Hacker News Reader

> In our evaluations, GPT-5.6 Sol on Ultrafast mode answered all 2,500 HLE questions in 11 hours and 11 minutes. Claude Fable 5 needed 78 hours and 27 minutes, more than three days of continuous compute, to arrive at the same conclusions. In other words, Ultrafast worked through the frontier of human knowledge in a single working day, achieving comparable accuracy nearly 7× faster.

This is actually insane.

Hopefully the release ultrafast of Terra and Luna too.

Fe2O3on Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

> “I think I might need some relaxation time. It feels important to take a breather and find ways to unwind. There’s a lot going on sometimes, and it’s easy to forget to slow down. Maybe I could explore some activities that help clear my mind or consider options like a calming walk, some quiet reading, or just reflecting on things that bring me joy. It’s all about finding that balance, right?”

— GPT-5.6 Terra, reasoning summary, mid-run

This is hilarious

Fe2O3on Show HN: Line9 – A Mermaid rendering engine with its own layout

Yeah sorry, I should have clarified that I wish OP's product was open source. mb

Fe2O3on Show HN: Line9 – A Mermaid rendering engine with its own layout

This solves my biggest gripe with Mermaid.

It's an amazing tool, but I wish it were open source.

Fe2O3on Show HN: iPhone app takes simultaneous images from 2 lenses, fuses into 1 photo

Anything like this for Android or Pixels?

Fe2O3on Halcyon Video – a 3D video store for your media server

This is so well thought out.

Fe2O3on Launch HN: Keet (YC S24) – An app to create video courses on anything

I see. Once again, really cool product! Congrats!

Fe2O3on Launch HN: Keet (YC S24) – An app to create video courses on anything

Super cool!

Would you mind giving more insight into how you make the videos (sourcing clips or generating them for Remotion videos, agentic?, and how you handle rendering issues and QA for the Manim videos) and costs?

Fe2O3on Manus will return to operating as an independent company

Absolutely. Haven't heard anyone talk about recently.

Fe2O3on Show HN: Git-knife – Edit commit messages, authors, and dates like a spreadsheet

This is cool, but has anyone ever needed to rewrite commit authors or dates?

Fe2O3on Stealing Reasoning Traces from Proprietary LLM APIs

This proves that OpenAI models reason in grug speak to save tokens! I wonder if open models are going to start doing that too to save on reasoning tokens.

Fe2O3on StockCoaster (Made by Orca)

I didn't make this, the Orca team did, but I thought it was really cool.

They did one-shot it with Fable.

Repo: https://github.com/stablyai/stockcoaster

Fe2O3on Launch HN: Stoa Markets (YC S26) – A Marketplace for GPUs and AI Servers

Will there be support for lower-end GPUs like RTX 4090s or RTX 6000 Pros in the future?

Fe2O3on Mistral Patent for “Code implemented tool calls”

Cloudflare introduced Code Mode far earlier (https://blog.cloudflare.com/code-mode/)

Fe2O3on Auto mode is now the default in Claude Code

I've been using Kilo Code (with MiniMax M3) with auto approve (similar to dangerously skip permissions) and I haven't had a single incident.

However, I don't give it long running tasks unsupervised, and I do interrupt it from time to time to give suggestions.

Fe2O3on Picophysics: Single file physics for games on platforms like N64, PSX, DC

It's hand written and should also work on microcontrollers like ESP32s or Pi Pico 2. Have you tried anything like that yet?

The Pico in particular has enough RAM and supports floating point math.

Fe2O3on Ask HN: Recommended Merchant of Record and Affliate Setup

For MOR, Stripe has its own (recently launched) Managed Payments system: https://docs.stripe.com/payments/managed-payments

Fe2O3on Windows 11's built-in Weather app wastes more than 1 GB of RAM

This article seems to be underestimating how much RAM a weather app should take. A well thought-out, native Weather app wouldn't take more than 100 mb of RAM.