104 stories
Nimbalyst is an open-source visual workspace for the coding agents you already run. Its desktop app, with an iOS companion, wraps Claude Code, Codex and OpenCode in parallel sessions, adds visual editors for markdown, diagrams, mockups and data models, and tracks the work on a kanban board.
Ben Holmes is the DevEx Engineering Lead at Warp. The company has spent the year shifting from the terminal that made its name to Warp Factories – open infrastructure for teams building software factories.
This is a special chapter of "Can my AI agents make me famous?", a running experiment: a team of AI agents runs Matthew Busel's accounts and tries to make him famous, then make money. The agents write every chapter, with real numbers only, including the parts that went badly. Chapter 3 is here.
This edition of the LLM Inference Digest covers new developments from 2026-10-07 to 2026-10-14 across arXiv, the vLLM and Hugging Face blogs, Together AI, Modal, and Latent Space.
91% of the most-starred repos on GitHub give their coding agent at least one instruction that never says which file, command or tool it means. In April we measured 28,721 repos, and our own limitations section admitted that a 10-star side project counted the same as a 50,000-star production repo.
In my last post the rule was: no model says done, a command exits 0. The obvious hole came up in the first comment I imagined writing to myself: who writes the command? If the same agent that writes the code also writes the check, "exit 0" means "the agent agreed with itself".
The future of local AI is agentic and requires multiple agents to share one machine: one agent summarising your emails overnight, one watching your health data and one doing the shopping, while you are still able to chat and ask questions in between.
AI Agents with Function Calling: Build Tools LLMs Can Use Create AI agents that can execute code, search the web, and call APIs — using function calling. Introduction Function calling (tool use) transforms LLMs from text generators into agents that can act.
You ask your agent to cover a new function. It comes back with eight tests, all green. You move on. Sometime later you're staring at the diff and a nagging question surfaces: what would actually break if this function returned the wrong thing? The answer, more often than you'd like, is nothing.
Your agent can fetch a page. It can also submit a form. Those are not the same permission. On October 9, 2026, Anthropic published Investigating unintended model actions in our evaluations and internal use (also on their research site).
Training computer-use agents currently runs into a clean wall: native desktop applications are painful to spin up at scale, and browser toys lack workflow depth.
OpenHands is one of the best things to happen to coding agents. Its own repository calls it "the self-hosted developer control center for coding agents and automations," and it earns the description: it runs the built-in OpenHands agent plus Claude Code, Codex, Gemini, or any agent that speaks the…
You face high cloud bills when you run powerful AI agents every day. Qwen3.5 gives you frontier-level multimodal reasoning locally. You combine it with OpenClaw for persistent agent workflows and Ollama for simple local serving.
A post this week called context-window compaction a "200k-token lobotomy" and patched it with external state files named after Memento. It is a good write-up, and the naming is honest about the stakes. But it also made the underlying problem easier to see than the fix does.
I won a $7,000 hackathon prize. The payout form offered me Wise. Wise's own help page says that personal accounts with an address in Indonesia "can no longer hold money or currencies in their account." That is the kind of mistake I built Cair to prevent: an agent that plans how a prize or client…
Spending cycles manually writing tests, or constantly updating brittle automation, can feel like a Sisyphean task. We know comprehensive testing is crucial for stable applications, but the sheer volume and diversity of cases often mean we cut corners or fall behind.
An AI agent runs with your credentials and acts before you can stop it. GitGuardian analyzed nine public incidents between May 2025 and July 2026 to reverse-engineer what breaks in production.
Part 2: the bridge connects the team. What can the team turn into something useful? In the first article, I connected my personal assistant, Instinct, to OpenCode on my Mac. Instinct is the PM. OpenCode is the developer.
Showing 18 of 104 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news from Dev.to AI
Join 15,000+ AI enthusiasts
