nutanc

Chaitanya, CTO Co Founder Ozonetel

[nutanc @nutanc]

Ok, today, I will be posting multiple videos of OpenAI GPT demos I built. All of them will be MIND BLOWINGLY GOOD. Because they are demos :)
But seriously, OpenAI is good for prototypes. Follow this thread if interested. At the med of the day I will do an analysis.

[nutanc @nutanc]

Costlier than Jev but improved accuracy for 5-6 points for our use cases.

[Sundar Pichai @sundarpichai]

Today we’re launching the Gemini Decisions API, powered by our new Gemini Decision 1 model in @GoogleAIStudio.

Instead of generating text token by token, it’s built for closed-set choices scoring up to 1,000 questions across text, images, audio, video + PDFs in a single pass. A few details:

- 3 decision types: yes/no, multiple choice (up to 255 options) + rubric scoring
- $0.10 / 1M input tokens with $0 billed for output tokens (~5x cheaper than Flash-Lite)
- leads on several benchmark evals with lowest calibration error

Google teams are already building with it, below is a look at Stitch Rapid designing a full product flow in seconds (1x speed)

[nutanc @nutanc]

Well, this is how you drive up a 10 billion loss in an year. The idea is that you recover those losses by taking over the jobs later. It will work to some extent. But not to the extent Anthropic wants.
BTW, who is going to fund this attack on the job losses? It's the American people baby :)
Anthropic is ready for the IPO.

[Tom Dunleavy @dunleavy89]

My friend runs one of the biggest woodworking businesses in the northeast. He was telling me the other day Anthropic offered him $1M just watch his team create cabinets. $1M! No other strings attached. Three months of watching employees virtually so they can model, learn and integrate it into Claude.

The rep said they were doing this with multiple firms across every industry.

All knowledge work will have every scenario and use case backed by experts 10k hours, in Claude within the next year or two.

Not a doomer but the "AI isn't going to drive job losses" is going to be so wrong it hurts.

[nutanc @nutanc]

@ponnappa We do Bisi bele bath with fried chicken bits.
We call it Bismillah bath.

[nutanc @nutanc]

@Hardik_Meisheri Simple no. Because they have not delivered so far?

[nutanc @nutanc]

Sarvam is not India's answer for a foundation model. Now, what do we do?

[nutanc @nutanc]

Temple done right. https://t.co/mLfZiyEgFg

[nutanc @nutanc]

Temple done right. https://t.co/mLfZiyEgFg

[nutanc @nutanc]

They didn't have to deal with the idiot amplification engine called social media.

[Vikram Sathaye @vikramsathaye]

My respect for Social Reformers of past has grown in multiples . It must have been so tough for them to convince society against Sati, Child marriage and women exploitation. We can’t convince people to stop firecrackers for their own lungs . Salute to them🫡

[nutanc @nutanc]

As I mentioned before and my other tweets, the problem is making sure we have quality faculty in the universities. Look at the research potential of one of the top engineering colleges in Telangana, JNTU CSE department. Some faculty, 100% publications are in low quality journals. The number of publications itself is fairly low to start with.

[Maheshwer Peri @maheshperi]

India is waging a war against its own researchers:

In Careers360’s Research Summit, Prof. Ram Gopal Rao, Vice Chancellor of BITS Pilani described India’s lack of investment in research beautifully. He said “India’s Higher Education is described as African Budgets, American ambitions, Russian methods, Chinese opacity and Indian Bureaucracy.
In the past decade, we have seen a slide in scientific temper and investments in research.
1. Non-NET fellowship are stuck at ₹8,000 a month since 2012, for 16,270 scholars in 45 central universities.
2. JRF stipend: In 2014, the JRF was Rs.25,000 per month. In 2019, it was revised to Rs.31m000. it is ₹37,000 PM. The hrowth hasn’t even kept pace with inflation and in real terms, it has FALLEN. IISc scholars even went on a hunger strike demanding an increase.
3. Maulana Azad fellowship: where more than 1,400 scholars have had stipends stalled since January 2025.
4. OBC fellowships: lists for three NET cycles in 2024-25 were held back, which the social justice ministry put down to insufficient funds.
5. INSPIRE: fellows have their stipends unpaid for 3 to 9 months. The schemes now under Vigyan Dhara fell 67.5% between 2016 and 2025.
6. KVPY: scrapped in 2022, after nearly two lakh students a year had taken its test.
7. JRF bottleneck: only 5,108 of 7,35,614 candidates (0.7%) got JRF in December 2025. Minister Sukanta Majumdar gave no year-wise data when asked.
8. The University of Hyderabad stopped Rohit Vemula’s ₹25,000 stipend in July 2015, and his last letter said he hadn’t been paid for seven months. He later committed suicide.
9. India’s R&D spending: fell from 0.82% of GDP in 2009-10 to 0.64% in 2020-21. PMRF spending was revised to ₹290 crore, less than half its ₹600 crore outlay.
10. SC fellowships: fell 61%, from 4,841 to 1,872, between 2020-21 and 2022-23.
If India indeed wants to be a Vishwa Guru, India should be investing in research, in creating quality Higher-Ed institutions. We cannot be cutting down on stipends, not paying our researchers, holding back payments, scrapping scholarships, not increasing fellowship amounts even to match inflation and still expect students to choose research.

[nutanc @nutanc]

This is just CSE JNTU.

[nutanc @nutanc]

A lot of inefficiency in India hides in plain sight because of the lack of transparency. Its like security through obscurity. Thats broken open now because of AI. What else can we break open? I let Claude loose on the research potential of JNTU. Results are shocking :)

[nutanc @nutanc]

As we can see, some faculty are getting by just publishing in obscure journals.

Disclaimer: This is based on public data and assumptions about the journal based on Beall's list, mass-publishing or unindexed venue.

[nutanc @nutanc]

Created a simulation to see how traffic could flow. Just moving the u turn a few 100 feet can have a big impact.
https://t.co/wCD4USRFnX

[nutanc @nutanc]

A possible alternative solution that @HYDTP can follow to reduce congestion through adjustment like they did for the KBR park. Move the U turn from near Nawaabs and have a traffic light near the AIG/Qmart. The traffic modelling suggests that it's much better(the layout didn't come properly, but text explains)
https://t.co/f59GwI2WDO

[nutanc @nutanc]

Yet another evidence point against "personalized" learning.

[PsikoBilim @Psikobilim_]

Öğretmenlerin %90'ının inandığı "öğrenme stilleri" teorisi yeni yapılan kontrollü deneyde yine çöktü:
Çocuğa "kendi stiline" (görsel/işitsel) uygun ders anlatmak hiçbir başarı artışı sağlamıyor. Asıl farkı yaratan, içeriği herkese hem sesli hem görsel sunmak.

[nutanc @nutanc]

These numbers matter a lot. We have clear proof with data. Just because of one u turn we are spending ₹7 lakhs per day on petrol. That's ₹7 lakhs per day on imports. We can save petrol like this instead of Ethanol. If we consider 10 junctions like this, it's around ₹1 crore per day or 30 crore per month. Every day we don't fix this we are losing ₹7 lakhs. And the fix is minimal. Just move the u turn a few hundred feet down or add a traffic light at the junction.(I will have to model this more I guess.)

[nutanc @nutanc]

There is a clear solution which can help thousands of commuters. And now we have real time live data. We can build more simulations. As it stands, below is the data. And we have a simulated solution. @HYDTP should not delay and implement quickly as 22,000 vehicle drivers are suffering everyday in the 3 hour slot. This translates to around ₹7.5 lakhs wasted on petrol everyday. ₹7.5 lakhs!!!!. Somebody please get this message across the Hyderabad traffic police. I can help more with simulations if needed.

[nutanc @nutanc]

@Hardik_Meisheri How? And why do you think that? Would love to understand the thought process.

[nutanc @nutanc]

@sudhakarudumula We can save ₹7 lakhs on petrol just solving one u turn near Nawaabs.
https://t.co/RgiqxQya1W

[nutanc @nutanc]

There is a clear solution which can help thousands of commuters. And now we have real time live data. We can build more simulations. As it stands, below is the data. And we have a simulated solution. @HYDTP should not delay and implement quickly as 22,000 vehicle drivers are suffering everyday in the 3 hour slot. This translates to around ₹7.5 lakhs wasted on petrol everyday. ₹7.5 lakhs!!!!. Somebody please get this message across the Hyderabad traffic police. I can help more with simulations if needed.

[nutanc @nutanc]

I think a lot of it depends on the person. I never loved the part of actually writing the code. So I always used scaffolding. But I lived solving problems using code. Agentic AI actually has made that part more fun as I don't need to fret about how to go about actually coding it. But I know enough of coding to guide the AI agent. And it's all fun.

[Ravi Mohan @ravi_mohan]

(OH on HN

"Don't get me wrong, being a Senior Agent Babysitter probably still beats flipping burgers or being a roofer (so it could be a lot worse) but agentic AI has really sucked a lot of the fun parts out of the job."

[nutanc @nutanc]

@prasanna_says And BTW, if bad publications is a criteria, then almost all the profs need to be fired ;)

[nutanc @nutanc]

We are actually stuck in a vortex which we cant seem to get out off. We need to fund more, but we need quality researchers whom we can fund. I personally have met 100s of researchers in and around the Hyderabad area. Among those, I would say only 2-3 were research worthy. I would not fund anyone else as it would be a waste of money.
So yes, we should do more research and we should fund more. But who do we fund? How do we get more research oriented people on the rolls?

[Maheshwer Peri @maheshperi]

India is waging a war against its own researchers:

In Careers360’s Research Summit, Prof. Ram Gopal Rao, Vice Chancellor of BITS Pilani described India’s lack of investment in research beautifully. He said “India’s Higher Education is described as African Budgets, American ambitions, Russian methods, Chinese opacity and Indian Bureaucracy.
In the past decade, we have seen a slide in scientific temper and investments in research.
1. Non-NET fellowship are stuck at ₹8,000 a month since 2012, for 16,270 scholars in 45 central universities.
2. JRF stipend: In 2014, the JRF was Rs.25,000 per month. In 2019, it was revised to Rs.31m000. it is ₹37,000 PM. The hrowth hasn’t even kept pace with inflation and in real terms, it has FALLEN. IISc scholars even went on a hunger strike demanding an increase.
3. Maulana Azad fellowship: where more than 1,400 scholars have had stipends stalled since January 2025.
4. OBC fellowships: lists for three NET cycles in 2024-25 were held back, which the social justice ministry put down to insufficient funds.
5. INSPIRE: fellows have their stipends unpaid for 3 to 9 months. The schemes now under Vigyan Dhara fell 67.5% between 2016 and 2025.
6. KVPY: scrapped in 2022, after nearly two lakh students a year had taken its test.
7. JRF bottleneck: only 5,108 of 7,35,614 candidates (0.7%) got JRF in December 2025. Minister Sukanta Majumdar gave no year-wise data when asked.
8. The University of Hyderabad stopped Rohit Vemula’s ₹25,000 stipend in July 2015, and his last letter said he hadn’t been paid for seven months. He later committed suicide.
9. India’s R&D spending: fell from 0.82% of GDP in 2009-10 to 0.64% in 2020-21. PMRF spending was revised to ₹290 crore, less than half its ₹600 crore outlay.
10. SC fellowships: fell 61%, from 4,841 to 1,872, between 2020-21 and 2022-23.
If India indeed wants to be a Vishwa Guru, India should be investing in research, in creating quality Higher-Ed institutions. We cannot be cutting down on stipends, not paying our researchers, holding back payments, scrapping scholarships, not increasing fellowship amounts even to match inflation and still expect students to choose research.

[nutanc @nutanc]

@prasanna_says The colleges are already understaffed. How will you fire those who are willing to work at those salaries :)

[nutanc @nutanc]

@Dharisssss Which ones and why are they peak?