Extract text from MDX files, removing J...

https://svelte.dev/docs/llms

We support the llms.txt convention for making documentation available to large language models and the applications that make use of them.

Patrick Collison on Twitter / X

I want some kind of LLM workflow tool.• Ability to manage a set of input files (Markdown or similar), plus other general-purpose context.• With real-time collaboration. (And maybe some concept of snapshots or VCS integration.)• And the ability to create/manage a inference…— Patrick Collison (@patrickc) June 6, 2026

Yilio on Twitter / X

🤖 terminal persistence🤖 write-collision safety🤖 canvas ui fixes pic.twitter.com/ckTND0JzoJ— Yilio (@yiliush) March 14, 2026

prime-radiant-inc/engineering-notebook

CLI tool that ingests Claude Code sessions, generates LLM summaries, and serves a browsable engineering journal

Andrej Karpathy on Twitter / X

LLM Knowledge BasesSomething I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating…— Andrej Karpathy (@karpathy) April 2, 2026

outl — local-first markdown outliner & LLM second brain

Open-source bullet-point outliner. Plain markdown on disk (no UUIDs), peer-to-peer tree-CRDT sync that doesn't lose data when devices edit offline — your devices talk straight to each other, end-to-end encrypted, no cloud or third-party server holding your notes — and an MCP server so Claude, Cursor and ChatGPT use your notes as a second brain. A modern Roam, Logseq and Obsidian alternative built in Rust.

Beyond Model Collapse: Scaling Up with Synthesized Data Requires...

Large Language Models (LLM) are increasingly trained on data generated by other LLM, either because generated text and images become part of the pre-training corpus, or because synthetized data is...

Yuchen Jin on Twitter / X

Karpathy’s “LLM Wiki” pattern: stop using LLMs as search engines over your docs. Use them as tireless knowledge engineers who compile, cross-reference, and maintain a living wiki. Humans curate and think.Diagram generated by my Claude agent knowledge worker. https://t.co/5u5i1GeFK8 pic.twitter.com/NIaq3KlAok— Yuchen Jin (@Yuchenj_UW) April 4, 2026

maxleedev on Twitter / X

current chat interfaces suck, so i built a canvas for llms https://t.co/s0vAq0g8aH pic.twitter.com/94RvYgIrGV— maxleedev (@maxleedev) September 2, 2025

Jared Goering on Twitter / X

Saw this and immediately built it. Open-sourced the whole thing:Ingest URLs, PDFs, tweets, images → LLM compiles a linked markdown wiki → Q&A with citations, knowledge graph, contradiction linting, auto-research, export to HTML/PDF/slides.Been using it nonstop as a personal… https://t.co/ypaXlEA7pn pic.twitter.com/8Z2DLAyQjH— Jared Goering (@jaredgoering) April 4, 2026

LLM cliché highlighter

Paste text below — or load it from a URL — and it highlights sentences that match known LLM clichés, including the tells catalogued in Wikipedia’s Signs of AI writing guide. Chain patterns like “no X, no Y” get a badge counting their items; tap or hover a highlight to see which cliché it hit.