HN user

iFire

413 karma
Posts3
Comments298
View on HN

Since this is the largest gathering of LISP users I have seen, I have a question.

Why prefer lisp-1 over lisp-2 or vice-versa?

Muse Spark 1.1 13 days ago

This is pretty cheap compared to anthropic opus and fable.

https://platform.claude.com/docs/en/about-claude/pricing

Model Base Input Tokens 5m Cache Writes 1h Cache Writes Cache Hits & Refreshes Output Tokens

Claude Fable 5 $10 / MTok $12.50 / MTok $20 / MTok $1 / MTok $50 / MTok

Claude Opus 4.8 $5 / MTok $6.25 / MTok $10 / MTok $0.50 / MTok $25 / MTok

Note Fable costs $50 MTok and Opus 4.8 costs $25 / MTok.

At the Ise Jingu, the shrine is not built to last; it is built to be reconstructed from scratch every twenty years.

If we want our systems to last, we would need the "process knowledge"—the actual mastery of the craft—to be in human hands rather than decaying in a dead system.

I don't think we can afford to process-knowledge-transfer many of our essential systems... without machine assistance.

Most of the platforms were successfully petitioned to have rust sdk mandatory added so that rust code can be added to the platforms. The previously situation was rust was not allowed because the external dependency of the rust sdk was blocked.

Note that the rust having no stable api is not fixed, so I think there's a bunch of internal systems on each platform to hard lock the rust dependencies across multiple rust users.

There's some friction between platform packagers and the code that the author wrote exactly as it was written.

Huh?

I thought the latest advance in computing (spring 2025 - last year) is self-play / reinforcement learning. Like we've ran out of training data a few years ago.

https://github.com/OpenPipe/ART

Reinforcement learning having the large language model devise puzzles that they solve via llm-as-judge.

The definition of llm-as-judge is your llm generate 8-12 trajectories and a different llm judges the result. I'd use an oracle like windows or linux operating system execution for the problem of ISA-assembly creation.

The winning entries are used to train the large language model.

You've got a good point.

Why not directly have the llm write ISA assembly. We're still grading based on results / theory proofs and for example the certifications for cryptographical government use are based on binary codes and not sources.

Edited:

Why not go further and print the chips, pcbs directly via 3d printing with llm instructions.

Edited (joke):

Why not go the furthest and turn the entire earth into a computer and grey goo?

FreeCAD 5 months ago

As part of my donated work in Godot Engine, my approach is to improve manifold https://github.com/elalish/manifold to get a "geometric kernel"

I think I've succeeded and many CAD tools use manifold for geometric kernels on 3d boundary meshes.

I was able to get Godot Engine and Blender to adopt elalish/manifold.

List of CAD tools that adopted elalish/manifold.

OpenSCAD Blender IFCjs Nomad Sculpt Grid.Space badcad Godot Engine OCADml Flitter BRL-CAD PolygonJS Spherene Babylon.js trimesh Gypsum Valence 3D bitbybit.dev PythonOpenSCAD Conversation AnchorSCAD Dactyl Web Configurator Arcol Bento3D SKÅPA Cadova BREP.io Otterplans Bracket Engineer