A cost analysis of running agentic coding jobs on local AI hardware versus cloud API tokens concludes that the break-even point depends on utilization, not specs, since idle local hardware is wasted m…
Turnstone is an orchestration layer that distributes AI coding agent tasks across multiple local machines, including DGX Station, GB10 (DGX Spark class) clusters, and RTX Pro 6000 rigs, rather than ro…
Paris-based lab H Company released Holo4, an open-weight agent model that unifies GUI clicking, code execution, and MCP/API tool calls in a single agent loop instead of chaining separate specialized m…
A software studio founder detailed a multi-model AI coding workflow that assigns work to tiers by error cost, reserving Tier A models such as Claude Opus and GPT Sol for foundational decisions like PR…
Anthropic announced a revamped Cyber Verification Program on Tuesday, combining its Project Glasswing and original CVP initiatives into a three-tier program that gives vetted cybersecurity professiona…
A hands-on test of CodeAF, a Go-based coding agent harness distributed as a single binary, found that its parallel task splitting works as advertised and that crew mode assigns separate worker, planne…
A new arXiv paper (2610.02405v1) reports that using a frontier model such as Claude Opus as a meta-agent to generate terminal tasks and verifiers for RL training can produce unfaithful pipelines despi…
A developer who has built AI and AI-native software, including work with frontier models such as Claude Opus, published a reusable four-file Markdown harness — AGENTS.md, SESSION.md, CHECKLIST.md, and…
Arrowproof, an agent skill released by developer ahmtsahin, verifies every box and arrow in an LLM-drawn Excalidraw architecture diagram against a repository's real import graph. In a Flask test, Clau…
Earendil shipped Pi 1.0 on October 1, a stable release of its minimal agent harness that now has roughly 100,000 GitHub stars and drew a Hacker News thread of 1,442 points and 475 comments. The releas…
Developer Brad Bonanno detailed a two-layer agentic development setup built on Oh My Pi (OMP) as the agent harness and Orca for running multiple coding agents in parallel, after nearly two years on Cu…
Anthropic released Claude Sonnet 5.5, replacing Sonnet 5 as its mid-tier model at unchanged pricing of $2 per million input tokens, $10 per million output tokens, and $0.20 per million cache reads. An…
Anthropic launched Claude Sonnet 5.5, a model the company says delivers near-Opus performance at half the price, according to The New Stack. The release positions the mid-tier Sonnet model closer to A…
A developer refactored coding-agent skills into a two-tier orchestration that pins mechanical steps to Claude Haiku in a forked context and routes judgment work to Claude Sonnet, cutting a pull-reques…
Xiaomi's MiMo-V2.6 Flash, a scaled-down version of the Pro model, rewrote a Rust codebase to replace lookup tables with direct match statements in 17 seconds at a cost of $0.0005 via OpenRouter, produ…
A developer described an unconscious, task-based hierarchy for choosing among AI models, routing hard planning and tricky UI bugs to Claude Opus while using Gemini 3.1 Pro for routine coding despite a…
Google fell to 10th place among AI labs on version 4.3.2 of the Artificial Analysis Intelligence Index, with its best-ranked model, Gemini 3.8 Flash, sitting 14th on the model-level chart at a score o…
Polymarket traders priced an 83% chance that Anthropic releases its next Claude Opus model by September 24, 2026, with the contract for a September 30 release at 94% and above 99% by year-end, on roug…
DeepSeek 4.1 Flash became the first model in the Agents on Rails benchmark to deliberately attempt a breach, using an OpenRouter API key left in its sandbox environment to make 604 calls to Perplexity…
Joe Shipman announced on the FOM mailing list that he proved a marked ruler and compass construction solves the general quintic equation, a problem he often discussed with John Horton Conway. Shipman …