I build games and apps with AI agents and post what actually happens. A few things I did recently:
1. Got glm in @cline to build a racing game where every texture and sound is generated, nothing downloaded.
2. I simulated an entire company to see where agents break.
3. Made a cel-shaded minecraft clone for my sister's birthday. One prompt, 3M+ tokens, ran for 4 hours.
4. And my agent saved my pc from a bsod that would have cost me 147$ for 😁
All of them are in replies 👇
more in hilights.
Replying to @dhruvtwt_
How do you turn your workflow into skill, by recording them / by just instructing step by step on what to do ?
13
Replying to @code_kartik
This type of culture , is threat to your work life balance and will wore you off even before you realise.
Glad you found this early and made the right choice.
Liked that you openly shared your experience and quote that moving blindly and moving fast is different
Not many do this , kudos 🎉
1
83
Replying to @DevanshuXi
I work with them , but need to transition to devops or rl researcher role.
Yup people are amazing but feel like growth is stagnant ( most eng are just next level ) and I am on my own to explore most of the things.
Though all bills are covered by them :)
229
Replying to @ai_for_success
The animations are cool , but still this model haven't fixed those rounded corners settings that comes with it by default.
10
Replying to @original_ngv
Kimi 3.1 was also able to do it. I remember it was not getting the event horizon so it wrote the mathematical equations for the calculation , found the right values and then work it's way to code the values in simulation webapp.
1
28
Replying to @harden_369741
I just a spec and progress doc that updates in realtime after each step is done!
1
1
36
Replying to @harden_369741
Go for it , fable 5.2 good for long running tasks and off context loading
24
Replying to @harden_369741
Well that's what fable 5.2 just did. I guess model on next level with the outputs I am getting during my test.
Till now only simple tests done, time to level up the task.
1
26
Replying to @TheVixhal
Long overdue for higher / elite class.
Asked fable to build its own launching page , no context apart from colours.
Result: teapawt.net/devloperhs/status/2119…
Claude Opus 5.2 just built myself a landing page, with no specific instructions.
Just asked fable to "build me a launch page for fable 5.2 following claude official colours"
It planned everything, researched all the details on fable 5.2 and built me a the entire self contained html webpage & required assets , all within 7 minutes at cost of 8% usage.
Insane speed and optimised usage , somehow costing less than opus 5.5
1
920
Replying to @harden_369741
Well it's just one sentence and fable handled it all - planning, researching , validating and then building.
Only instruction I gave it was to follow the anthropic colors.
Best part it understood what I wanted and followed through till end.
As per my tests , model is good for long running and robotics related task , yet to try other tasks too.
2
2
91
Replying to @nidhisinghattri
Strangely enough claude fable 5.2 lost to gemini carbon at automation bench.
Hope this is not real and just a llm hallucination failing at that task, else need to be studied.
1
1
45
Replying to @TheVixhal
Robotics and long running related tasks got a major leap with this model. What all you explored and found model to be good at ?
593

