Solopreneur | indie hacker
Kochi, Kerala
Joined April 2010
- Tweets6K
- Following1.4K
- Followers308
- Likes5.1K
Pinned Tweet
"What is an ocean, but a multitude of drops"
youtube.com/watch?v=lxumQYpB…
we already have decentralised social networks. I am guessing these take down actions would accelerate people moving away from these ad factories to such private networks.
GUI automation is getting increasingly better and local models are catching up fast with frontier models for computer use.
This makes me sad. It is also a lead indicator of the diminishing need for human expertise in software engineering.
Krishna Sangeeth KS retweeted
1/4
Meet Qwenputer: Qwen3.5-4B with a full RISC-V CPU inside its weights, using the model's own Gated DeltaNet layers as RAM.
It runs C and MicroPython in its forward passes, no external runtime.
On DeepMind math: base 55–90%, base + Python tool 95–100%, Qwenputer 97.5–100%.
Krishna Sangeeth KS retweeted
An early attempt at getting @googlegemma 's Embedding Gemma 2 to paint using its shared understanding of text and image.
30 ms(around 30 images per second) per image on the Apple Neural Engine on a base Mac M1 pro. generates an image at the end of every word. Trained for about 12 hours on an A100. It is still undertrained. But, with enough data, images can get a lot better.
Krishna Sangeeth KS retweeted
Maya-2 voice model weights are officially live! 🇮🇳🇮🇳
The frontier voice model for India is now completely open-weight.
• Outperforms ElevenLabs v3, Sarvam Bulbul v3, and Cartesia Sonic 3.5
• 1.5B+ people covered across all 28 states and 8 union territories
• SOTA voice synthesis across 11 official languages
• 20 native speakers pre-loaded, ready out of the box
• Best-in-class zero-shot voice cloning
Built by a team of five from the land of languages.
Go build and have fun!
Krishna Sangeeth KS retweeted
Unlimited OCR 2 is here, and it's open source. 📖 ✨
Longer documents can mean a lot more attention computation. Our new SR-SWA mechanism keeps that in check by condensing text-visual attention interactions into a fixed-size set of working references.
Here's what it delivers:
- Document parsing at virtually any length, within a finite context window
- Nearly constant per-step decoding latency and memory footprint as documents grow longer
- State-of-the-art performance on MPDocBench and MarathonDocBench, covering documents from dozens to hundreds of pages
Check out the model here ↓
Krishna Sangeeth KS retweeted
I regret to inform you that nobody cares about your potential. Potential is nothing without execution. When you're young, everyone cares about your potential. You get used to focusing on it. But as you get older, no one cares about your potential. Just your delivery against it.
Cool stufff
i opened up an AI's brain tonight with @_lyraaaa_'s neuron explorer
qwen 3.5 4b has 294,912 neurons
push just one and it becomes someone else
here's who i found 🧵
Me and @_TheIndianRaj_ built a diagnostic evaluator for an @AIBoomi kochi hackathon recently. It’s a full duplex voice based evaluator that tests student’s knowledge assimilation through socratic Q&A method
youtube.com/watch?v=tsAnUGd6…
We used Qwen for ASR, Silero for VAD, turns3.2 for turn detection, GPT as reasoning LLM and Phonon as TTS. Entire thing was orchestrated with Pipecat.
We were able to build a full duplex system that can scale within the timespan of a hackathon. Goes to show how easy it is becoming to build voice AI systems now.
The judge instead of apologising for the wrongdoing of his son behaved badly to the family of the deceased . Unfortunate.
youtu.be/84qb1jCTLg0?si=8JnP…
How does people who are custodians of law hand over vehicle to folks who don’t have license. Not acceptable.
Meanwhile, news from Kerala: A Motor Vehicles Claims Tribunal judge’s minor son drove his Benz and killed a man on a two wheeler.
onmanorama.com/news/kerala/2…
Krishna Sangeeth KS retweeted
This is what Crome saying “this is your last opportunity to fix the mess you’ve created, else you’re out.”
Pretty clear they will be out.
We’re talking about an eng team unable or unwilling to run a RCA and publish it, when everyone assumed they could
bugzilla.mozilla.org/show_bu…
Krishna Sangeeth KS retweeted
Can you use EmbeddingGemma 2 for Speech-to-Text?
This experiment uses EmbeddingGemma 2’s unified audio-text vector space to match speech against text via vector similarity.
The result? Transcribing an hour of audio in about 13 seconds, locally!
