AI + SDLC updates in 5 minutes/day.
Practical workflows, testing patterns, and tools worth adopting now.
Synchronizing with global intelligence nodes...
Agent orchestration is leaving the lab: Gas Town hits the cloud, Pulumi bets infra on agents, ops rules change
AI agent orchestration is moving from demos to cloud-grade operations. Steve Yegge’s agent project [Gas Town comes to the cloud](https://thenewstack....
OlmoEarth v1.1 cuts geospatial inference compute by up to 3x without hurting accuracy
Allen Institute for AI’s OlmoEarth v1.1 trims geospatial model compute up to 3x with near-flat accuracy, changing cost math for satellite-scale infere...
Google ships Gemini 3.5 Flash: GA, agent-ready, and fast enough to matter
Google launched Gemini 3.5 Flash, a general-availability model tuned for agentic workflows with big speed gains and lower API pricing than Pro. Googl...
GitHub Copilot app brings Agent Merge to automate CI fixes and PR merges
GitHub launched a desktop Copilot app that runs outside the IDE and now automates CI and merges with Agent Merge. The new [GitHub Copilot app](https:...
New benchmark shows AI coding agents lag on real refactors — orchestration and guardrails are now the work
BlueOptima’s BARE benchmark found top AI coding models succeed under 23% on real refactoring tasks, exposing a gap with headline coding scores. New d...
Cursor turns its IDE agent into headless infra with a public Agents SDK; Composer 2.5 steadies the hands
Cursor turned its IDE agent into headless infrastructure with a public Agents SDK, while Composer 2.5 made the agent steadier on long tasks. Cursor’s...
LoRA/DoRA make NVIDIA’s Cosmos Predict 2.5 practical for domain‑specific robot video on a single GPU
NVIDIA’s Cosmos Predict 2.5 can now be fine-tuned with LoRA/DoRA to make domain-specific robot videos on a single GPU. A new guide shows parameter-ef...
AI slop is breaking bug bounties; add gates and consumer-side audits
AI-generated bug reports are overwhelming security channels, pushing maintainers to add submission gates and move audits to the consumer side. Linus ...
Microsoft ships GA "computer use" agents in Copilot Studio for UI-driven automation
Microsoft Copilot Studio’s computer-use agents are now GA, letting AI operate UIs to automate systems that don’t have APIs. Microsoft’s “computer use...
Codex 0.131: remote-control workflows and diagnostics land, safety and metering quirks surface
OpenAI Codex 0.131 ships deeper remote workflow control, a new diagnostics tool, and a safer Windows sandbox—while users flag data loss and metering b...
Cursor ships Composer 2.5 in-IDE model, nudges teams toward headless agents via its SDK
Cursor released Composer 2.5, a stronger in-IDE coding model that aims to match frontier agents on real repo work. The drop lands only inside the Cur...
CLI coding agents harden: Claude Code stabilizes and resumes long runs; Copilot CLI ships workflow boosts; enterprises eye consolidation
CLI coding agents are maturing fast: Claude Code fixed reliability gaps and added /resume for long runs, while GitHub Copilot CLI shipped notable work...
Kilo Code vs Cursor: BYOK across autocomplete without leaving VS Code
AI coding tools are diverging: Kilo Code runs inside your IDE with full BYOK; it says Cursor’s forked editor keeps BYOK to chat. [Kilo Code’s compari...
Claude Opus 4.7 drops long‑context surcharge — budget rules for 1M‑token prompts just changed
Anthropic’s Claude Opus 4.7 includes a 1M‑token context window at standard per‑token rates with no extra long‑context fee. This isn’t cheaper by defa...
Gemma 4 in the wild: E4B vs 31B shows when to route small vs big
A real-world test shows when to use Gemma 4 E4B versus 31B, with clear tradeoffs across quality, latency, and cost. A developer ran 50 messy, real st...
Bigger context, smarter retrieval: Grok 4.20’s 2M tokens meet Agentic RAG
xAI’s Grok 4.20 brings a 2M-token working set, but real gains come when you pair it with agentic retrieval that can reflect and retry. A deep dive ar...
Pi Agent now has a fast, single-binary Rust CLI you can extend
Pi Agent now has a fast Rust CLI port that starts instantly and keeps streaming stable. The new [pi_agent_rust](https://github.com/Dicklesworthstone/...
OpenAI folds ChatGPT, Codex, and the API into one agentic platform under Brockman
OpenAI is merging ChatGPT, Codex, and its developer API into one product org to build a single agentic platform. Reporting says Greg Brockman now lea...
GitHub rolls out Copilot desktop app preview; CLI adds MCP discovery and reproducible setups
GitHub launched a Copilot desktop app preview with agent-driven workflows and tighter MCP integration, backed by fresh Copilot CLI updates. The new [...
Select Interactive offers a plug-and-play agentic stack with Cursor, Claude Code, and Linear
Select Interactive is packaging a production-style agentic setup that wires Linear tickets to draft PRs using Cursor and Claude Code. Their program p...
Synthetic web poisoning goes mainstream: Halupedia’s AI-only “encyclopedia”
Halupedia is deliberately publishing AI-made encyclopedia pages, raising real risks for data pipelines and model training. [Halupedia](https://www.we...
OpenCode gets local, persistent memory with a MemPalace plugin
OpenCode gets persistent, local memory via a MemPalace plugin that saves chats and a lightweight knowledge graph. This TypeScript plugin auto-saves e...
Spec-first AI coding is here: tools to tame agent output
AI coding is shifting from vibe-driven scripts to spec-first workflows teams can govern. InfoWorld spotlights tools like Kiro, Spec Kit, Tessl, and Z...