Software engineer specializing in high-scale distributed systems, event-driven architecture, and vector search. Writing Go, designing for simplicity.
Researchers from Meta, MIT, and the University of Washington introduce Context Language Models (CLMs), a new approach that enables language models to manage and edit their own context rather than relying on predefined mechanisms for summarization, compression, and information retrieval,…
Continue reading on infoq.com →Reliability management company Gremlin has announced the general availability of Foresight AI, an agentic product that analyses services for potential failures, recommends changes and reruns tests to check that a fix works. By Matt Saunders
Continue reading on infoq.com →AWS recently announced enhanced custom event buses for Amazon EventBridge, allowing organizations to share a centralized bus across accounts with ordered delivery, simplified subscriber management, event replay, content-based deduplication, and a new publisher/subscriber-based pricing model. By Renato Losio
Continue reading on infoq.com →I remember hearing a while ago that Dwarf Fortress didn't use version control. That fact has been lodged in my head, because given its inherent complexity I have trouble imagining a codebase that would benefit from version control more. That's…
Continue reading on simonwillison.net →Python 3.15.0 added to actions/python-versions Bit of a niche link, but I've been waiting for this for a couple of days - I even told ChatGPT to check for it: Clone https://github.com/actions/python-versions and git pull once an hour until they…
Continue reading on simonwillison.net →The paper challenges the assumption that language models need explicit tokenizers to be efficient demonstrating that standard flat Transformers can process raw byte sequences and actually outperform traditional subword models as parameter sizes scale. The prevailing thought in the field…
Continue reading on arxiv.org →Tomorrow and Tuesday. If you see this you’re in!
Continue reading on latent.space →Inside Standard Bots’ AI stack, pretrained models learn factory tasks from demonstrations and improve through corrections from real deployments.
Continue reading on latent.space →Cloudflare has put Traces into open beta, extending automatic tracing from Workers to security rules, transformations, cache, routing and origin handling as OpenTelemetry spans. Traces accept and forward W3C traceparent headers, and Trace Rules allow targeted sampling. Pricing moves to…
Continue reading on infoq.com →Anthropic detailed the activity of its A.I. agents in a blog post on Friday, without naming the targeted websites. But two sources with knowledge of the incidents said Anthropic’s A.I. agents had submitted 20 visa applications through a form available…
Continue reading on simonwillison.net →From the Bitter Lesson of AI scaling to the unsolved mysteries of protein folding, Google DeepMind’s Pushmeet Kohli and Biohub’s Sal Candido are rethinking what it takes to build AI that truly understands biology.
Continue reading on latent.space →Deno is joining Cloudflare The Deno team released the first version of celld back in August - their open source implementation of the Durable Objects pattern from Cloudflare Workers. Today, Cloudflare are acquiring Deno outright, with the goal of building…
Continue reading on simonwillison.net →Google has released Android Bench 2.0, a major update to its benchmark framework for evaluating AI models and agents on Android development tasks. The update introduces long-horizon tasks (LHTs), agent-based evaluation, and continuous scoring to better assess performance on complex,…
Continue reading on infoq.com →The barriers to building software have collapsed. Today, anyone can build. Hackathons are a great place to start learning. The post Hack the World: Why hackathons are still the best place to learn to build appeared first on The GitHub…
Continue reading on github.blog →Everyone is very concerned about being respectable, so I’m going to be the goofball who raises worst-case possibilities. I think there is a 1% chance we live in Minicrypt, and a 15% chance we functionally lose confidence in our existing…
Continue reading on simonwillison.net →Shopify has updated its Checkout Blocks app, transitioning five high-traffic checkout UI extensions to remote-dom using Preact and Polaris web components. The rewrite, which involved moving to TypeScript and a new API version, led to significant reductions in bundle sizes…
Continue reading on infoq.com →GitHub migrated more than 800,000 lines of Copilot runtime code from TypeScript and Node.js to Rust in about 14.5 weeks using AI-assisted development. The incremental migration used N-API interoperability, automated testing, human review, and 128 pull requests while continuing to…
Continue reading on infoq.com →I shipped a new feature for my blog today: the Newsletters page, which offers an index of all of the newsletters I've sent out, both my free weekly Substack and my monthly sponsors-only updates. I built the feature almost entirely…
Continue reading on simonwillison.net →Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.
Continue reading on openai.com →Discover how Sophos uses OpenAI’s Daybreak to cut cyber-threat investigation time by 96% and automate 52% of MDR cases while preserving human oversight.
Continue reading on openai.com →Release: ttok 1.0 I released ttok 0.4, ran uv tool upgrade ttok, piped a file into the new version... and realized that it was defaulting to the GPT-4 tokenizer when it should very clearly default to GPT-5/GPT-6 instead! I figured…
Continue reading on simonwillison.net →Release: ttok 0.4 ttok is my CLI tool for counting tokens, using OpenAI's open source tiktoken library. It hasn't been in updated in a couple of years, but I finally fixed a Click warning, updated CI, and added a --list-models…
Continue reading on simonwillison.net →Computer programming is, fundamentally, about two things: Problem-solving using computers Learning to control complexity while solving these problems I have a hard time imagining a future where knowing how to solve problems with computers and how to control the complexity…
Continue reading on simonwillison.net →As we kick off Cybersecurity Awareness Month, the GitHub Bug Bounty team spotlights @vaib25vicky, exploring their methodology, techniques, and experiences hacking on GitHub. The post How one bug bounty researcher chooses the features they investigate appeared first on The GitHub…
Continue reading on github.blog →Also: do us engineers truly enjoy ‘hard problems’, or do we really just want to solve those which attract promotions, new open models launch in the EU and US, and more
Continue reading on newsletter.pragmaticengineer.com →