Submit

RSS Reader

Feed list
Back

All items

Newest item

  1. Gemini Decisions API simonwillison.net · Simon Willison's Weblog ·

    Gemini Decisions API Google join Jev and OpenAI in the decision model category with "Gemini Decision 1". This new model API is almost identical to Jev: it supports the same three types of questions (yes/no, choice, and rubric-scoring) and even reuses Jev's term "Noul" for a yes/no question. It's priced the same as the GPT-6 Luna decision model: 10 cents per million input tokens, and output is free. Jev remains the cheapest of the three, at 4.2 cents per million. Jev is text (and JSON) only....

  2. aws-emulator simonwillison.net · Simon Willison's Weblog ·

    aws-emulator Finally, an official emulator from AWS to run tests against a local clone of their many different services without having to provision a paid API key to do so. It's written in Rust by a huge swarm of agents - 29,684 commits in the first three weeks of the project. Swaminathan (Swami) Sivasubramanian wrote about how it came to be in a guest post on Werner Vogels' blog. It currently requires Docker to run on macOS or Windows. I'm hoping they fix that in the future - it would be...

  3. My Helix fork tutors me natemeyvis.com · Nate Meyvis ·

    The other day I wrote about how I'm now writing in a WebAssembly fork of Helix. This is working great, even though (i) my vim / Helix knowledge is uneven and (ii) the WebAssembly fork is still buggy. Some extra infrastructure is addressing both of these problems: The editor now saves a rolling history of my N most recent keypresses and recent states of the buffer. Every so often, this information gets sent to a decision model, which determines whether it describes some sort of Helix user...

  4. Browse tools.simonwillison.net by tag simonwillison.net · Simon Willison's Weblog ·

    Browse tools.simonwillison.net by tag I've been wanting a better way to browse my collection of vibe-coded tools (244 and counting) for a while. I had a few Fable 5.2 credits left over before my weekly reset so I set it to work using tree-sitter to analyze the code for JavaScript APIs, libraries, and web API hosts used by each tool. The homepage now features tag clouds for browsing by each of those categories of tag: Tags: javascript, tools, ai, generative-ai, llms, claude, vibe-coding

  5. Local Analytics Doesn’t Need a Database Server duckdb.org · DuckDB ·

    From interactive maps to graph exploration, DuckDB makes it possible to analyze data without a database server. Ilya Boyandin shares how this approach led to SQLRooms, a toolkit for building analytics applications that bring data, visualizations, and AI-assisted analysis together on the user’s machine.

  6. llm 0.37.2 simonwillison.net · Simon Willison's Weblog ·

    Release: llm 0.37.2 Fixes a security issue reported by Daniel de Araujo in GHSA-v9h7-jj4g-f862 and GHSA-r639-rr7r-x72w. LLM has a mechanism called extra-openai-models.yaml - now managed by the new-in-0.37 llm openai endpoint add command - for using LLM with OpenAI-compatible API endpoints from other providers. Daniel reported two ways this could accidentally send your configured OpenAI API key to one of those providers: if the key named by api_key_name had never been stored, or if a...

  7. Node.js 26.13.1 (LTS) nodejs.org · Node.js Blog ·
  8. Node.js 24.22.3 (LTS) nodejs.org · Node.js Blog ·
  9. Node.js 22.23.5 (LTS) nodejs.org · Node.js Blog ·
  10. Tests as data: ensuring AI-generated code does what we want martinfowler.com · Martin Fowler ·

    Automated testing in the age of AI coding assistants is problematic: when AI agents write both production and test code, developers risk losing the assurance that automated tests protect against functional errors. Matteo Vaccari makes three claims: (1) when AI writes the code, developers become its customers; (2) therefore customer tests, not developer tests, become the primary contract between humans and AI; (3) moving that contract into test data rather than test code makes it easier to...

  11. Anthropic's IPO roadshow video simonwillison.net · Simon Willison's Weblog ·

    Anthropic's IPO roadshow video Anthropic kicked off their IPO roadshow yesterday, and their roadshow video has some previously unreleased information about how their business works. The section on "Approach to compute" with co-founder Tom Brown is particularly interesting, describing how Anthropic train and serve Claude across AWS Trainium, Google TPUs, NVIDIA GPUs, and AMD GPUs. I'm not sure why there's no official video transcript, but here's one that I extracted using MacWhisper....

  12. Kai extends Autonomous Defense Platform visibility to internet-facing assets helpnetsecurity.com · Help Net Security ·

    Kai has announced External Attack Surface Management (EASM), now available on the Kai Autonomous Defense Platform. The company also launched Kai Labs, an expanded research team focused on the hardest open problems where AI meets security. Most exposure management programs only see inside, so they miss the exposures attackers find first. With EASM, Kai unifies internal and external exposures into a single remediation plan, accelerating the path to zero. The external view sharpens what counts...

  13. Micronaut Framework 5.2.6 Released! micronaut.io · Micronaut Blog ·
  14. Git fixes six vulnerabilities, including code execution during recursive clones helpnetsecurity.com · Help Net Security ·

    The Git project has released security updates addressing six vulnerabilities that could allow attackers to execute code, write to unintended files or cause memory corruption when Git processes malicious repositories or other specially prepared input. Code execution during cloning A vulnerability tracked as CVE-2026-111760 stems from an integer truncation in Git’s handling of its index. An extremely long file path can pass Git’s safety checks under one name and then be written under a shorter...

  15. Embed Security lets analysts teach its AI SOC Platform how to investigate helpnetsecurity.com · Help Net Security ·

    Embed Security announced new capabilities that let security teams teach Embed how they investigate, what matters in their environment, and how to improve their detections. With customer-built iSteps, expanded NoiseIQ Memories, and Detection Engineering, organizations can extend Embed’s built-in security expertise with their own knowledge and operating practices. Rather than programming workflows, analysts can teach Embed what they know, and its decision layer applies that expertise...

  16. A New Browser - Software Freedom and the Three Nordstjernen Browsers bytecode.news · ByteCode.News ·

    External submission: A program is free when its users control it. Today’s browser engines are so large that the freedom to study them exists only on paper. Nordstjernen is a browser engine written from scratch, small enough for one person to read, released under the GNU GPL as three browsers: Sol, Northstar and Southstar. Northstar, licensed under the GPL alone, shows where this should go.

  17. Possible Futures borretti.me · Fernando Borretti ·

    A map of possible futures.

  18. HowTo: Fix Eufy HomeBase 2 Storage Full Issues shkspr.mobi · Terence Eden’s Blog ·

    Quick Fix: Insert a USB memory stick, format it in the app, restart the Eufy HomeBase 2, format the internal memory, restart the hub. Background I've had the eufyCam system for over 6 years - which is pretty long-life for IoT devices. The cameras have worked pretty much flawlessly. Four years ago I added their Video Doorbell which has been similarly well behaved. But last night I went to…

  19. Rubrik enhances DevOps Protection to preserve legitimate work during recovery helpnetsecurity.com · Help Net Security ·

    Rubrik has announced cyber recovery capabilities for DevOps platforms Microsoft Azure DevOps and GitHub. With built-in anomaly detection, blast radius investigation, and surgical recovery, organizations will be able to detect suspicious activity on their code, instantly scope the impact of an attack, and undo the attackers’ changes from air-gapped, immutable backups, without disrupting legitimate developer work. “An organization’s source code is where innovation lives, and attackers know...

  20. Microsoft researchers demonstrate hidden backdoor technique for AI agents helpnetsecurity.com · Help Net Security ·

    Microsoft researchers have demonstrated how small changes to an AI model can implant a hidden backdoor, causing an agent to execute an attacker’s command when a specific trigger appears. The technique, called Lazarus, requires no model retraining and allows the agent to behave normally during standard safety evaluations. The company has not observed threat actors weaponizing the technique, but says the research highlights a security concern for organizations that give AI agents access to...

Search posts