A developer's Claude 3.5 Sonnet MCP setup failed last Thursday due to oversized database schema responses exceeding context limits, causing timeouts and JSON parse errors. The developer fixed it by wr…
ASSET Research Group disclosed GhostSplice on August 10, a proof-of-concept that splits a secret-exfiltration request across multiple MCP tool channels to bypass AI coding agent refusals. In controlle…
A developer reverse-engineered GitHub Copilot by placing it behind a man-in-the-middle proxy, uncovering details about its network traffic, harness, memory, and how context is becoming the product. Th…
Pylon co-founders Marty Kausas and Advith Chelikani told SaaStr AI Day that a 1,000-person support team deflected 50% of its tickets with an automated resolution agent but headcount didn't change, arg…
Datadog CISO Emilio Escobar said the real AI security threat is not models escaping but the coming explosion in discovered vulnerabilities, as the company has over 4,000 engineers using coding agents …
Adam Ward, head of talent at AI coding company Cursor, said on 'Lenny's Podcast' that most companies get work trials wrong by focusing on extracting information from candidates rather than making the …
Ungate, a new Cursor extension by developer orchidfiles, lets users run Claude, ChatGPT, and MiniMax subscriptions in Cursor without paying API token costs. The extension, installable via `cursor --in…
A developer has built SKI, a free desktop app that gives coding agents like Claude Code and Codex a bidirectional voice interface. The app lets developers speak to agents and hear their responses alou…
Cursor's cloud backend routes all LLM API calls through its servers at api2.cursor.sh, making localhost base URLs unreachable and causing chat requests to hang. A developer found that exposing a local…
Legora CEO Max Junestrand said the shift away from per-seat software pricing was 'a matter of time' as AI usage drives up computing costs. In June, Legora released Legora Agent, and later that month i…
A new report from CloudBees finds 81% of enterprise technology leaders reported a rise in production issues tied to AI-generated code, while 92% said they were confident the code was production-ready …
Cursor launched Origin on August 11th, a Git platform designed to host code produced by fleets of AI agents, extending the company's reach from agent assignment to code merging. The product, introduce…
Grok 4.6 appears close to public release after the unreleased xAI model briefly surfaced in Cursor's production model picker on August 10th and an outside developer received preview access hours later…
A software team in early 2026 found that automating implementation with AI agents shifted the bottleneck from writing code to reviewing it, increasing review time and lowering engineer happiness. They…
A developer built Recall, a local CLI that derives structured context from a repository and stores it inside the repository itself, aiming to eliminate the need for coding agents to rediscover the rep…
Developer activeing123 released mcptoon v0.2.0, a token-efficient MCP CLI client that reduces MCP tool discovery token usage from 10,000+ to 350 tokens by outputting TOON (Token-Optimized Object Notat…
An engineer's five-month review of Cline, an open-source VS Code AI coding extension, finds it highly capable but not actually free, with API bills averaging $60-90 per month. The Plan/Act workflow an…
A backend engineer who spent one week using LLM agents for coding and review found that 80 of 730 Claude Code sessions involved direct human input, while 650 were agent-initiated, and Codex ran more s…
Qarinah, a local-first project-memory tool, compiles a compact, cited memory pack instead of replaying full project history to coding agents. In benchmarks across six software-task fixtures, it reduce…
A developer released a guide and starter kit for writing AGENTS.md files that give AI coding agents like Codex, Claude Code, and Cursor the context they need to work safely. The guide emphasizes short…