Stop Guessing Which Local Model To Run
A practitioner's guide to local AI.
A practitioner's guide to local AI.
Release: llm-gemini 0.34 New model gemini-3.8-flash for Gemini 3.8 Flash, with low, medium and high thinking levels. #146 Fixed async responses failing to record the resolved model version. Thanks, Charlie Tonneslan. #137 Google released Gemini 3.8 Flash (and 3.8 Flash Cyber, but that's available to "trusted defenders" only) today. Here are the pelicans for high, medium, and low. This is high: For comparison, here are the same pelicans generated using Gemini 3.7 Flash. Something I appreciate…
The API Platform Conference, the international event dedicated to the API Platform framework and its ecosystem, will take place in two weeks in Lille, France, on September 17–18, 2026. Nearly 30 talks are scheduled, in both French and English, covering…
Anthropic publish the system prompts for their Claude consumer applications (Claude.ai and the Claude mobile apps - sadly not for Claude Cowork or Claude Code). I love that they do this, and that they share not just the current prompts but historic changes to their prompts as well. They used to keep all of the prompts on a single page, but when I checked today I noticed they had re-arranged those prompts into an index page and then a page per model - here's the page for Haiku 4.5 for example,…
In this episode, Scott talks to Ian Littman about Longhorn PHP 2026, a 2-day conference in Austin, TX, on October 15–16, 2026, at the Holiday Inn Austin Midtown. Links: Our Discord – https://discord.gg/aMTxunVx Buy our shirts – https://store.phparch.com/products/community-corner-podcast-t-shirt Ian’s Links: Longhorn – https://longhornphp.com/ $25 off – https://ti.to/longhorn-php/longhorn-php-2026/discount/communitycorner Scott’s Links: Website – https://scott.keck-warren.com/ Bluesky – […] The…
Between March and July 2026, I built a production application of 861,601 lines of code. This included 696 user stories and 779 merged pull requests over 105 days, but I can’t tell you what it cost. The first version of an autonomous SDLC framework driving Claude Code did the work. That generation didn’t record usage, […]
Direct2D has always been the biggest hurdle for Paint.NET on WINE, and it's clear that it will never be completed enough for Paint.NET's use. And I can't just "disable" the use of Direct2D. So, instead, Paint.NET now has an internal, from-scratch, clean-room reverse-engineered rewrite of Direct2D that it uses on WINE (triggered by using /wine). It lives in PaintDotNet.Windows.Direct2D1.Managed.dll. This was written by our good friend Claude, without whom this would NOT have been possible and…
Germany is spending €108 million to move its federal websites onto a PHP application. The money is the budget for the eleventh version of the Government Site Builder, the German federal administration's standard content management solution: €26.88 million for product development and support, €73.2 million for migration and relaunch, €8 million for operations, phased over four years. More than 80 federal agencies and institutions already use it, and they have built well over 250 websites with…
Today is Claude Fable (and Mythos) 5.1 day. Anthropic say that Fable 5.1 "sets a new standard for coding, knowledge work, and long-running problem-solving tasks". Their announcement spends a notable amount of time on scientific research, boasting of a 52.6% score on the brand new Terminal-Bench-Science 0.1 benchmark (first announced on August 27th), up from 24.7% for Fable 5, 29.0% for Opus 5 and 22.4% for GPT-5.6 Sol. Other benchmarks show slightly improved scores, but none as impressive as…
+ a popular LLM interview question.
I was poking around in my ~/.cache/ folder using OmniDiskSweeper when I spotted something interesting. The OpenAI Codex desktop app (since rebranded to just ChatGPT) has 1.7GB of stuff in there in a folder called codex-primary-runtime, including a full Python installation, a full Node.js installation, and native binaries for Poppler, git, and the LibreOffice open source office suite (which forked from OpenOffice.org in 2010): The…
Today, we’re excited to add Microsoft Teams as a notification channel in Socket. Security and engineering teams can now send organization alerts and supply chain attack campaign notifications directly to the Teams channels they already monitor, with filters that control exactly which events reach each destination. When Socket finds something that needs attention, teams shouldn’t have to keep another dashboard open to find out. Microsoft Teams notifications bring relevant security activity into…
Tool: GeoJSON Map Viewer I was helping Natalie gather some maps of local political boundaries (for the Granada Community Services District and the Midcoast Community Council) and found a need to display some GeoJSON files on a map and export that as a PNG. I asked GPT-5.6-Sol for suggestions of tools and it proactively built one. After some iterations using Claude Code for web and Fable 5.1 we got to this finished tool. As for the GeoJSON.. it turns out if you ask ChatGPT Work to provide…
They took the letters from me! I have to talk about dwarf behavior now. I can't even talk about dwarf AI. It doesn't exist. It's dwarf behavior, and they misbehave sometimes — Tarn Adams, co-creator of Dwarf Fortress Tags: ai, game-design
Release: datasette-mcp 0.2 "rows" from execute_sql is now an array of objects. Previously it was an array of arrays. This should help weaker models avoid losing track of which positional array element maps to which column. #1 Now depends on mcp>=2.1.1. This is the first non-alpha release of the plugin. I'm confident it's ready as I've been using it quite a bit myself. Tags: datasette, model-context-protocol
Aucun résultat
Essayez avec d'autres termes de recherche.