Developer tools news — AI coding assistants, IDEs, CLI tools, APIs, and productivity tools for software engineers. GitHub Copilot, Cursor, and more.
AMD published a step-by-step FlyDSL workflow for implementing a custom diffusion attention kernel, targeting vLLM's TiDAR (Think in Diffusion, Talk in Autoregression) mode with paged KV caches and scratch storage for spe…
Medusa has built agentic automations, using Claude Code, to handle its release workflow, including drafting release notes, updating documentation, and generating changelog entries, according to a September 17, 2026 compa…
Researchers at UC Berkeley and Arena published HarnessTax on September 16, 2026, finding that swapping the harness around the same coding model changed task success by only about ±2 points on SWE-bench Lite and ±5 on Ter…
GitHub made workflow execution protections generally available on September 17, 2026 and announced that public repositories on the default policy will no longer run workflows started by the pull_request_target event, wit…
Mutagent Helix published a meta-evaluation comparing its agent-building tool against hand-driving Claude Code across twenty agent benchmarks, measuring each calibration pass by dollar cost and number of human interaction…
Meta Developer Advocate Dilmer Valecillos recommends skipping the Unity MCP server in favor of Unity's new CLI and pipeline package, which he says offers dramatically faster iteration times by using the Roslyn compiler f…
Datasette 0.65.5 was released on 16th September 2026 with a security fix for a flaw where a trailing newline in a requested table name could bypass table permissions and expose private rows. The issue was reported by dpf…
A developer built Mycelium, an open-source persistent associative memory system for AI agents that preserves project decisions, dead ends, and context across sessions and model changes. The developer reports that the too…
A developer has published a Python walkthrough for building a runnable MCP client-host loop, covering stdio transport, streamable HTTP, and letting an LLM choose which tool to invoke. The tutorial, adapted from a Chinese…
VLLM contributor mmastrac opened a pull request adding a "Jev-like" structured generation mode for the DiffusionGemma model, retitling it from a work-in-progress draft to "[Core] structured generation mode for DiffusionG…
Developer ivanfioravanti merged a pull request adding Qwen3.8 Flash Next support to the antirez/ds4 repository, including qwen4exp loading, tokenizer and chat formatting, PLE sidecars, Metal text and vision graphs, built…
TypeSafe AI has published a comprehensive project reference for Jev, its first public System One Model, which takes unstructured or structured state as input and returns typed probabilistic decisions rather than generate…
OpenSpec launched as a lightweight, configurable framework for creating and managing software specifications, aiming to keep teams and coding agents aligned as work evolves. The framework supports more than 40 coding too…
A developer at lkforge built browser-based game AI opponents using classical game-tree search — minimax with alpha-beta pruning for tic-tac-toe, expectimax for 2048, and breadth-first search for Color Lines — deliberatel…
IaFlux Studio ran a 69-agent content system for 35 minutes in which 16 texts reached its review gates and 15 were rejected at the first language check — a 94 percent rejection rate — with no human approving any text. The…
A developer's unattended YouTube Shorts upload pipeline failed after exactly seven days because the Google Cloud OAuth consent screen was left in Testing mode, which expires refresh tokens after seven days. The fix requi…
A developer published "Learn Claude Code," an interactive mindmap generated from the Claude Code documentation at code.claude.com/docs, organizing the tool's concepts into stages numbered 1 through 6. The map tracks lear…
Traces analyzed its own stored coding-agent sessions and found that roughly 30% of questions were answered from the `traces_search` result list alone, without opening a single session, while about one in ten questions pr…
AI coding agents such as Claude Code and Codex still require developers to act as the feedback loop, correcting generated code one iteration at a time because of missing project context, ambiguous specifications, and hal…
RTK, a Rust proxy that claims to cut LLM token consumption by 60-90% and has crossed 80,000 GitHub stars, produced zero reduction in actual API billing in a Quesma benchmark that spent over $1,500 across 1,740 test attem…