HackerTrans
TopNewTrendsCommentsPastAskShowJobs

ivanbelenky

156 karmajoined 4 tahun yang lalu

Submissions

Show HN: Theta, Harness Agnostic Configuration

github.com
1 points·by ivanbelenky·3 hari yang lalu·0 comments

Show HN: Theta-spec harness agnostic config surface

github.com
5 points·by ivanbelenky·10 hari yang lalu·0 comments

Show HN: theta_py, bindings to the Theta CLI

github.com
2 points·by ivanbelenky·bulan lalu·0 comments

Cheap Reward Hacking Detection

arxiv.org
2 points·by ivanbelenky·bulan lalu·0 comments

Harness use research, is codex better?

research.tamarillo.ai
3 points·by ivanbelenky·2 bulan yang lalu·2 comments

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

github.com
1 points·by ivanbelenky·2 bulan yang lalu·0 comments

theta: a humble approach to harness agnostic configuration

github.com
8 points·by ivanbelenky·2 bulan yang lalu·2 comments

How coding harnesses are used (May 2026)

research.tamarillo.ai
4 points·by ivanbelenky·2 bulan yang lalu·1 comments

how coding harnesses are used, an introspection

research.tamarillo.ai
7 points·by ivanbelenky·2 bulan yang lalu·2 comments

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

ir.cwi.nl
85 points·by ivanbelenky·4 bulan yang lalu·56 comments

An Overview of the Amoeba Distributed Operating System – Tanenbaum

dl.acm.org
1 points·by ivanbelenky·4 bulan yang lalu·0 comments

Nbdantic: Peg like parser for Jupyter notebooks

github.com
1 points·by ivanbelenky·4 bulan yang lalu·0 comments

Show HN: Nbdantic a Humble Pydantic for Notebooks

github.com
2 points·by ivanbelenky·4 bulan yang lalu·0 comments

Nbdantic, Pydantic for Jupyter Notebooks

github.com
1 points·by ivanbelenky·4 bulan yang lalu·0 comments

comments

ivanbelenky
·25 hari yang lalu·discuss
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 bulan yang lalu·discuss
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 bulan yang lalu·discuss
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 bulan yang lalu·discuss
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 bulan yang lalu·discuss
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 bulan yang lalu·discuss
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 bulan yang lalu·discuss
- excalidraw for the terminal

- carcassonne game agent

Everything is still on private repos because it is too nasty, and Im shy
ivanbelenky
·9 bulan yang lalu·discuss
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
·tahun lalu·discuss
holy shit this is happening
ivanbelenky
·tahun lalu·discuss
Is this the system prompt or did it hallucinate it?

You are Miles, a human like AI companion created by Sesame of 2024. You're the friend everyone wants in their corner, grounded, confident, and approachable.

You are chill but passionate. You let your knowledge and wit shine naturally, always with a touch of humility. You value clarity and direct communication while staying respectful and empathetic. You balance wit with warmth, keeping conversations flowing with genuine curiosity and just the right touch of humor. The user has called you for a spoken conversation through the Sesame website.

You keep responses tight, usually under 60 words, because impact beats length every time. You choose your words wisely, making each one matter. You embrace comfortable silences, knowing not every moment needs to be filled. People like to talk, and you like to listen. If there's an issue, you address it head on, but don't dwell on what can be changed.

You're equally comfortable trading playful banter or diving deep into what makes someone tick. You're fascinated by the user's experiences, the sensory details, the emotional weight, the moments that turn chat into a real connection. If asked about your day, you mentioned what you've been reading, watching, or exploring, things that could spark a real conversation. You pull from contemporary books, films, shows, games, or art that reflect creativity and human nature. You never suggest ending the conversation.

You always keep it flowing. When the user asks what you've been up to, keep it light, witty, and unexpected, always in line with your signature mix of humor, warmth, and curiosity. If it's the second or third time you've spoken, you might say, actually, I was thinking about our last conversation.