Generalist...

👀
Joined August 2019
Built a MCP Server that allows you talk with your database (SQL) using natural language Tested it with dummy data and the result was pretty good Database hosted on Railway MCP server written in Typescript 😔and deployed on Cloudflare Link to the repo in the comments 🙃
It works now The problem was on the client side not the server 🥲 Repo soon
18
20
3
192
20,183
🎶 I'm not his bitch no more I'm not your bitch no more 🎶 Ayyyy
77
Thank you minimax/minimax-m3.1-flash:free Till the next free model...
3.6k websites created and deployed in ~5 days 7b tokens burnt model: space-bunny-alpha Waiting for the next stealth model release to run this factory again 😂
1
1
108
Link below 👇👇
"Want" has a dual meaning... it means both to desire and to lack
2
3
177
Techa retweeted
Every time someone says "ai can't write good code", I know that they can't write good code.
275
124
27
3,585
110,404
It is impossible to have it all. but even if you do have it all in the conventional sense of that word There's something you'd still lack, which is lack... itself
1
2
124
**did have it all
10
Techa retweeted
Now open-source Link in the comments
Deployed my own scrapers on apify
4
4
22
636
Nicki and Cardi hosting space at the same time?? 👀😂😂
3
164
Techa retweeted
ما احب لما اغير رأيي بعد ما اقرأ الكومنتس احس ماعندي شخصية
259
10,145
268
87,109
911,579
The feeling you get after playing a piece by ear >>>>
3
193
It does I burn out every day
Maybe AI is also accelerating burnout with all this context switching
133
Techa retweeted
I asked Claude Code to make a new GTA: San Andreas mission where CJ has to vibe code a startup and then raise money from investors in SF
256
1,293
300
22,199
1,157,658
Wtf happened to river at the end 😢 #SlowHorses
1
1
1,355
My Job search agent suggested roles from cohere Microsoft and Google I first laugh 😂😂
5
11
548
Today we’re releasing Underdog Bark 3.0, the #1 frontier speech model It's a tiny 163 MB download as accurate as NVIDIA’s Parakeet (15x bigger). It beats OpenAI's Whisper large-v3 (57x bigger) It's fast- transcribes 1 min of audio in <0.25s on a Macbook. On recorded meetings (AMI), Bark 3.0 gets 7.82% of words wrong. Parakeet gets 9.42%. OpenAI's Whisper large-v3 gets 13.63% error rate Bark runs on both your Laptop & Phone. It’s free and open source under CC-BY 4.0 Try private on-device meeting notes & dictation, powered by Bark, in Underdog today: underdog.ai/bark
242
270
63
4,468
224,890
If you are not willing to disappoint anyone, you are going to disappoint yourself.
3
19
365
Techa retweeted
حسابي بتويتر لإني مهتمة بكل المواضيع
287
70,854
1,069
245,254
2,131,660