Tina Park

AI Engineer & Developer Advocate | Building AI products in public | React, Next.js, GenAI

[Tina Park @devtinapark]

Building Spoken Kitchen to save family recipes

I tested @OpenAI GPT-4o vs @DeepgramAI Nova-3 for transcribing English-Korean in a noisy kitchen.

GPT-4o was more accurate.
Nova-3 was faster & cheaper.

For Spoken Kitchen, accuracy won.

https://t.co/LCJPmtz9NB

#BuildInPublic

[Tina Park @devtinapark]

@kevton_ @OpenAI @DeepgramAI Didn’t know this one — thanks! Looks like it supports auto language detection, which is my main requirement, and it’s actually cheaper than what I tested. Have you tried it on noisy or non-English audio? Tempted to add it as round 2.

[Tina Park @devtinapark]

I benchmarked @OpenAI GPT-4o-transcribe vs @DeepgramAI Nova-3 on real Korean/English audio for https://t.co/3YUqtdbtkh.

🏆 GPT-4o-transcribe
• Better accuracy (CER 0.053 vs 0.077)
• More robust to noise
⚡ Nova-3
• ~2× faster
• ~13% cheaper

Results 👇

[ClaudeDevs @ClaudeDevs]

We've reset 5-hour and weekly rate limits for all users on Pro and Max plans.

We fixed an issue that caused some Claude Code sessions to spawn excessive parallel subagents, burning through usage faster than expected.

[Tina Park @devtinapark]

📖 Full write-up:
https://t.co/r3V18ByfHg
💻 Code + dataset:
https://t.co/DBqjai2CIj

[Tina Park @devtinapark]

Another night at Visible Builders OC 🚀

People come for the first time curious.
They come back because everyone is actually building.

No talk. Just shipping.

Grateful for the community.

Let's #buildinpublic

[Matt @m13v_]

the '5-word prompt triggered a 5h lockout' thing is usually the rolling window already near full, the prompt just tipped it. you never saw it coming because the bar's hidden. claude-meter reads anthropic's usage endpoint so the 5h window is visible before it locks https://t.co/WZovrl4JO3

[Tina Park @devtinapark]

@m13v_ Spot on. The lack of visibility into the rolling limit is a huge pain for heavy CLI sessions. Managing token context directly through the API layer removes a lot of that unpredictability.
Thanks for sharing the tool! 🙌

[Tina Park @devtinapark]

Nothing kills flow state faster than hitting a daily AI rate limit right in the middle of a heavy development sprint. 😩

If you're using Claude Code, a short 5-word prompt can trigger an unexpected 5-hour lockout.

Here is why it happens and how to fix it. 👇 (1/5)

[Tina Park @devtinapark]

🧹 3. Flush Context: Run ⁠/clear⁠ after every sub-task to drop rolling history tax back to zero.

I open-sourced the config framework so you can stop bleeding tokens and stay in your zone.

Full breakdown & repo here:
🔗 https://t.co/gF29AkPVbd
📦 https://t.co/298g4FuhO3 (5/5)

[Tina Park @devtinapark]

🛡️ 1. Token Firewall: Use ⁠.claude/settings.json⁠ to hard-block tools from crawling heavy dependency paths.
🧠 2. Conceptual Split: Brainstorm on DeepSeek R1 via @OpenRouter ($0). Use CLI only for execution to get @Anthropic's 90% prompt caching discount. (4/5)

[Tina Park @devtinapark]

My Korean mom never writes her recipes down.

So I built an AI that turns her voice into written recipes 💛

Now supporting Korean, Spanish, and Chinese so more families can preserve theirs.

Join waitlist: https://t.co/3YUqtdbtkh

[Tina Park @devtinapark]

Full writeup with the three failure modes + the free prompt:

https://t.co/Qd8UhcQJG1

[Tina Park @devtinapark]

I vibe-coded my hackathon project in a day. It looked done.

Then I sat down to plan the path to production and realized I'd be unwinding decisions for months.

🧵

[Tina Park @devtinapark]

I packaged the interview process as a copy-pasteable prompt.

Paste it into any LLM. It runs a structured interview, pushes back on, and outputs a build spec at the end.

Plan 30–60 min. Link in reply below ↓

What's the failure mode you've hit most building with AI?

[Tina Park @devtinapark]

🚀 Just wrapped DeveloperWeek 2026 in San Jose!

Inspiring to connect with talented builders and kick off my move to the Bay Area. Excited to apply these insights to building at the intersection of AI, product & community.

#DeveloperWeek #AI #TechCommunity