ivanbelenky

25 ngày trướcdiscuss

for the internal use at my company we created a tool to partially solve this issue by building a manifest that MAY contain tags and other metadata for agentic resources lookup.

https://theta.tamarillo.ai

ivanbelenky

2 tháng trướcdiscuss

humble sliced public repo harness configs research, codex shows interesting traits

- overrepresentation in high starred buckets - overrepresentation in rust - if we trust proxy signal, ~50% of CC repos and growing equally as fast

it is also a harness that gets configured mainly with a toml file, single manifest is not the case but a great chunk of the configuration surfaces is sitting in `config.toml`

ivanbelenky

2 tháng trướcdiscuss

theta-spec is a declarative, harness-agnostic configuration standard for AI coding agents. `theta` is its canonical implementation.

We use it internally at `tamarillo.ai` and we are fully aware of its limitations, but we also feel it’s mature enough to share. This is our interpretation of what it would take to allow individuals working across different harnesses (or teams with more complex configurations) to be able to keep things consistent, or share their configurations with others.

Any feedback and contribution to the spec and reference implementation is extremely welcomed. We already support a few of the most common harnesses today.

Also when putting this together there were a lot of assumptions made, and many of those could prove to be wrong, so contributions are welcomed all the way through to the fundamentals.

ivanbelenky

2 tháng trướcdiscuss

At tamarillo.ai, we are building, among many other things, tooling to standardize coding harnesses. This is our humble attempt to understand one slice of their usage.

ivanbelenky

2 tháng trướcdiscuss

something is happening with `codex`, at tamarillo.ai we did a [little experiment](https://research.tamarillo.ai/coding-harness-inspection/), with 400K repos that have AI harnesses configured and very interesting behavior is observed

- growing fast as fuck

- overepresentation on starred repos (even though stars mean less these days, it is definitely something to look at)

- overepresentation in `rust`

- in terms of aliveness, codex is first

ivanbelenky

2 tháng trướcdiscuss

At tamarillo.ai, we are building, among many other things, tooling to standardize coding harnesses. This is our humble attempt to understand one slice of their usage.

ivanbelenky

9 tháng trướcdiscuss

- excalidraw for the terminal

- carcassonne game agent

Everything is still on private repos because it is too nasty, and Im shy

ivanbelenky

9 tháng trướcdiscuss

Thanks for sharing. I did not know this law existed and had a name. I know nothing about nothing but it appears to be the case that the interpretation of metrics for policies assume implicitly the "shape" of the domain. E.g. in RL for games we see a bunch of outlier behavior for policies just gaming the signal.

There seems to be 2 types

- Specification failure: signal is bad-ish, a completely broken behavior --> local optimal points achieved for policies that phenomenologically do not represent what was expected/desired to cover --> signaling an improvable reward signal definition

- Domain constraint failure: signal is still good and optimization is "legitimate", but you are prompted with the question "do I need to constraint my domain of solutions?"

  - finding a bug that reduces time to completion of a game in a speedrun setting would be a new acceptable baseline, because there are no rules to finishing the game earlier
  
  - shooting amphetamines on a 100m run would probably minimize time, but other factors will make people consider disallowing such practices.

ivanbelenky

12 tháng trướcdiscuss

toy game engine for the tty concept

ivanbelenky

năm ngoáidiscuss

https://github.com/ivanbelenky/RL one the great pleasures in my life was implementing almost completely this book

ivanbelenky

năm ngoáidiscuss

Awesome

ivanbelenky

năm ngoáidiscuss

Contributions are welcomee!!

ivanbelenky

năm ngoáidiscuss

it can be extended arbitrary given the proper dataset. For the current default settings, road class covers everything below 3. This translates to

FREEWAY = 1 # Freeway (Multi-lane, controlled access)

PP_TH = 2 # Primary Provincial/Territorial highway

SP_TH_MA = 3 # Secondary Provincial/territorial highway/ municipal arterial

MC_USP_TH = 4 # Municipal collector/Unpaved secondary provincial/territorial highway

LS_WR = 5 # Local street/ winter road

3 was the sweetspot. The dataset can be explored here in case you want to get an intuition on detail level. https://geodata.bts.gov/datasets/usdot::north-american-roads...

ivanbelenky

năm ngoáidiscuss

This is a project I did not maintain much for the past few months, but recently I migrated many other codebases to be uv managed, and I find this optimal for many reasons. Happy to receive contributions and fix the quite strict requirements I set. That would probably be the faster way.

ivanbelenky

năm ngoáidiscuss

Thx for the heads up on optimizations available. The “Approximations” comment does not apply to the shortest path calculation, but rather to the distances and upper bound times estimations. This is the consequence of enabling routing for points that dont exist as nodes (closest node approximation).

ivanbelenky

năm ngoáidiscuss

"This NTAD dataset is a work of the United States government as defined in 17 U.S.C. § 101 and as such are not protected by any U.S. copyrights. This work is available for unrestricted public use."

I based my work on this, maybe the link is out, thx for testing. The dataset has already been consumed and collapsed into a smaller graph representation.

ivanbelenky

năm ngoáidiscuss

does that account for 1% of gmaps functionality?

ivanbelenky

năm ngoáidiscuss

holy shit this is happening

ivanbelenky

năm ngoáidiscuss

my code is not as good as anything above most probably. Ive done this exploring while studying. No linter no typechecker, grug engineer mentality. But thanks nevertheless for the comment :)

ivanbelenky

năm ngoáidiscuss

It has not been stress tested, or optimized, tread lightly and thanks a lot for appreciating the work.

ivanbelenky

Submissions

Show HN: Theta, Harness Agnostic Configuration

Show HN: Theta-spec harness agnostic config surface

Show HN: theta_py, bindings to the Theta CLI

Cheap Reward Hacking Detection

Harness use research, is codex better?

Show HN: theta-spec - a humble harness agnostic configuration spec

theta: a humble approach to harness agnostic configuration

How coding harnesses are used (May 2026)

how coding harnesses are used, an introspection

Stdwin: Standard window interface by Guido Van Rossum [pdf]

An Overview of the Amoeba Distributed Operating System – Tanenbaum

Nbdantic: Peg like parser for Jupyter notebooks

Show HN: Nbdantic a Humble Pydantic for Notebooks

Nbdantic, Pydantic for Jupyter Notebooks

TTY RL toy game engine

Constrained Random Walks

TTY Trainable Game Engine

C minimal Xbox controller state to events mapper for macOS

Infinite TTY pixel art editor written in Rust

Show HN: US Routing – Python library for fast local routing in the US

comments