GoKawiil
Tech News
A writer describes rebuilding their personal homepage entirely through Claude, without writing or running code or opening a GitHub pull request, using Opus 5.5 in a Claude Project. Roughly 60 parallel Claude sessions handled tasks including a CGI parody video and an original soundtrack, with most orchestration done from a phone rather than a local machine.
An engineer at Recurse Center tried to solve a 3D-printed physical puzzle where corn-kernel-shaped pieces must slide into a grooved cob without gaps or overlaps. After manually attempting it, they asked Claude to write a solving script, which required some back-and-forth to correct piece shapes via computer vision. Rather than implementing recursive backtracking as expected, Claude's script imported Google's OR-Tools CP-SAT constraint solver library to find a solution.
A user named Cobanov used Anthropic's Claude AI to debloat his four-year-old Android TV through developer/ADB access, instructing it to disable unused apps, shorten animations, and log all changes rather than uninstall anything. He also replaced Google TV's ad-heavy home screen with FLauncher, an open-source app launcher, and reported the TV ran smoother than when new, all without rooting the device.
Andrew Boyd, founder of Standard Agents Inc., says his Jev decision model beat Pokémon Red's Elite Four and Champion, reaching the Hall of Fame on September 23, 2026, less than a week after the run began. Jev isn't a chatbot or LLM; it picks from lists of weighted options rather than reading the screen, while Anthropic's Claude Opus 5 monitored the game log and adjusted those options to help it when stuck. A harness changelog logged 474 fixes, including repeated failures like walking into a shut door 53 times and looping a ladder 124 times.
Anthropic has opened a public Claude Marketplace consolidating plugins, connectors, agents and consulting services in one hub. The listing already includes more than 2,000 integrations from companies such as Atlassian, Google, Microsoft, Notion and Salesforce, plus Claude-powered products from partners like CrowdStrike, Cursor, Harvey, Legora, Lovable and Snowflake, alongside integration support from Accenture, Boston Consulting Group and Deloitte. Developers can build connectors using Model Context Protocol and Agent Skills, and companies can apply to list their Claude-based products.
Three computer scientists connected leading AI language models to a Toyota Corolla's steering, throttle and brakes using a comma four device and GPS telemetry, then had each model attempt a short parking-lot driving course with no human input beyond a foot hovering over the brake. Only OpenAI's GPT-6 Astra completed the full course, doing so on its second try in about five minutes over a distance of under 500 feet, while most other attempts failed to get past the first corner.
Drawgent is a new open-source utility that connects existing installations of Claude Code, Codex or opencode agents to a live Excalidraw whiteboard. Users can request diagrams via a chat panel or annotate a drawing with an 'AGENT:' note, and the connected agent reads the canvas, makes edits, verifies the result, and marks the task done. Setup runs a one-time check per agent, installs ACP adapters and, if needed, a headless Chrome renderer, storing configuration locally.
A developer created a set of Claude Code skills that convert a single chess game into a readable post-mortem, combining Stockfish engine analysis with the player's own recorded thoughts during the match. In a demonstration, Claude transcribed a French audio recording of the player's in-game reasoning via whisper.cpp, aligned it with move timestamps from the PGN, and produced a narrated video explaining specific decisions, such as bishop placement choices, verified against engine lines. All underlying files—transcript, engine analysis, annotated PGN, and storyboard—are shared in the project's example folder.
Benchmarking site Arena analyzed high-reasoning Text Arena responses from August and September 2026 and found Anthropic's Claude Opus 5.5 uses far fewer em dashes and semicolons than Opus 5, along with shorter, simpler sentences. Em dash usage fell from 15.2 to 0.8 per 1,000 words, and average sentence length dropped from 12.14 to 10.03 words, though overall answers grew longer, from 453 to 481 words on average.
A Haskell programmer has published an essay addressing anxieties about AI-driven burnout, job insecurity from LLM-assisted coding, and declining code quality. The author, writing entirely without AI assistance, argues that much of programming's satisfaction comes from the act of expressing thought in code itself, and warns that relying on LLMs to generate code risks eroding that enjoyment.
The US Court of Appeals for the DC Circuit ruled 2-1 that the Trump administration acted within its authority under the Supply Chain Security Act when it barred federal agencies and defense contractors from using Anthropic's products. The panel found the government could blacklist Anthropic for refusing to enable certain AI capabilities even absent malicious intent, denying Anthropic's petition for review. Anthropic said it disagrees with the ruling and may seek en banc review or petition the Supreme Court.
Science writer and former theoretical physicist Matt von Hippel issued a public challenge for an AI model to tackle a computationally demanding problem from his former field of theoretical physics. Within about a month, Anthropic's Claude was shown to complete the task, calculating a nine-loop result that von Hippel says was hard not because the method was unknown but because the computation itself was formidable.