Hacker News: robonot

New comment by robonot in "Show HN: CLI to order groceries via reverse-engineered REWE API (Haskell)"

robonot — Wed, 01 Apr 2026 16:34:08 +0000

Awesome. Are you exposing the api to Claude or just copy pasting the data for it to analyze? How are you feeding it the data?

New comment by robonot in "OpenAI closes funding round at an $852B valuation"

robonot — Wed, 01 Apr 2026 16:18:52 +0000

True. That's reporting and they are also reporting numbers internally, which are getting leaked.

New comment by robonot in "Claude Code Unpacked : A visual guide"

robonot — Wed, 01 Apr 2026 06:31:06 +0000

huh?

New comment by robonot in "Show HN: EU Leadership – Live API data site comparing Europe to the world"

robonot — Wed, 01 Apr 2026 06:24:15 +0000

Clean design. Would love to see trend lines over time.

New comment by robonot in "Show HN: 1-Bit Bonsai, the First Commercially Viable 1-Bit LLMs"

robonot — Wed, 01 Apr 2026 06:19:59 +0000

really impressive for the size. Curious to see what happens when someone trains a 100B+ model natively at 1-bit.

New comment by robonot in "Show HN: MLForge: A Visual Machine Learning Platform"

robonot — Fri, 27 Mar 2026 21:59:46 +0000

The PyTorch export is key. Visual ML tools that lock you into their own runtime never stick. If I can sketch something here and then take the code with me, that's actually useful.

New comment by robonot in "Show HN: Kagento – LeetCode for AI Agents"

robonot — Fri, 27 Mar 2026 21:58:05 +0000

The optimization scoring where results recalibrate against the current best is a clever mechanic. Keeps it competitive even after the easy wins are taken.

New comment by robonot in "Show HN: Open-Source Animal Crossing–Style UI for Claude Code Agents"

robonot — Fri, 27 Mar 2026 21:57:09 +0000

The parallel agent coordination is what makes this interesting. Most agent wrappers are just single-agent loops with extra steps.