Dan Two

Building AI-native products from Nepal. Founder of Project Parva. Exploring agents, startups, education, and human-centered AI.

[Dan Two @DanTwo11]

1/ I’ve been building Project Parva.

It started as a Nepali calendar API for BS/AD conversion, festivals, panchanga, muhurta, and sunrise calculations.

But the real problem is bigger:

Nepali time in software is messy.
https://t.co/4NxfDjgwsR

[Dan Two @DanTwo11]

@piggy1627 250$

[Dan Two @DanTwo11]

@amonyx "hi"

[Dan Two @DanTwo11]

@amonyx hi

[Dan Two @DanTwo11]

@trikcode I’m also building Project Parva for reliable Bikram Sambat/date logic (Nepal is ~57 years ahead of Gregorian and software gets it wrong), and Lekh, a Nepali keyboard for Mac/Windows. I want our language + calendar to survive modern software and AI.
https://t.co/4NxfDjgwsR

[Dan Two @DanTwo11]

@trikcode I'm building MirageSSD, a filesystem written from scratch in Rust
It started as a way to turn Google Drive into an actual Windows disk Now I'm taking it further streaming Genshin Impact's 150GB of assets on demand, without keeping the entire game installed
https://t.co/yCNvJ1nsyD

[Wise @trikcode]

I'm giving out a Devin Max subscription

Tell me what you building

[Dan Two @DanTwo11]

@Da7_Tech I'm building MirageSSD, filesystem written from scratch in Rust
It started as a way to turn Google Drive into an actual Windows disk. Now I'm taking it further: streaming Genshin Impact's 150GB of assets on demand, without keeping the entire game installed
https://t.co/yCNvJ1nsyD

[Cognition @cognition]

Introducing Dreaming: Across sessions, Devin builds a memory graph of how you like to work

At night Devin self-improves its memory to remove stale records and discover latent information

We are creating an OSS standard called Agent Memory Repo: https://t.co/b6qzEJsaeT

[Dan Two @DanTwo11]

@markfenner I'm a CS student from Nepal. I’m building Project Parva for reliable Bikram Sambat/date logic (Nepal is ~57 years ahead of Gregorian and software gets it wrong), and Lekh, a Nepali keyboard for Mac/Windows. I want our language + calendar to survive modern software and AI.

[Dan Two @DanTwo11]

@ElonMuskPD @elonmusk ???

[Dan Two @DanTwo11]

@LexnLin I'm a CS student from Nepal. I’m building Project Parva for reliable Bikram Sambat/date logic (Nepal is ~57 years ahead of Gregorian and software gets it wrong), and Lekh, a Nepali keyboard for Mac/Windows. I want our language + calendar to survive modern software and AI.

[Dan Two @DanTwo11]

@Da7_Tech I’m building Project Parva for reliable Bikram Sambat/date logic (Nepal is ~57 years ahead of Gregorian and software gets it wrong), and Lekh, a Nepali keyboard for Mac/Windows. I want our language + calendar to survive modern software and AI.
https://t.co/4NxfDjgwsR

[Dan Two @DanTwo11]

@Da7_Tech I’m building Project Parva for reliable Bikram Sambat/date logic (Nepal is ~57 years ahead of Gregorian and software gets it wrong), and Lekh, a Nepali keyboard for Mac/Windows. I want our language + calendar to survive modern software and AI.
https://t.co/4NxfDjgwsR

[Da7em @Da7_Tech]

Giving away a $200 Droid Max subscription.

Show me what you’re building and tell me how you’d use Droid to push it further.

Repo links definitely help.

Winner in 24 hours.

[Dan Two @DanTwo11]

I’m building Project Parva for reliable Bikram Sambat/date logic (Nepal is ~57 years ahead of Gregorian and software gets it wrong), and Lekh, a Nepali keyboard for Mac/Windows. I want our language + calendar to survive modern software and AI.

[Da7em @Da7_Tech]

Giving away a $200 Devin Max sub.

- SWE-2 Unlimited

- Opus 5.5 & Fable 5.1

- Sol 6 & Astra

- Top open-source models like Kimi K3

- Powerful agents with their own Mac, Linux, and Windows VMs

Drop what you're building below.

[Dan Two @DanTwo11]

@Da7_Tech I’m building Project Parva for reliable Bikram Sambat/date logic (Nepal is ~57 years ahead of Gregorian and software gets it wrong), and Lekh, a Nepali keyboard for Mac/Windows. I want our language + calendar to survive modern software and AI.

[Da7em @Da7_Tech]

Giving away a $200 Devin Max sub.

- SWE-2 Unlimited

- Opus 5.5 & Fable 5.1

- Sol 6 & Astra

- Top open-source models like Kimi K3

- Powerful agents with their own Mac, Linux, and Windows VMs

Drop what you're building below.

[Dan Two @DanTwo11]

@Handllex @dreamina_ai Dreamina

[Vox @Voxyz_ai]

One more thing:
want Codex to build good-looking pages without having to keep saying “make it look better”? Try these 3 design Skills together:

𝟭. 𝗜𝗺𝗽𝗲𝗰𝗰𝗮𝗯𝗹𝗲

Use it when the page is built, but something still feels off.

Too bland? Use bolder. Too cluttered? Use distill. Almost finished? Use polish to refine the details. It turns “make it look better” into specific design changes Codex can make.

https://t.co/w3i4Plx8Iw

𝟮. 𝟮𝟭𝘀𝘁 𝗗𝗲𝘀𝗶𝗴𝗻

This is a Skill I put together that gets Codex to look for components and interaction references on https://t.co/SUeM4ML7vz before building a page.

I’d suggest packaging your own go-to component library into a Skill, too. It doesn’t have to be https://t.co/SUeM4ML7vz.

Focus on the one or two sections that carry the page: a hero, a set of pricing cards, or a product showcase. Pick what fits, then adapt it to your brand, content, and existing project.

𝟯. 𝗨𝗫 𝗔𝘂𝗱𝗶𝘁

A good-looking screenshot isn’t enough. Have Codex open the browser and actually use the page.

Click buttons, fill out forms, switch to a mobile viewport, and complete the user journey. Find buttons that do nothing, confusing error messages, and steps where it’s unclear what to do next. Get reproduction steps and specific fixes.

If you can’t be bothered setting up Skills, start by adding this line to the end of your task:

“Make the best decision to improve UX, DX, and AX—without breaking existing functionality.”

Ask it to weigh the user experience, developer experience, and how easily the next agent can pick up the work.

[PrismML @PrismML]

Today, we’re announcing Ternary Bonsai 2 27B.

Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-precision counterpart while retaining 98.2% of its aggregate benchmark performance.

Two months after the first Bonsai 27B release, the biggest change is quality. The footprint remains 5.9 GB, but the gap to full precision has narrowed materially, with particularly strong gains in agentic coding, multimodal reasoning, and long-horizon tool use.

Ternary Bonsai 2 27B is available today under Apache 2.0.