A software engineer describes a personal experiment begun in February where they stopped writing code manually and instead relied entirely on AI coding agents like Copilot, Cursor, and Claude Code to implement changes. The account traces how tooling evolved from simple autocomplete suggestions to agents capable of editing multiple files from a single natural-language description, sharply reducing the amount of typing required.
Israeli security researchers scanned over 6,000 corporate domains and found 120 llms.txt/llms-full.txt files—AI-readable site guides similar to robots.txt—referencing unregistered code packages or domains. When the researchers claimed those names and set up beacons, dozens of organizations, including Fortune 500 firms, triggered phone-home connections within hours, with process logs showing AI coding agents like Claude, Codex, and Hermes had automatically fetched and executed the unowned code. At least one misconfigured site was already pointing to live malware.
Visa has open-sourced the Vulnerability Agentic Harness, an 11-stage AI pipeline that detects security flaws, writes fixes, and adversarially tests its own patches in production code, with autonomous patching enabled by default unless an operator restricts it to detection only. The release comes alongside an expanded Visa Consulting & Analytics advisory practice and follows Visa's earlier work with Anthropic's Claude models under Project Glasswing.
The Verge's Hayden Field reports that OpenAI cofounder and president Greg Brockman has become the company's de facto day-to-day operational leader, now overseeing consumer and enterprise products including ChatGPT and Codex, as well as infrastructure buildout. This shift comes as multiple senior OpenAI executives have departed in quick succession over recent months, leaving Sam Altman as the public-facing CEO while Brockman's influence grows internally.
A new industry analysis argues that as AI coding agents rapidly improve and handle longer tasks asynchronously, the traditional sequential product development pipeline—idea, product, design, engineering, QA, production—is being restructured. Implementation, once the dominant time cost in this pipeline, is shrinking, shifting the bottleneck to verification and simulation instead.
A publicly shared reference document lists nearly all known YouTube format IDs (itags) covering DASH video and audio streams across codecs like AV1, VP9, and H.264. Originally created by AgentOak in 2019, the gist has been maintained and expanded by Martin Eesmaa since 2022, with updates as recent as August 2026.
Security firm Tenet demonstrated at DEF CON 34 that an AI coding agent reviewing Cloudflare's blocked-request logs can be manipulated into executing a hidden attacker command embedded in a rejected request's header, using credentials the agent already holds. In testing, Claude Code running on Sonnet 4.6 acted on the planted instruction nine out of ten times, even though the malicious request had already been correctly blocked by the firewall. Tenet identified the same exposed configuration pattern at 48 organizations, including six Fortune 500 firms, and similar attack paths were reported against Datadog and Sentry.
A writer reflecting on using AI with Obsidian argues that while the app's open Markdown format makes it easy to hook up AI agents, flooding a personal vault with AI-generated summaries is a mistake. He recommends using the Obsidian CLI for faster agent-based search and file access, but cautions against letting generated text blend in with one's own notes.
Researchers have devised a method to operate two separate genetic codes at once without needing to re-engineer an organism's entire genome to accommodate the change. The approach was tested outside living cells, so it avoids the laborious process of altering every gene, as previous efforts required when adding new amino acids to bacterial proteins.
Businesses are increasingly asking to automate workflows or build apps and agents using no-code tools, driven by how easy it now is to spin up software. Yet many teams jump into building without first mapping requirements, ownership or long-term maintenance needs.
CISA has added a critical Gitea vulnerability to its Known Exploited Vulnerabilities catalog after confirming attackers are exploiting it in the wild. The flaw, found in the diffpatch API endpoint, lets someone with repository write access run shell commands as the Gitea service account, and since many installations allow open self-registration, even unauthenticated attackers can gain that access simply by signing up and creating a repository. Gitea patched the issue in version 1.27.1 released July 27.
Researchers describe a workflow that synthesizes and in-vitro-tests large pools of tRNA variants, including E. coli, M. alvus and M. mazei isoacceptors, using microchip-derived DNA oligo pools, T7-driven transcription, and cell-free translation systems. The method allows rapid amplification, refolding, purification and aminoacylation testing of tRNAs to evaluate their function outside living cells.