Devin Plumb

3 followers · 684 views

on the atlas · 110

Ari Autoresearch: Autonomous Post-Training in AC2 | Applied Compute1 savers
The Sane Asylum - Colossus21 savers
[2409.14252] Collaborative Text Editing with Eg-walker: Better, Faster, Smaller1 savers
Building fine-grained version control for agents with Rust and Durable Objects — Delta Blog2 savers
Basis | Ship Your Interpreter1 savers
Introducing our Training API1 savers
LLMs are making formal software verification feasible at a much larger scale \ Anthropic7 savers
Introducing Flint - Recursive1 savers
Code Review Sucks Now, but It Doesn't Have To - Just Be2 savers
Dev Patel on X: "Nobody Prompt Caches Their Voice Agent" / X1 savers
Handwired: turn your regular JavaScript code into a neural net1 savers
What is Codemode | Armin Ronacher's Thoughts and Writings1 savers
Josh Rosen on X: "Agent Traces: Patterns for Capturing Agent Execution " / X1 savers
How to be more ambitious: A tutorial for humans with models37 savers
Redesigning source control at Anthropic \ Anthropic10 savers
How to Unclench | Jonny Miller23 savers
Rayan Krishnan on X: "Human Intelligence is Surprising" / X1 savers
[2609.30063] Self-Play Pretraining with Zero Data2 savers
What if you don't need MCP at all?2 savers
A Startup With 10,000 Engineers1 savers
Introducing System One Models and Jev - TypeSafe AI Blog21 savers
Harsh Gupta on X: "LeanDB: A strongly typed SQL Frontend " / X1 savers
A.I. Could Possibly End Humanity. How Are Humans Supposed to Process That? - The New York Times1 savers
If coding is solved, what now?: Measuring the sloppiness of code | EARENDIL1 savers
Astra for Coding: Why Are We Doing This Again? | Armin Ronacher's Thoughts and Writings4 savers
Reading List3 savers
How Universities Should Prepare Founders4 savers
Does AI stop children from learning?1 savers
A “diff” tool for AI: Finding behavioral differences in new models \ Anthropic2 savers
There Are No New Ideas in AI… Only New Datasets12 savers
India’s Cockroaches Were Never Radical Enough | The Nation1 savers
How to keep thinking5 savers
crawshaw - 2026-05-071 savers
Understand - a novelette by Ted Chiang6 savers
Black Hat USA 2026: The 'Breaking' News: The OpenAI–Hugging Face Incident - YouTube6 savers
In Memory of My Wife, Elise Cawley (1961–2026), with Thanks for 36 Wonderful Years—Stephen Wolfram Writings26 savers
Mixture-of-Kittens: our open-source MoE megakernel for NVL72s · Cursor3 savers
Pangram 4 Technical Overview | Pangram Labs1 savers
wsj.com2 savers
Kimi K3 Tech Blog: Open Frontier Intelligence3 savers
ali on X: "22580: From GPT2 to Kimi3, Explained" / X4 savers
Just get to the point: teaching Thinking Machines' 1T Inkling model dad jokes with GRPO on Tinker1 savers
How coding agents read your code (and how to write for them) | Modem Blog1 savers
British Grammar Invades the American World Cup | The New Yorker1 savers
NY to SF, Transit Times over History - Slater1 savers
The Last Question24 savers
On Making1 savers
Welcome Inkling by Thinking Machines1 savers
Inkling: Our Open-Weights Model - Thinking Machines Lab14 savers
Security incident disclosure — July 20265 savers
A digestion of the Jacobian conjecture counterexample | What's new1 savers
AI is approving our pull requests: Here's how we made it safe - The Intercom Blog1 savers
Jane Street Blog - Formal methods and the future of programming1 savers
Rewriting Bun in Rust | Bun Blog12 savers
Benchmarking Coding Agents on Databricks’ Multi-Million Line Codebase | Databricks Blog2 savers
250 Years, 25 Reasons: Why America Gets to Be America | LinkedIn1 savers
Zen and the Art of Machine Learning Research2 savers
[2309.10668] Language Modeling Is Compression4 savers
Language Modeling Without Neural Networks1 savers
Can gzip be a language model?5 savers
Rhythm Garg on X: "Should you post-train your own model? " / X1 savers
Software Is Made Between Commits — Zed's Blog1 savers
Dario Amodei — Policy on the AI Exponential18 savers
On measuring AI - Nikil Ravi1 savers
Noam Brown on X: "Implications of Large-Scale Test-Time Compute" / X7 savers
Automatic Formal Verification for Code Generation1 savers
Reinforcement learning is an infrastructure problem1 savers
The Web Animation Performance Tier List - Motion Magazine3 savers
Build Your Own Database6 savers
A Call for New Aesthetics5 savers
How's Linear so fast? A technical breakdown8 savers
unit-distance-cot.pdf3 savers
unit-distance-remarks.pdf3 savers
unit-distance-proof.pdf2 savers
An OpenAI model has disproved a central conjecture in discrete geometry | OpenAI10 savers
Mixture of Experts1 savers
Optimizing a Layer Normalization Kernel with CUDA: a Worklog1 savers
The Irish Drug Kingpin Daniel Kinahan Is Arrested in Dubai | The New Yorker1 savers
Using a 1978 terminal in 2026 (DEC VT-100) · Nikhil Jha1 savers
GitHub RCE Vulnerability: CVE-2026-3854 Breakdown | Wiz Blog4 savers
Ghostty Is Leaving GitHub – Mitchell Hashimoto6 savers
[2604.18002] Neural Garbage Collection: Learning to Forget while Learning to Reason1 savers
One Developer, Two Dozen Agents, Zero Alignment2 savers
Riffle: Reactive Relational State for Local-First Applications1 savers
Building data-centric apps with a reactive relational database8 savers
Sam Altman May Control Our Future—Can He Be Trusted? | The New Yorker10 savers
The United States needs fewer bus stops - Works in Progress Magazine3 savers
Scaling long-running autonomous coding · Cursor7 savers
Dynamic context discovery · Cursor3 savers
MAKING SOFTWARE62 savers
2025 letter | Dan Wang62 savers
Dario Amodei — The Adolescence of Technology44 savers
Defeating Nondeterminism in LLM Inference - Thinking Machines Lab40 savers
How To Scale Your Model35 savers
The Intelligence Curse30 savers
How Complex Systems Fail22 savers
Aman's AI Journal • Primers • Ilya Sutskever's Top 3021 savers
2025 LLM Year in Review | karpathy16 savers
What are Diffusion Models? | Lil'Log16 savers
Reward Hacking in Reinforcement Learning | Lil'Log12 savers