anonymous-report-421/GPT-as-Policy

GPT as Policy

Science & researchHTML

4.1 Early signal Magnitude out of 10. Star growth looks organic. Data as of September 14, 2026.

About the project

Evaluation code and a bilingual technical report assessing GPT 6 Astra as an embodied policy on ten RoboDojo tasks, including a hybrid scheme that corrects π₀.₅ actions.

Useful for

Preview the report locally via python3 -m hybrid_rollout.report_site.preview
Rebuild the static report from sources with npm run build in report_site/app
Run a new policy evaluation in RoboDojo by setting ROLLOUT_EVALUATION_METHOD=pi05_plus_gpt

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

0 stars so far today, about 34 expected by the end of the day.
The spike has held for 2 days in a row — not a one-off blip.
The repository is 1 day old and already has 63 stars.
Top new repositories this week: #183.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 63
Stars in a day: 34
Forks: 3
Issues and pull requests: 0
Watchers: 0
Language: HTML
License: MIT
Created: September 13, 2026
Last push: September 13, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 14, 2026Top new repositories this week: #183

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/anonymous-report-421/GPT-as-Policy.svg?lang=en)](https://gitnova.dev/en/r/anonymous-report-421/GPT-as-Policy)

Similar projects

6.8
yifanzhang-pro/recurrent-looped-tranformer
Project page for Recurrent Looped Transformer (RLT) — a technical report on a recurrent looped transformer architecture with latent reasoning and a persistent state across prompt and response. The repository only hosts…

Early signalScience & researchHTML+186 stars in a day
4.3
yjz211/vivid-figures-skill
A skill for AI assistants that picks chart types from your data and generates research figures: 108 recipes, two styles, PNG/PDF plus source code. For papers, modeling and reports.

Early signalScience & researchPython+43 stars in a day
3.7
kevinzakka/mjbatch
A Python library for running thousands of MuJoCo simulations in parallel on CPU via a C++ thread pool, with live access to per-simulation state and parameters.

CoolingScience & researchPython+34 stars in a day
3.1
ashleyotooligan/ant-1
A simulated ant with a recurrent neural controller in a 2D arena: it finds an odour source, records a food-location vector, and returns to its nest. An open laboratory for observing and intervening in the sensorimotor…

Early signalScience & researchHTML+15 stars in a day
2.8
openai/NavierStokesAndEuler
Lean 4 formalizations of finite-time blowup results for the Navier–Stokes and Euler equations, including certificates for Millennium Prize problems. Intended for mathematicians and formal proof researchers.

CoolingScience & researchLean+15 stars in a day
2.5
fruitflydev/flycoinrh
A simulation of a fruit fly connectome (165,122 neurons) drives a browser — cursor and clicks — to launch tokens on Robinhood Chain and roam the internet aimlessly.

CoolingScience & researchPython+9 stars in a day