AIToday
Large Language ModelsAI Coding AssistantsHacker NewsPublished: Sep 10, 2026, 13:00 JST2 min read

Astra 6 Reforged build passes 94 Node tests

Astra 6 Reforged build passes 94 Node tests

3 Key Points

  1. What happened

    A developer rebuilt a ChatGPT 5 and Gemini 3 browser clicker game into Reforged using Astra 6 via Hermes Agent. The newer version adds a 3D tower, first-person exploration, spells, activities and procedural audio.

  2. Why it matters

    The original ran as a single HTML file with image-based art and recorded sound clips. Reforged splits the work into separate modules for simulation, activities and interface, and replaces recorded clips with Web Audio code.

  3. What to watch

    The final verification passed 94 Node tests and 79 browser tests, but the article cautions these are implementation checks, not scores for comparing models. It also says the build took repeated corrections, so the result hinges on how much human feedback was supplied.

WHO IT HITSThis lands on developers and technical teams evaluating how much human feedback an AI coding agent needs to ship a working browser game, and on anyone reading agent-produced test counts as a quality signal rather than a model comparison.

Ask the AI about this article →

Summaries like this, in your inbox every morning.

Context & Analysis

The article is a first-person build log comparing two AI-made versions of the same browser clicker game. The original was made with ChatGPT 5 and some Gemini 3, and the article notes the exact division of work between those two is unknown, so individual features cannot be credited to one or the other. The newer version, Reforged, was built with Astra 6 through Hermes Agent, which provided tools for reading files, editing code, running tests and opening the game in a browser.

The most visible change is that the room exists as a 3D scene written in Three.js, with first-person exploration added during development at the author's request. Spells, a target range and a slot activity were folded into the same Stardust economy, and the code was split into separate modules rather than continuing to grow the original single HTML file. Sound moved from recorded clips to Web Audio code that reacts to game events. The author supplied direction and played the results, so the comparison is explicitly not a matched-prompt benchmark: Astra 6 had the original to work from, a larger brief, different tools and repeated feedback, and there are no comparable time, token or cost records for the original.

The correction section is where the build log becomes a cautionary tale. A balance problem — rebirth being skippable by saving enough currency — also exposed a gap in the automated strategies, which kept buying upgrades and missed that route. Astra 6 then changed the boss-health curve and reran the strategies, after which 48 of 48 tested no-jackpot first-run strategies failed to finish, while tested prestige continuations still completed. A separate save-import bug let an imported boss have an extremely short attack interval, freezing combat; the fix restricted accepted intervals to between four and five seconds and added regression tests. For readers weighing agent-built software, the outcome likely hinges on how much of the verification was written and corrected with human playtesting, rather than on the raw test counts alone.

FAQ
What is the difference between the original game and Reforged?
The original used image-based art, separate sound files and a video ending. Reforged adds a rendered 3D chamber, an explorable tower, upgradeable spells, target practice, slots and procedural Web Audio.
What was the balance problem in Reforged?
A player could save enough currency to finish the first run without rebirth. The initial automated strategies kept spending on upgrades, so they missed that route; after a health-curve change, 48 of 48 tested no-jackpot first-run strategies failed to finish.
Do saves transfer between the two editions?
No. Saves do not transfer between editions, and clearing site data can erase them.

Get the latest Large Language Models news every morning

For example, today's edition would include:

  • DeepSeek V4.1-Flash: 763B model beats V4 Pro on AA Index 40Latent Space · 37m ago
  • Dynatrace acquires Arize AI as observability shifts to actionSiliconANGLE AI · 6h ago
  • Shared base cuts 100 fine-tunes from 1.5 TB to 19.3 GBDaily Dose of Data Science · 6h ago

AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. Q&As are published on this page for other readers too.

Related Articles

Next articleAstra's no-CoT jump replicates: 8.6x better than Fable 5.1