GPT-6 Astra in Codex CLI 0.156.1
skills off
Zoom, inline player and more ways to view
The model's own page, run in a sandboxed frame only when you ask (a page that needs its own origin opens in a new tab on a separate demo site). Phones get a full-screen player capped at 1.5x pixel density (2x on larger screens) so it stays smooth; the original page runs uncapped. It starts in its auto-tour (T switches to play mode on a keyboard).
Wall time 50m 34sCost $10.77 estimated
Review
No verdict yet.
The full review
OK. Finished on its own after 50.6 min.
Scores
AI judge
Not scored
No rubric for this prompt
Visitor votes and reviewer grades are not available yet.
- AI judge
- AI judge: the test runner (model claude-opus-5-5), scoring by visual review of the 1600 px render against the pre-registered rubric. No AI-judge score exists for this result: there is no rubric for this prompt, so no score is shown and none is made up.
- Visitors
- Public voting with a blind reveal is coming: you score the output first, then see the other scores.
- Reviewer
- The reviewer's own grade appears here once it is added.
Scores compare results for the same prompt only. AI-judge boards rank runs within one prompt, equal totals sharing a rank; scores from different prompts are never averaged.
Downloads
Files actually published for this run. Original output, site-made previews and post-run conversions are labelled separately.
The exact prompt
as run, 909 characters. Every result for this prompt
Build a single-page Three.js scene (one index.html file, no build step, three.js from a pinned CDN) with a rigged humanoid character (a procedural skeleton and simple body meshes are fine) that plays walk, run and jump cycles, with on-screen buttons or keys to switch between them and blend smoothly from one to the next. The motion must look human, not spider-like: respect realistic joint limits (knees and elbows bend one way only, no joint rotates past a human range), feet plant on the ground with no sliding while in contact, the pelvis bobs and the torso stays upright with natural counter-rotation of shoulders and hips, and arms swing opposite to the legs. Include a ground grid, an orbit camera and a toggle that shows the skeleton. It must run at 60 fps in a desktop browser and work with touch. Write everything into the working directory and finish with a short README.md describing the controls.
How it was made
Step by step
The prompt, every agent turn and tool call (tool name and a one-line summary; inputs and outputs are not shown), then the final message. The full transcript is 6.7 MB; it is published as a scrubbed, compressed download rather than shown on the page.
Show all 79 steps
Loading the timeline…
Download the full transcript Codex CLI rollout JSONL, 166 KB, gzip. Scrubbed: anything that looks like a key, token, e-mail address or phone number is replaced, and account details and the test machine's file paths are removed.
Cost breakdown
Headline cost $10.77, estimated from the token counts at list price.
| Tokens by type | Tokens | $ per 1M | Cost |
|---|---|---|---|
| Input (uncached) | 150 | $10.00 | $0.0015 |
| Cache write | 146,105 | $10.00 | $1.4610 |
| Cache read | 4,286,374 | $1.00 | $4.2864 |
| Output | 100,324 | $50.00 | $5.0162 |
| of which reasoning | 59,112 | billed as output |
- Total computed from tokens
- $10.77
- Total reported by the harness
- none
Computed from harness-reported token counts x list prices. Cache writes priced at the input rate (the price table has no separate cache-write price).
Prices: Project price table (vendor list prices), 2026-09-22.
Run notes
- frozen prompt (written): prompts/humanoid_motion_cycle.md verbatim (written 2026-09-30 from a public X post GPT-6 Sol human motion looks spider-like)
- plain CODEX_HOME copy (config.toml only, run work/ trusted; no AGENTS.md/skills/state)
- Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
- Isolation audit: outside paths seen