GoKawiil
Tech News
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.
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.
A bug report filed as issue #25921 states that OpenAI's Codex Desktop application continuously generates Crashpad pending dump files with no cleanup mechanism. The reporter estimates the dumps grow by at least 5GB per day, consuming disk space indefinitely if left unaddressed.
A Show HN project called PDF TO MP3 lets users convert PDF documents into audiobooks by connecting their Codex or Claude account via an MCP server. Document processing is covered by the user's existing AI subscription, while the actual text-to-speech generation is billed separately through an OpenAI or Google Gemini API key. Users authenticate the MCP server, add their speech API key, then attach a PDF in their chat client and request an audiobook conversion.
A developer documented a project called KindleCTL, in which an AI coding agent was used to jailbreak a 10th-generation Kindle Basic and install a custom photo slideshow app. Earlier attempts with other AI models, including GPT-5.6 Sol and Anthropic's Fable 5.1 and Opus 5.5, failed due to technical errors or built-in cybersecurity restrictions, but GPT-6 Astra succeeded in building the jailbreak and the app. The resulting app cycles through ten photos for four minutes each, accessible from the Kindle's library screen alongside books.
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.
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.
A new desktop application called Pinrail lets coding agents such as Claude Code, Codex, Cursor or OpenCode pause at designated steps and request human approval before proceeding. Reviewers see content-specific views, like code diffs or generated images, and their decisions are sent back to the agent as structured Markdown or JSON. The tool currently runs on macOS and Linux, with Windows support planned, and all data stays local via a loopback-only API.
Berth is a new open-source application that runs coding agents such as Claude Code and Codex on a developer's own machines, allowing tasks to continue even after the laptop is closed. It is distributed as a signed and notarized app for both Apple silicon and Intel Macs.
Jotbus introduces a new tool that provides end-to-end encrypted shared scratchpads for coding agents like Claude Code and Codex. Users can create a secure, temporary workspace instantly without signing up, enabling seamless collaboration and handoffs among agents. The service is initiated via a simple command that sets up the environment for an hour with selected agents.
OpenAI has begun deploying an undetectable, machine-readable watermark called textGrain in ChatGPT and Codex, initially available only to users within the European Union. The company claims that textGrain's effectiveness matches or surpasses similar methods used by other AI developers, though it does not guarantee reliable detection or verify authorship. The move aligns with EU AI regulations, but has drawn some criticism from the community.
OpenAI announced plans to implement an invisible watermark in text generated by ChatGPT and Codex, starting in Europe to comply with the EU AI Act. The watermark, called textGrain, adds a statistical signal to the output, which can be detected by a dedicated tool to verify AI authorship. API users worldwide will also have the option to enable watermarking for certain models.