building @just_unmute · talk to claude code & codex by voice · shipping in public from bengaluru · @iitgn
Bengaluru
Joined August 2022
- Tweets1.7K
- Following553
- Followers201
- Likes1.3K
Pinned Tweet
i gave fable 5.2 one prompt and went to sleep
11 hours later it had built the entire history of earth as a fully interactive 3d globe. big bang to today
drag the timeline to any year, spin to any place, click anything to go deeper. this is just ww2
the last thing on the timeline is the ai that built it
I wanted to test Fable 5.2's quality with one-shot prompts without human feedback.
Everything in this game is from scratch: models, sounds, textures. ~$550 at API pricing, ~2.7M output and 445M input tokens, heavily cached. Took 8 hours!
Play it here: claude.ai/artifact/BGY1SztrA…
testing a theory right now
opus 5.5 plans and orchestrates. fable 5.2 only executes, one big job per session, no back and forth
long chatty fable sessions burn tokens and waste what its actually good at
will share numbers once its done
1
34
what i noticed after letting fable 5.2 run a whole project alone
long running doesnt really mean long. its more like wide and deep at the same time. research in one corner, deep code in another, testing somewhere else, and every branch has its own mess inside it. fable just holds all of it, in one shot. havent seen that from any model before
stuff thats working for me
- write a proper spec. honestly thats the only bottleneck now, not the model
- let it research as it goes and dont let it assume anything. its research is good enough to trust
- make it check its own work. opus 5.5 did this too but missed a lot. fable actually catches its own mistakes
- then just step back and let it steer
this is what one prompt and 11 hours got me
i gave fable 5.2 one prompt and went to sleep
11 hours later it had built the entire history of earth as a fully interactive 3d globe. big bang to today
drag the timeline to any year, spin to any place, click anything to go deeper. this is just ww2
the last thing on the timeline is the ai that built it
1
1
87
wanted to post a fable 5.2 example last night. its still running. almost 6 hours in lol
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
2
1
115
11+ hours later
teapaw.org/arpittalksstuff/status…
i gave fable 5.2 one prompt and went to sleep
11 hours later it had built the entire history of earth as a fully interactive 3d globe. big bang to today
drag the timeline to any year, spin to any place, click anything to go deeper. this is just ww2
the last thing on the timeline is the ai that built it
34
try it: earth-whole-story.pages.dev
what's inside:
- 13.8 billion years on one scrollable timeline
- continents drifting from real plate data
- 67,000+ events, every country
- 16 scroll stories (ww2, black death, spice routes, silk roads...)
- 12 trails (follow the buddha, the story of salt...)
- kid mode, sources on everything
the exact prompt and all the code are open source
prompt: github.com/arpitpatel25/eart…
repo: github.com/arpitpatel25/eart…
11 hours unsupervised, about $162 at api pricing, it wrote and passed its own test suite
1
4
514
The cheap model is the one your agent actually runs all day.
Releasing Muse Ember today -- our smallest model that delivers higher intelligence per dollar than others in its class. Built for token-heavy work that agents repeat all day: tool calls, coding subtasks, routing, extraction, and long document parsing. Available today on the Meta Model API and in Muse Code.
2
125
Arpit retweeted
this bridge only exists where my lantern shines 🏮
first time ever making a game: a papercraft adventure about carrying the last flame home.
built with Opus 5.5. the courier, lanterns and ruins were all generated in Mixar.
would you play this?
#indiegame #gamedev
ChatGPT Plus voice just went from 1 hour a day to 3.
To be fair: Images 2.6 landed on Plus four days ago! You can turn a sketch into a GIF, and images generate 50% faster.
We also tripled daily GPT‑Live voice time from 1 to 3 hours.
On Codex, even tho Plus limits stayed the same, 6.1 Terra gets you more tasks out of that allowance.
(all in the last 4 weeks)
1
2
68
MIT's Missing Semester now teaches coding agents. Right after Git and debugging.
MIT just released the 2026 edition of The Missing Semester, and it now includes Coding Agents.
The entire course is free, with lecture notes, exercises, and YouTube videos.
It's a great complement to learning how to code. It covers the practical tools and skills that programming courses often skip.
It starts with Shell, Git, debugging, and profiling, then moves into shipping software, code quality, and AI coding tools like Claude Code, Codex, MCP, and Skills.
Definitely worth checking out if you're a developer.
1
37
Claude Code cloud sessions now set up your repo env on their own. Keys stay hidden from Claude.
We've made it easier to get your repo running in Claude Code cloud sessions on Pro, Max, and Ultra.
Claude figures out what dependencies, network access, and API keys it needs, then saves the environment for next time. API keys are saved securely, so Claude never sees them.
1
1
88
