AMERICAN NEWS

Tesla to pay $243M judgement over Autopilot crash 34 by jeffbee | 11 comments on Hacker News.

Choosing a Language Based on Its Syntax? 7 by todsacerdoti | 0 comments on Hacker News.

Pocketbase lost its funding from FLOSS fund 40 by Onavo | 12 comments on Hacker News.

Sub-Millisecond RAG on Apple Silicon. No Server. No API. One File 6 by ckarani | 1 comments on Hacker News.

History of AT&T Long Lines 8 by p_ing | 2 comments on Hacker News.

Towards Autonomous Mathematics Research 20 by gmays | 2 comments on Hacker News.

(Ars) Editor's Note: Retraction of article containing fabricated quotations 41 by bikenaga | 22 comments on Hacker News.

Palantir Gets Millions of Dollars from New York City's Public Hospitals 52 by cdrnsf | 6 comments on Hacker News.

uBlock filter list to hide all YouTube Shorts 34 by i5heu | 12 comments on Hacker News.

Audiophiles Can't Distinguish Audio Sent Through Copper, Banana or Mud 41 by RandomGerm4n | 29 comments on Hacker News.

Show HN: Moltis – AI assistant with memory, tools, and self-extending skills 12 by fabienpenso | 2 comments on Hacker News. Hey HN. I'm Fabien, principal engineer, 25 years shipping production systems (Ruby, Swift, now Rust). I built Moltis because I wanted an AI assistant I could run myself, trust end to end, and make extensible in the Rust way using traits and the type system. It shares some ideas with OpenClaw (same memory approach, Pi-inspired self-extension) but is Rust-native from the ground up. The agent can create its own skills at runtime. Moltis is one Rust binary, 150k lines, ~60MB, web UI included. No Node, no Python, no runtime deps. Multi-provider LLM routing (OpenAI, local GGUF/MLX, Hugging Face), sandboxed execution (Docker/Podman/Apple Containers), hybrid vector + full-text memory, MCP tool servers with auto-restart, and multi-channel (web, Telegram, API) with shared context. MIT licensed. No telemetry phoning home, but full observability built in (OpenTelemetry...

IronClaw: a Rust-based clawd that runs tools in isolated WASM sandboxes 51 by dawg91 | 20 comments on Hacker News.

Dario Amodei – "We are near the end of the exponential" 37 by danielmorozoff | 52 comments on Hacker News.

Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL 12 by calebhwin | 9 comments on Hacker News. Hi HN, Been hacking on a simple way to run agents entirely inside of a Postgres database, "an agent per row". Things you could build with this: * Your own agent orchestrator * A personal assistant with time travel * (more things I can't think of yet) Not quite there yet but thought I'd share it in its current state.

GPT‑5.3‑Codex‑Spark 66 by meetpateltech | 23 comments on Hacker News.

NetNewsWire Turns 23 43 by robin_reala | 8 comments on Hacker News.

We rendered and embedded one million CAD files 9 by DavidFerris | 5 comments on Hacker News.

Show HN: Open-Source SDK for AI Knowledge Work 9 by ankit219 | 1 comments on Hacker News. GitHub: https://ift.tt/RtHWG3c Most AI agent frameworks target code. Write code, run tests, fix errors, repeat. That works because code has a natural verification signal. It works or it doesn't. This SDK treats knowledge work like an engineering problem: Task → Brief → Rubric (hidden from executor) → Work → Verify → Fail? → Retry → Pass → Submit The orchestrator coordinates subagents, web search, code execution, and file I/O. then checks its own work against criteria it can't game (the rubric is generated in a separate call and the executor never sees it directly). We originally built this as a harness for RL training on knowledge tasks. The rubric is the reward function. If you're training models on knowledge work, the brief→rubric→execute→verify loop gives you a structured reward signal for tasks that normally don't have one. What makes Knowledge work different from code? (apa...

The Singularity will occur on a Tuesday 104 by ecto | 57 comments on Hacker News.

Show HN: HN Companion – web app that enhances the experience of reading HN 3 by georgeck | 0 comments on Hacker News. HN is all about the rich discussions. We wanted to take the HN experience one step further - to bring the familiar keyboard-first navigation, find interesting viewpoints in the threads and get a gist of long threads so that we can decide which rabbit holes to explore. So we built HN Companion a year ago, and have been refining it ever since. Try it: https://ift.tt/uwph95H or available as an extension for Firefox / Chrome: [0]. Most AI summarization strips the voices from conversations by flattening threads into a wall of text. This kills the joy of reading HN discussions. Instead, HN Companion works differently - it understands the thread hierarchy, the voting patterns and contrasting viewpoints - everything that makes HN interesting. Think of it like clustering related discussions across multiple hierarchies into a group and surfacing the comments that represent eac...