Niranjan (@praneos) header
Niranjan (@praneos) profile picture

Building agentic AI systems & tools. From prototype to production 🚀 DriftStop 🎯 → https://teapaw.org/t.co/HPA2Ws5sG3 Pi Fortress 🛡️ → https://teapaw.org/t.co/RWEFPEKkqy

Bangalore, India
Joined August 2026
Photo by Niranjan (@praneos)Photo by Niranjan (@praneos)Photo by Niranjan (@praneos)Photo by Niranjan (@praneos)Photo by Niranjan (@praneos)Photo by Niranjan (@praneos)Photo by Niranjan (@praneos)Photo by Niranjan (@praneos)Photo by Niranjan (@praneos)Photo by Niranjan (@praneos)
ahh moment
Told ya bro's it's going to free fall lol
13
384
14,158
This is hilarious. Also the AI interviewers face gets angrier and angrier as the interview goes on.
183
245
35
3,212
643,672
It’s all about AI dating coaches these days
dating in sf. we are cooked
34
101
20
1,425
139,681
I suspect we're entering the temporary golden age of what a regular dude can do with AI. Enjoy it while it lasts.
96
173
38
3,577
81,052
Claude keeps hitting new lows every day!
1
4
3,260
You have to adjust "subscription value" by model efficiency to see how many tasks that gets you. And then you have to also adjust that for success rate. Because if you don't, then using Sol on Low will just look so much better than Sol on High, because it gets more tasks done. This shows the $20 plans, but OpenAI has twice the subsidization on their higher plans, so they look better there.
22
5
1
328
18,881
Niranjan retweeted
Someone spent 20k on AirGradient sensor to prove that government is lying the public
59
591
21
8,683
668,246
Looking at the $GOOG stock price, would they come up with voluntary exit package soon? 🤔
37
CEO of snowflake joining Elon in calling top When your competitor is over levered and you’re under levered in a bull market, your goal is to trigger a bank run This way you tank the over levered players and look like a genius catching their customers on their way down Bold
1/16 the ai industry is making an unusual bet: buy compute for years, sell intelligence by the token. banks, commodity merchants, airlines, utilities and cloud providers each explain a different part of the risk.
48
116
7
2,668
474,746
M5 Ultra 🥲
🤖 Made with AI
1
153
typed "plau" and opus 5.5 inferred it as "okay". right hand shifted by 1 key. :D would deepseek 4.1 also handle it?
10
Niranjan retweeted
Hey @Microsoft , I will give you an idea to do layoffs. 1. Open youtube... Search "Day in life of a Microsoft Engineer". 2. You will get list of people who only eat but do not work in office. 3. Layoff them
563
2,501
319
39,788
4,029,999
Tried the ASD-STE100 format for summarizing docs. So pleasant to read! 📝✨ It genuinely feels like it was written by ASD people, for ASD people 👌 Same message. Two versions. 👀 Complex writing on the left. ASD-STE100 on the right. 📝 Which one do you finish reading? 🤔 examples in thread 👇
1
31
Technical documentation (software install) 💻 Complex: 46 words, 1 sentence. ❌ ASD-STE100: 31 words, 3 short sentences. ✅
1
21
Research paper (results summary) 📊 Complex version buries the result. 😵 ASD-STE100 states the result first, then the limit. 🎯
2
Niranjan retweeted
51
482
49
4,784
167,463
Niranjan retweeted
Replying to @wanxubo
claude pro订阅的opus5.5换算使用单价和deepseek v4.1 flash其实是一样的,更何况你还要搭配claude code使用,这进一步提高了claude的token效率使得deepseek相比之下看起来性价比更低了。 我是这样想的
5
3
1
51
30,515
Someone please rewrite the rust compiler in assembler. The compile times are killing me.
116
42
22
1,898
132,739