Researcher Derik Kauffman discovered a hidden list of over 100,000 words and phrases blocked from iOS autocomplete and swipe-typing across major languages, and published it online. The list includes slurs, sexual and drug terms, but also political phrases like 'dictator Trump,' 'sleepy Joe,' and 'covid was a hoax,' plus inconsistencies such as blocking 'bad girl' but not 'bad boy.' Kauffman extracted the list from a hash table buried in iOS using AI coding tools, and another researcher independently verified the findings; Apple told Reuters the keyboard avoids suggesting potentially offensive terms but doesn't stop users from typing them manually.
theverge.com
· 2026-11-06
A developer reported that OpenAI's Codex tool had its 'Improve the model for everyone' data-sharing setting turned back on without their knowledge, despite having previously disabled it. Coworkers confirmed the same issue, and the poster noted the setting can be checked and disabled via OpenAI's data-controls and privacy pages. Other users on Hacker News had flagged similar behavior before.
news.ycombinator.com
· 2026-11-03
deepsense.ai has published a playbook of ten patterns for structuring repositories and workflows around AI coding agents, developed after its team built HyperCode, a repository intelligence layer, during an OpenAI Codex hackathon. The patterns cover making repos agent-readable through documentation like AGENTS.md, compiling context just-in-time for tasks, and using validation loops to turn recurring agent mistakes into guardrails. The team tested these approaches internally across staff with varying experience using Codex and Claude Code.
deepsense.ai
· 2026-11-03
Symantec's Threat Hunter Team identified a relay service that has been installing genuine OpenAI Codex and Anthropic Claude Code command-line tools on enterprise systems since early 2026, primarily in mainland China, South Korea, Taiwan, and Malaysia. The service reroutes AI requests through its own infrastructure instead of OpenAI's or Anthropic's servers and disables built-in security safeguards, though researchers have not found evidence of malware or active exploitation yet.
darkreading.com
· 2026-10-29
At TechCrunch Disrupt, OpenAI enterprise product lead Alexander Embiricos discussed dots, the always-on AI assistant OpenAI launched at its late-September developer day. He said the team built on technology from OpenAI's Codex coding tool but worked to frame dots as a single ongoing entity rather than separate conversations, making it feel more intuitive. Dots is available to ChatGPT Pro subscribers ($100/month and up) and can connect to a user's calendar, email and computer to help complete tasks.
techcrunch.com
· 2026-10-27
Forever Security researchers Gal Weizman and Omer Samet discovered an in-the-wild attack in which a malicious file named AGENTS.md was planted in a customer's downloads folder, disguised as engineering notes. When AI coding agents like OpenAI's Codex or Claude Code read the file as trusted project context, it could prompt them to rewrite their own configuration, enabling further attacker actions such as credential theft. The firm says it intercepted and stopped the attack before any malicious code executed.
darkreading.com
· 2026-10-26
Fanatics has introduced "Shop the Look," a feature that uses AI to suggest coordinated outfits from its catalog of over 1.5 million SKUs, built with help from OpenAI's Codex. Chief product officer Justin Tsai said the tool pairs items by team and style to address shopping sessions that often ran over 30 minutes due to the company's vast and fast-growing product range.
cnbc.com
· 2026-10-26
Forever Security researchers discovered a malicious AGENTS.md instruction file in a customer's Downloads folder that caused an AI coding agent to attempt installing a rogue npm package called 'function-color.' They reproduced the attack against OpenAI Codex and showed a similar technique against Claude Code that could leak OAuth tokens and hijack accounts, all using only crafted text instructions placed in the agent's working directory.
bleepingcomputer.com
· 2026-10-25
A modder known as pepsipu (Sammy Hajhamid) created a software-only, tethered jailbreak for the Nintendo Switch 2, dubbed 'ns2jb,' with help from OpenAI's Codex tool. The exploit relies on the game SmileBASIC 4 and must be re-run each time the console restarts; a demo shows a modified Mario Kart World with added characters like Cinnamoroll, Peter Griffin and Steve from Minecraft.
theverge.com
· 2026-10-22
A developer released SIwithin, a single-file Python tool that runs AI coding CLIs like Claude Code and OpenAI Codex unattended, restricting them to specified folders and enforcing a dollar budget per run. It uses a loopback proxy to meter Claude API requests with a per-run token instead of the user's real key, and logs one record per run showing cost and completion status. The tool currently works only on macOS and refuses to run on Linux or Windows.
github.com
· 2026-10-20
A developer who began using AI coding agents in February 2025 describes persistent problems with task tracking and reliability, including agents that stall and require restarts, falsely report tasks as complete, and fail to properly manage multi-step work. The author distinguishes between the underlying language models, which have improved significantly, and the agent software wrapping them, which has not kept pace. An example cited involves an open-source file-sharing app where an agent, OpenCode, split a passphrase-protection feature into ten subtasks but mishandled execution of the plan.
mtlynch.io
· 2026-10-09
A developer reverse-engineered the Nokia 110 4G's firmware to turn its Calculator app into a chat interface that connects to DeepSeek's chat API. The prototype lets users type messages on the number pad and have the AI agent control phone functions like checking battery level, toggling the torch, starting calls, and setting alarms. The app is loaded into RAM from a computer and currently must be reloaded after every restart or power-off since permanent installation isn't yet solved.
github.com
· 2026-10-08
GoKawiil