Live feed

infoq.com · 2026-10-09 · Ranked: agentic + evaluation match · practitioner analysis · fresh 0.98 · score 2.73

Android Bench 2 Adds Support for Long-Horizon Tasks, Agentic Evaluation, and Continuous Scoring

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 evaluatio... Context & related coverage →

simonwillison.net · 2026-10-09 · Ranked: agent + codex match · practitioner analysis · fresh 0.94 · score 2.46

A new feature for my blog, built using my voice

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 al... Context & related coverage →

langchain.com · 2026-10-09 · Ranked: agent match · practitioner analysis · fresh 0.98 · score 2.13

How to build great out-of-the-box user experiences with Managed Deep Agents

Managed Deep Agents includes a new API for managing reactions for your distributed agents, and a system to dynamically assign emoji responses with your instrument of choice. Learn more. Context & related coverage →

Kingy AI · 2026-10-09 · Ranked: community signal · fresh 0.98 · score 1.98 · Context

Qwen Image 2.1 Turbo Arrives: Eight-Step Generation, With a License Catch.

langchain.com · 2026-10-09 · Ranked: harness match · practitioner analysis · fresh 0.98 · score 1.98

How to Build a Model Router in the Harness

How we built a model router into Open SWE's harness that cut median cost per coding task by 64% with no measurable drop in quality, and how to build your own. Context & related coverage →

simonwillison.net · 2026-10-09 · Ranked: practitioner analysis · fresh 0.96 · score 1.91

Quoting Matthew Green

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 confide... Context & related coverage →

infoq.com · 2026-10-09 · Ranked: practitioner analysis · fresh 0.96 · score 1.90

Github Migrates Copilot Runtime to Rust with AI-Assisted Rewrite

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 t... Context & related coverage →

aws.amazon.com · 2026-10-09 · Ranked: agent + evaluation match · vendor update · fresh 0.95 · score 1.89

ICYMI: What landed for AI builders in September 2026

A monthly recap of the latest Amazon Bedrock, Amazon Bedrock AgentCore, and Strands updates from September 2026: broader model choice, faster serverless agents with built-in evaluation, and automated knowledge base sy... Context & related coverage →

openai.com · 2026-10-09 · Ranked: agent + codex match · frontier lab · fresh 0.84 · score 1.63

Asana cuts model costs 76x in browser tests with GPT-6.1 Sol

Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models. Context & related coverage →

openai.com · 2026-10-09 · Ranked: frontier lab · fresh 0.84 · score 1.46

Sophos cuts threat investigation time by 96% with OpenAI Daybreak

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. Context & related coverage →