Hugging Face's logo
Dipankar Sarkar's picture
🏗️ Building on HF

Dipankar Sarkar PRO

dipankarsarkar
4 1347 280
RiverRider's profile picture gabriellidenor's profile picture SimonDuApodex's profile picture
·
https://www.dipankar.cc

AI & ML interests

Building the AI-native stack. Agents as infrastructure, safety as architecture, performance as plumbing. I publish the receipts: papers, datasets, demos.

Recent Activity

reacted to Quazim0t0's post with 🤯 about 11 hours ago
I turned the fruit fly's connectome into a language model. It learned broken English. MaleCNS v1.0 (Janelia / Google), as released. 167,565 neurons, 25.6M synapses. I made that the core of a spiking net and trained synapse strengths only. The wiring is still the fly's. It learned language. ~16M tokens in, it produces stuff like Once upon a time, there was a girl smiled. The language is in the brain's activity, not just the readout. It sees through its own eyes. Photoreceptors on both eyes into the optic lobes. A dopamine reward through the fly's own PAM / PPL1 cells is what actually got it to use the pictures. It's still a fly. Put it back in a whole-brain fly sim and sugar still fires the proboscis. It can live as a fly again. 30 simulated days with the language synapses frozen: the rest of the brain adapted around them. Language and reflex both still there. Talk to it, show it pictures, sugar test, or let it live 1-30 days: Space: https://huggingface.co/spaces/Quazim0t0/MaleCNS-Fly Model, code, write-up: https://huggingface.co/Quazim0t0/MaleCNS-SpikeWhale-Anatomy-LM Research experiment, not a chatbot. Simulation of the released wiring.
liked a dataset about 11 hours ago
Logics-MLLM/Logics-SWE-Env-2.5K
upvoted a paper about 11 hours ago
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
View all activity

Organizations

Skelf Research's profile picture Neul Labs's profile picture Incredlabs's profile picture Cognisoc's profile picture