
building @buildful_ai ⟡ swe @bug0inc talking ai, mostly
Bangalore, India
Joined March 2024
- Tweets5.1K
- Following656
- Followers1K
- Likes32.1K
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!
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.
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 😅
Ankit retweeted
I'm in my churn era.
Charging me too much? I'll slop up a replacement.
Bad MCP server? I'm sure Claude can make a better one.
Slow to respond? Claude isn't.
Missing important features? You know what's a prompt away...
Seriously, if you aren't keeping up with the needs of your fastest moving customers, you are going to be replaced.
Ankit retweeted
I’m in love with this sentence:
“One of the most underrated skills you can learn is the ability to ignore your mood and stick with the plan.”
Ankit retweeted
"AI is just matrix multiplication" is the new "emotions are just chemicals in the brain"
Ankit retweeted
the fact that this was written … last year … breaks my brain
There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper so I barely even touch the keyboard. I ask for the dumbest things like "decrease the padding on the sidebar by half" because I'm too lazy to find it. I "Accept All" always, I don't read the diffs anymore. When I get error messages I just copy paste them in with no comment, usually that fixes it. The code grows beyond my usual comprehension, I'd have to really read through it for a while. Sometimes the LLMs can't fix a bug so I just work around it or ask for random changes until it goes away. It's not too bad for throwaway weekend projects, but still quite amusing. I'm building a project or webapp, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works.
The age of agents is going to be amazing for most programmers, but it'll be hard times for the cantankerous ones.
Specialized knowledge and rare skills will no longer offer immunity for those who are a pain to work with.
Best learn some basic people skills.
Ankit retweeted
Own your intelligence.
Anyone that opposes this has something to sell you (perhaps your own intelligence back to you.)
Local models need to continue proliferating. The “absolute unit” massive models may be out of reach for now locally, so your best option is to, indeed, keep your options open. Own your harness, data, connections, runtime: your agents. Embrace open source.
Ankit retweeted
1/ Excited to announce our new company Particle
This is our first step in a series of models focused on developers.
With particle-1, we focused on token efficiency and managed to keep parity in performance while using ~45% fewer tokens.
Live now: particle.ai
Ankit retweeted
shipped a few things in Buildful this week
gpt-6.1 terra and kimi k3.1 pro are in the model picker now… plus a highspeed kimi w 1M context
also added a Buildful Pass, $30/mo gets u $80 of usage on glm, deepseek, minimax and kimi. its an add-on for pro and team
buildful.ai

ALT A dark banner with the headline "New models this week." Below it, three tiles. The large top tile shows the OpenAI logo and "GPT-6.1 Terra". The bottom left tile is blue, with the Kimi logo and "Kimi K3.1 Pro". The bottom right tile shows "1M token context" above "Kimi K3.1 Pro Highspeed".

ALT A dark banner with the headline "And a new Buildful Pass." The top tile shows a wallet labelled "Buildful Pass" holding four model cards: Kimi K3, GLM 5.3 Flash, DeepSeek V4.1 Flash and MiniMax M3.1 Flash. Below it, one tile reads "Model usage: $80 on the four Pass models", and the other reads "You pay $30 a month, on Pro and Team".
Ankit retweeted
A benchmark showing Haiku 5.5 beating DeepSeek v4.1 Flash 1017 is a joke not a benchmark lol
Ankit retweeted
No human will ever write code better than LLMs. Accept this fact, stop pretending, and move on.
Ankit retweeted
shipped close to 300 features + bug fixes already. still a lot more to go.
buildful uses open-weight models for most of the work, qa as leverage, and frontier models only when needed.
nothing to install. nothing to download.
roughly 1/10th the monthly cost.
Ankit retweeted
or skip the 4x RTX Pro 6000s
picked deepseek-v4.1-flash-1017 in Buildful, asked for a habit tracker, closed the laptop
came back to a PR it already tested in a real browser
no five-figure GPU rig. zero GPUs on our desk
























