AI

llm-openrouter 0.7.1

Release: llm-openrouter 0.7.1 Performance fix for loading OpenRouter models. Thanks, waveplate. #59 Tags: llm, openrouter

llm 0.34

Release: llm 0.34 One new feature: llm logs --usage Markdown output now includes the response duration in milliseconds and as a human-readable duration. llm logs --short includes a new duration_ms field. #1653 Plus…

End-to-end agentic development with Google Gemini, Antigravity, and GitLab

Learn more about GitLab → https://g.dev/ai/gitlab Get started with GitLab on the Google Cloud Marketplace today → https://g.dev/cloud/google-cloud-marketplace Learn more about Google Gemini →…

llm-anthropic 0.28

Release: llm-anthropic 0.28 Claude Fable 5.1, reasoning traces are now displayed by default for models that support them, plus a new llm_anthropic.ClaudeRefusal exception for when Claude throws a refusal. Tags: llm,…

Web Search on Amazon Bedrock is now available in AWS GovCloud (US-West)

The Web Search built-in server-side tool on Amazon Bedrock is now available in AWS GovCloud (US-West), helping bring grounded web results to compliance-sensitive government and public-sector workloads. Web Search helps…

llm-gemini 0.34

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.…

He built a voice controlled drone to avoid using a remote! 🤯✈️

Ditching the remote control to fly a drone with your VOICE? 🛰️🎙️ Meet Bryen Param, the Live Agents category winner of the Gemini Live Agent Challenge! We caught up with him at Google Cloud Next ‘26 to discover how he…

Claude's new system prompt really doesn't want to reproduce song lyrics

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…

Real-Time Intelligence with IBM Time Series Models on Confluent

Don't wait to graduate: A student’s AI ancestry storyteller

Can AI bring ancestry to life? 🧬 College student Jeremiah Somoine won the Creative Storyteller category of the Gemini Live Agent Challenge with his incredible project, Sankofa! Using Gemini models and Google Agent…

ATV Big Air Tour turned 3 days of work into 3 hours with ChatGPT

ATV Big Air Tour uses ChatGPT Work to speed up marketing, merchandising, and more. It even turned merchandise photos into an inventory website in 15 minutes.

Quoting Rick Brewster

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…

New to Rust, converting a project from Python

Hi All, I'm new to Rust, coming from a systems engineering and Python background, with the idea of learning Rust for AI tooling and safe agent runtimes. To help get more fluent, I want to start converting some of my…

Sora API dừng ngày 24/09/2026: checklist cần làm ngay

Originally published on NextFuture Nếu service của bạn còn gọi POST /v1/videos của OpenAI để render video, bạn có một deadline cứng: 24/09/2026. Tài liệu API vẫn còn đầy đủ, nên rất dễ để việc này rơi khỏi sprint. Đây…

Gemini 3.8 Flash giá $0.75/1M: dev có nên đổi model?

Originally published on NextFuture Pipeline coding agent của bạn đang chạy ổn trên Gemini 3.7 Flash, hoá đơn token tháng vừa rồi vẫn nằm trong ngân sách. Google vừa phát hành 3.8 Flash và nói rằng model mới mạnh hơn ở…

How I Built In-Game Hot Reloading with an LLM Chat (Zero Build Steps, Pure ESM)

Imagine playing a 3D WebGL game in your browser, hitting an EDIT button, typing "make the camera lower and double the player's thrust", and watching the running game smoothly update in real time — without a page…

12 Open Source Gems To Become The Ultimate Developer 🔥

TL;DR It's been a while since I've done a collection (maybe month ago), but today let's look at 12 new and not-so-new projects that can really help you in development. They touch on different areas of development, but…

OpenAI’s new reasoning technique alarms AI safety experts

OpenAI’s new Astra model will use “recurrent depth,” a technique that allows the model to operate outside of the sequential thinking that characterizes most reasoning models.

Your next OpenAI API timeout might not be a timeout at all

OpenAI said Tuesday that its upcoming Astra model is the company’s first to reach the Critical cybersecurity threshold in its The post Your next OpenAI API timeout might not be a timeout at all appeared first on The New…

Anthropic’s Claude failures have made agent observability a security priority

Anthropic aimed to steer its ship into safer, more carefully charted waters this week. The company announced it was improving The post Anthropic’s Claude failures have made agent observability a security priority…