
building @buildful_ai ⟡ swe @bug0inc talking ai, mostly
Bangalore, India
Joined March 2024
- Tweets5.1K
- Following656
- Followers1K
- Likes32.1K
Oh boy, I can’t believe I’ve spent 2 days on one feature, just iterating on feedback from Astra 6, and now Astra 6.2 since today.
It really made me realize how easy it is for humans to miss edge cases that these LLMs catch.
Anyway, it feels like I’m stuck in an endless feedback loop haha
2
7
201
Tried Astra 6.2 on a few 3D tasks. It's definitely token-efficient, but honestly it's not even close to Opus 5.5
1
3
99
I've been running Hy4 Flash in @buildful_ai for a bunch of random tasks
and I can’t believe how much cheaper it is than DeepSeek V4.1 flash, wild!
⚡Meet Hy4 flash, the cheapest model for everyday productivity. Matches Claude Haiku 5.5 (high) on daily work (human blind tests), yet 18x task cost reduction. API pricing (per 1M tokens): $0.003 cached · $0.070 input · $0.281 output. 🔗:hy.tencent.ai/research/hy4-f…
2
2
215
Ankit retweeted
your job as a software engineer in 2026 is to scroll twitter for useful things to send to your agent
you can now test Artifacts repos locally!
- create, fork & import repos with wrangler dev
- clone & push without impacting what's in production
- repo events (repo.forked) can trigger your workflows locally, so you can test them before you deploy
big shoutout to @leostera for shipping this!
no blood bags from mystic falls this time (tvd people, iykyk🩸)
so cranberry juice and raspberry cheesecake it is for friday night
2
10
238
Ankit retweeted
System design is not important anymore - if you believe this, just wait until your 2-hour agent run fails at step 95 of 100 :) I hope it does not happen, but it actually might.
Agentic apps have two classes: short-running and long-running. When you are building short agents, a simple retry loop is enough. Each LLM call is isolated, cheap, and stateless. Fail, retry, done.
But retrying a long-running agent spanning hours is expensive in API costs, tool calls, and wall clock time, and retries can also have side effects like resending notifications. Some failures that a long-running agent might hit in production are:
- LLM provider rate limiting
- Network timeouts for downstream calls
- Pod eviction due to OOM kills mid-run
- Pod rotation during deployment
- Context window overflow
- Human-in-the-loop pauses for days
Notice how most of these are not AI problems. They are classic software engineering problems that are showing up in a new system.
This is where we need checkpointing, idempotency, durable event logs, and resumable workflows. These are backend engineering fundamentals where we built robust, fault-tolerant systems by applying hundreds of patterns.
Good software engineering practices do not go out of fashion. Because someday, you will ship your "tutorial" to production. That is when system design suddenly matters again.
Fundamentals remain fundamentals, even when the abstraction layer changes.
This is the exact reason why I love using @buildful_ai
so that i don’t have to deal with this
Ankit retweeted
The code I’m merging now is probably the safest and most correct code I’ve ever written, but man it sucks to get endless feedback from LLMs. These things can always find another thing to complain about more than any human would ever subject me to 😅
if you haven't tried @buildful_ai, give it a shot.
i bet you're gonna love doing cloudmaxing with it
Have been using @buildful_ai for about a month, and I must say, it's such a great and polished product!
Thanks @BytesWithAnkit for giving me early access to this, along with a discount coupon code hehe.
holy shit
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…
2
4
135
























