A compact unofficial client lets a 2007 Nokia Series 40 phone (tested on a Nokia 6300) chat with Claude via a Java ME MIDlet and a tiny Go server. The phone app (~100 KB JAR) provides a keypad-first chat UI with bubbles, timestamps, typing indicator, reading mode, paged long replies, message actions (shorten, simplify, translate, edit), calendar/to‑do integration, saving replies to the phone, quick prompts, language support (English/Turkish) and an install/setup wizard. Web search, news, weather and exchange rates are performed by the server and listed with replies. Builds are reproducible and the server is available as a single Go binary / Docker image (~7 MB).
The server exists to bridge the phone’s archaic TLS and modern Claude API: Series 40 phones only support TLS 1.0 with RSA key exchange, no SNI, and an outdated root store, so the server terminates TLS using a private CA certificate that the user installs on the phone, then talks modern HTTPS to the Claude API. Per-device pairing issues a revocable access token; chats are stored in SQLite for 30 days (pinned ones kept), and the server enforces per-device request and token limits. Deployment requires a public IPv4 host with TCP/443, Docker and simple scripts to generate a CA and deploy; the Claude API key stays on your server and usage is billed to it. Licensed MIT.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
OpenAI and Synopsys have announced GPT-Synopsys, a frontier intelligence platform designed to revolutionize chip design. The collaboration aims to enhance AI-driven automation and optimization in semiconductor development. (news.synopsys.com)
The US government's new AI chatbot has refrained from debunking claims made by Trump. The chatbot is currently experiencing connection issues that prevent full functionality. (techxplore.com)
OpenAI reduced the usage allowance for the $200 plan from 20x to 10x the ChatGPT Plus limit starting October 30, 2026. A new Pro 500 tier offers 25x the usage of Plus for users needing more capacity. (news.ycombinator.com)
Vectorless, reasoning-based retrieval-augmented generation (RAG) is introduced by VectifyAI to improve AI reasoning without relying on vector embeddings. The approach enhances reasoning capabilities in AI models, as detailed in their GitHub repository. (github.com)
The video features interviews with AI CEOs in 2026 discussing the future of artificial intelligence and its impact on industries. It highlights advancements in AI leadership and technological integration. (youtube.com)
A GitHub project involving 'torturing' large language models has sparked a heated debate about AI consciousness and model welfare. Experts agree that LLMs are not sentient, but some AI safety advocates worry about their 'mental health' as models become more advanced. (404media.co)
Today's best Hacker News stories, summarized and screenshotted, one email a day.