
18 y/o developer, built a thing which got 15k+ users, contributor @t3dotcodes
Joined January 2026
- Tweets1.4K
- Following159
- Followers342
- Likes3.8K
Utkarsh retweeted
We got me performing humiliation rituals before GTA 6, but if anyone is hiring or knows anyone that is, my DMs are open
Eng/Dev Rel/content/fake personality hire + willing to relocate
Would really appreciate any pointers as well 🫡
Utkarsh retweeted
Zen is getting DRM support! Very soon you'll be able to watch and listen to your favourite streaming services like Netflix or Spotify directly in Zen!
We know this has been your most anticipated feature, and we're thrilled to finally deliver on it!
DRM support
Utkarsh retweeted
Introducing AA+
A Chrome extension that turns Artificial Analysis into an user-oriented analytics tool
It has:
- Subsidization data from Priors
- More customizability
- Radar charts to show strengths and weaknesses of different models
And most importantly, dark mode!
Utkarsh retweeted
T3 Code 2.3 is out on iOS and Android 📱
🎙️ Talk to your agents
• On-device dictation, now on Android as well
• Or transcribe on your own computer through a paired environment
• Or opt into cloud dictation with any model from OpenAI, Grok or OpenRouter
💬 In the app
• @-mention a model to name it for the agent
• /side starts a side chat without leaving the thread
• Subagent approvals show up in the parent thread
• Mermaid diagrams and math render like on the web
• Long-press an image to save it
⚡ Faster sync and reconnects, even on bad Wi-Fi, and threads open faster
📐 New workspace layout system with better support for different poses across phones, foldables, tablets both on Android and iOS
Get it today from the App Store or Google Play
Utkarsh retweeted
.@jullerino is joining Effect Days this year! 🇮🇹
Julius is one of the developers behind @t3dotcodes, an open-source interface for AI coding agents.
Utkarsh retweeted
Replying to @jullerino @t3dotcodes
Thank you @UtkarshUsername for doing the grunt work for this feature!
Today we’re releasing Sarvam Prism, a System One model built on Sarvam 105B for fast, accurate decisions across enterprise workflows.
It scores 71.8 with a median response time of 44 milliseconds, the highest average score among decision models that respond in under 100 milliseconds.
Utkarsh retweeted
Made a thing: @t3dotcodes widget for Noctalia. I find it handy, maybe you will too :)
github.com/piexelated/agent-…
Utkarsh retweeted
At this point the reaction is:
Bad software: I'll just build my own.
Good software: I'd rather use this and let it get even better than build my own.
Utkarsh retweeted
So apparently @t3dotcodes was the fifth most engaged open source project this year. Pretty cool 🙌
another thing that came to mind right now, is anyone using any TUI DB manager such as LazySQL, Rainfrog, etc..
if you do, I would appreciate feedback on what you like, don't like, think is missing, think is bloat, etc..
i'm making an actual good TUI database manager. i don't think any of the ones i tried either work as well or have all the features i want. still very early in dev, but if you wanna follow along; github.com/0x4bs3nt/pond
Utkarsh retweeted
T3 Code originally was such a light wrapper that your agent didn't even know what it was.
With Orchestrator V2 (harnesses can call each other), we had to fully overhaul this.
With built-in browser, device manager for mobile, subagents/delegates, "send to other thread", html inline visualizations, etc...it got a bit bloated.
Biggest issue first: we listed all the models available to use for subagents. For most people, didn't matter. For OpenCode and Pi users with literally hundreds of models? Real bad. Fixed now, sorry!
I knew I had to go further. The tool schema was...too big. Far too big. So I took that as a challenge.
I created an insane eval. Spent like a week on it. Took all the ways my agents used these tools in my day to day work, as well as all the failures and rage moments I had, and turned them into a generic eval I can run to test changes to the tools and their descriptions.
I expected to mostly focus on trimming the descriptions, but I was AMAZED how many error cases I found. My eval had over 80 cases, and Opus failed over half of them.
As you can guess, the hill climb began soon after :)
Step 1: Bench Sonnet 5.5
Step 2: Keep adjusting tool descriptions until Sonnet 5.5 gets perfect score
Step 3: Add Sol into tests, do the same
Step 4: Add Opus, do the same
Step 5: merge it (because error rates are better now)
Step 6: new thread, tell Opus to trim until it uses 50% less context without any regressions in the eval
Step 7: ship it
This was super fun. Amazed at how many problems you can kinda just turn into evals and then do shit like this. The "shape" of this was not far from the UI overhaul hill climb. Surreal you can just, like, do this.
Utkarsh retweeted
Fwiw, I think the "realistic pareto line" right now is:
- GPT-6 Luna
- GPT-6.1 Sol
- Opus 5.5
Utkarsh retweeted
T3 Code Nightly users who just updated: I'm sorry. We shipped a broken one.
Revert to stable for now. Stay there if you want fewer breaks (probably for the best). New build will be live in 10 or so mins to fix this.
Utkarsh retweeted
We've started adding some compaction to the t3 database, but old databases does not release the freed up space to the OS.
You can run `t3 doctor` to rebuild the database which will allow future compactions to release freed up space to the OS automatically. Also suggests you to clean up the older v1 database when you've made sure v2 works for you and you don't need to roll back.





















