Bapusaheb Patil

Design Engineering x Brand Design for Products ✨
5x Award-Winning Designer 🏆
Art Gallery: 🖼

I post about design, dev and AI.

[Bapusaheb Patil @baps_patil]

Announcing Lexborn, a language learning web app to help you speak with confidence!

Using @OpenAI's latest GPT-Realtime-2 and GPT-Realtime-Translate APIs, it provides daily real-time voice chats with AI partners who remember your last conversation, gently fix mistakes, and meet you at your level.

No tutor schedule.

[Bapusaheb Patil @baps_patil]

Sign up today and regret it tomorrow.

https://t.co/Lj0Ud3Ozqs

(.org domain because being cringe should be non-profitable)

[Bapusaheb Patil @baps_patil]

Introducing Cringe.

A dating app designed to keep you single.

Every other app optimizes for matches. Cringe optimizes against them, and it says so out loud.

[Bapusaheb Patil @baps_patil]

Yoooo @ClaudeDevs, am I using /goal and /batch together correctly?

[Bapusaheb Patil @baps_patil]

/goal is the best thing to come out of Claude Code since Claude Code.

[Bapusaheb Patil @baps_patil]

Sign up for the waitlist here:
https://t.co/WMEZpdUjcw

[Bapusaheb Patil @baps_patil]

Announcing Lexborn, a language learning web app to help you speak with confidence!

Using @OpenAI's latest GPT-Realtime-2 and GPT-Realtime-Translate APIs, it provides daily real-time voice chats with AI partners who remember your last conversation, gently fix mistakes, and meet you at your level.

No tutor schedule.

[Bapusaheb Patil @baps_patil]

Here's why it exists and how I made it...

(P.S. It uses @nextjs 16 for frontend + @convex for backend + @polar_sh for payments + @clerk for auth)

[Bapusaheb Patil @baps_patil]

View it here: https://t.co/fxPy7C08Ka

Submit your @tan_stack project here: https://t.co/U4FPgP5VhI

[Bapusaheb Patil @baps_patil]

My retro OS web app, BapsOS, is now live on the @tan_stack showcase!

Thank you, @tannerlinsley.

[Bapusaheb Patil @baps_patil]

@rohanpdofficial @Cloudflare @CloudflareDev Great work! It worked like magic on my Next.js projects.

For my TanStack Start projects, getting this error, and this is the latest Cloudflare setup for TanStack Start according to their docs:

[Bapusaheb Patil @baps_patil]

Year in Code. 2025. ⁦@cursor_ai⁩

[Bapusaheb Patil @baps_patil]

@jamesacowling @convex Checking that was the first thing I did, which is why I asked here too. Because I got this error on Sentry, I'm guessing internal server errors have something to do with degradation issues?

[Bapusaheb Patil @baps_patil]

@ericzakariasson Grok 4.1 and Grok 4.1 Fast in Cursor. Let's go!

[Bapusaheb Patil @baps_patil]

@cursor_ai When are we seeing Grok 4.1 Fast in the IDE?

[Bapusaheb Patil @baps_patil]

This was a few hours before the official announcement!

[Bapusaheb Patil @baps_patil]

Just tried the Gemini 3 Pro Preview model available in Cursor, if you add gemini-3-pro-preview as a custom model.

I was curious about it's pricing, so I gave it a few tasks.

The pricing, at least effectively in @cursor_ai, if not the API pricing directly, seems likely to be:
- $3 per 1M input tokens
- $15 per 1M output tokens
- $0.30 per 1M cache read

[Bapusaheb Patil @baps_patil]

@JamKo_Ams @cursor_ai My sample size is too small, but it felt on part with GPT-5.1 Codex. Could be a different story after I use it for a few days.

[Bapusaheb Patil @baps_patil]

@jediahkatz Curious to know this from someone building Cursor:

Do you personally use GPT 5.1 Codex (High), Codex (Medium), Codex Mini (High) and Codex Mini (Medium)? If yes, what are your use cases and how has your experience been?

[Bapusaheb Patil @baps_patil]

Agentic use for coding. In @cursor_ai,
1. sometimes it doesn't finish the task at hand when other models do, when the context length exceeds just ~100K tokens.
2. it throws random <xai> output tags on the 3rd or 4th user message.

Otherwise, it is really fast, and is really smart in the official @grok app. I would love to have Grok 4 Fast be my default model in @cursor_ai!