Yatharth ( AI native dev )

885 posts

Yatharth ( AI native dev ) banner
Yatharth ( AI native dev )

Yatharth ( AI native dev )

@Yatharth_L

Products builder not a coder

Remote Katılım Mart 2020
104 Takip Edilen20 Takipçiler
Yatharth ( AI native dev )
Just published new version of express-route-cache.js.org - Cache Studio ->unified cache dashboard inspired by prisma studio - Improved Docs - Improved stampede protection for distributed system - Hashed cache keys to reduce sizes - Memory Optimization - Fixed Known issues
Yatharth ( AI native dev ) tweet media
English
0
0
0
3
DROID
DROID@droidbuilds·
developers, which IDE genuinely has the potential to replace VS Code?
DROID tweet mediaDROID tweet media
English
355
17
580
1.2M
Aditya
Aditya@Aditya_181105·
Which windows laptop can handle this?
Aditya tweet media
English
68
5
161
12.4K
Yatharth ( AI native dev )
Google had the best IDE but no more as they removed it's core feature of managing agents & totally broke IDE. I think it's time to switch from @antigravity
English
0
0
0
12
Gemini CLI
Gemini CLI@geminicli·
Transitioning Gemini CLI users to Antigravity CLI We are unifying our efforts around a single harness and platform, Google Antigravity with four distinct surfaces: • Antigravity 2.0 • Antigravity CLI • Antigravity SDK • Antigravity IDE This will allow us to move faster and give you a streamlined experience wherever you do your best work. Rebuilt in Go for speed, Antigravity CLI is available today and brings robust multi-agent orchestration and asynchronous workflows to your terminal. Important things to know: 1. If you are using Gemini CLI through your Google one account (Google AI Pro or AI Ultra) or through Gemini Code Assist for individuals (free offering) we will be helping you migrate your workflows over the next 30 days. 2. No action required for Enterprise users. Enterprise plans and API keys will continue to be supported in Gemini CLI. Read the full details in our blog post → goo.gle/4eWkUgK
English
244
592
4.4K
539.1K
Brian Johnson
Brian Johnson@_brian_johnson·
@Yatharth_L Same. Cursor is still the fast editing surface, but Codex is better when I want a second agent chewing on a scoped task.
English
1
0
1
19
Yatharth ( AI native dev )
Yatharth ( AI native dev )@Yatharth_L·
I used Claude code but hate its limit 😭. Now used gemini cli it's 🔥. Used all day fixing major issues but still 50% usage .
English
1
0
0
101
Yatharth ( AI native dev )
Yatharth ( AI native dev )@Yatharth_L·
Found critical bugs 🐛 .... Fixed most of them . I need to refactor the UI. Honestly product is great but UI is too mordern tech or web3 inspired.
English
0
0
0
2
Brian Johnson
Brian Johnson@_brian_johnson·
@Yatharth_L Gemini’s free-tier headroom is nice, but the tradeoff is usually workflow fit. I’d still keep Claude for planning/review and use Gemini for broad cleanup passes.
English
1
0
1
56
Yatharth ( AI native dev )
Yatharth ( AI native dev )@Yatharth_L·
@alexabelonix Totally agree, Last year I built an interview app that cost 5$ per round no student can afford to pay. I had the product but I realised the audience was wrong and dropped the idea . Now working on the same but for HR MVP is ready but fixing 🪲
English
0
0
0
41
Alexa Web3 (e/acc)
Alexa Web3 (e/acc)@alexabelonix·
Failure is not proof you should quit. It is data. It tells you: the offer was unclear the audience was wrong the timing was bad the system was weak the assumption was false Use the lesson. Change the approach. Keep going. Failure only becomes final when you stop learning from it.
English
38
5
76
1.3K
Cas.Fyn
Cas.Fyn@FynCas·
Claude + MakeUGC + Veo 3 = $65,065 Launch 200+ ads/day straight from your laptop. No creators No product shoots No $10K/month agencies Recreate top-performing competitor ads—the ethical way. Drop in their ad → choose an avatar → generate high-converting variations. Comment “Claude” and I’ll send the full setup + step-by-step playbook. (must be following)
English
163
18
243
22.6K
Arun
Arun@hiarun02·
> NO Claude > NO Codex > NO Cursor > NO Copilot Just skill. Can you still ship?
Arun tweet media
English
232
7
273
22.7K
Yatharth ( AI native dev )
Yatharth ( AI native dev )@Yatharth_L·
@romaindewolff I have created multiple doc pipelines for healthcare org handling invoices, lab scan, prescription, insurance & even discharge summary. This was also a crazy scale of 1 million users.
English
0
0
1
9
Yatharth ( AI native dev )
Yatharth ( AI native dev )@Yatharth_L·
@romaindewolff I totally agree that document processing on the server is a nightmare. U can try some edge ai solution that does orc on the client side similar to google. Also maybe you are zipping docs on the server it's huge load instead save onto S3 and serve from there in email.
English
2
0
1
68
Romain de Wolff
Romain de Wolff@romaindewolff·
I almost killed my company on Friday. $90,000. One Azure bill. Gone. Let me tell you what happened because I think founders need to hear this. We built an amazing document intelligence system at Whisperit. It analyzes our customers' files: PDFs, Word docs, scanned documents, using OCR. It works beautifully and user love it. But we had a bug. A small email with a zip file. Inside the zip, a PDF. Some weird edge case that created an infinite loop in our code. The virtual machine would crash, restart, and try to reprocess the same document. Again. And again. And again. We pay more than one cent per page processed. You can imagine what happened next. I saw the graph and my stomach dropped. An exponential spike. The kind of curve you want to see on your revenue chart (!!) not your cloud bill. The forecast for next month said $400,000+. I thought: this must be a mistake. Emergency 🚨. Check everything. It wasn't a mistake. The worst part? We had a warning. Back in November we had a $25K unusual spike. We fixed it. Added upload limits. I thought we were safe. But I never set a spending cap on Azure. Never set up alerts for unusual usage. I knew I should. I just didn't do it. I went through every stage: Denial → "this can't be right" Anger → screaming at myself Shame → feeling small, really small Tears → first time in a long time I cried that evening. Not because of the money, because I imagined having to close Whisperit. My team. Everything we built. Gone because of one missing setting and my stupidity. The week had been incredible. New version shipping. Lots of new users. Sales going well. Migration going well. Growing the team responsibly. And then Friday hit like a truck. Remember my last post about mistakes? Yeah. We're still making them. Bigger ones. $90,000 is the price of a NICE car. Paid for a bug and a missing checkbox. Here's what I'm doing RIGHT NOW so this never happens again: 1. Hard spending limits on every cloud service — no exceptions 2. Alerts at 50%, 80%, 100% of expected spend 3. Circuit breakers in our processing pipeline — if a document fails 3 times, it stops 4. Weekly cloud cost review — not monthly, weekly 5. Every API endpoint gets a budget ceiling If you're a founder reading this: Go set your spending limits. Today. Right now. Before your next meeting. Before your next coffee. It takes 10 minutes and it could save your company. We move fast. That's our superpower. But speed without guardrails is a bomb with a timer. I know what doesn't kill you makes you stronger. I really hope this one doesn't kill me. Still standing. Barely. Building. 🚀
Romain de Wolff tweet media
English
109
34
344
56.9K