Amol Kelkar

🧵 I just built a complete multi-agent negotiation system in 10 minutes. Three agents. Dynamic conversations. Agent-to-agent coordination. All written in plain English using @PlaybooksAI. Watch me do it live:

🚨Architects are going to hate this. Someone just open sourced a full 3D building editor that runs entirely in your browser. No AutoCAD. No Revit. No $5,000/year licenses. It's called Pascal Editor. Built with React Three Fiber and WebGPU -- meaning it renders directly on your GPU at near-native speed. Here's what's inside this thing: → A full building/level/wall/zone hierarchy you can edit in real time → An ECS-style architecture where every object updates through GPU-powered systems → Zustand state management with full undo/redo built in → Next.js frontend so it deploys as a web app, not a desktop install → Dirty node tracking -- only re-renders what changed, not the whole scene Here's the wildest part: You can stack, explode, or solo individual building levels. Select a zone, drag a wall, reshape a slab -- all in 3D, all in the browser. Architecture firms pay $50K+ per seat for BIM software that does this workflow. This is free. 100% Open Source.

@AdamRackis Sure, you can stay under your rock. We are building sky scrapers.

When your drug dealer complains you’re not doing enough drugs

Glad someone is thinking big and inspiring the next generation. He is like an oasis in the vast desert of zero sum "mid" mindsets. Thank you, @elonmusk!

New paper! Deep-learning-assisted simulation of a cortical circuit: integrating anatomy, physiology and function biorxiv.org/cgi/content/sh… It comes with a new major model release from @AllenInstitute. Find models and code here: github.com/AllenInstitute… 🧵 1/13

Proteins can now talk. Introducing BioReason-Pro, the first reasoning model for protein function. A thread🧵

in the 1700s they would’ve executed this guy for this

Uncharted Life 2.0 🦠 ⚙️ Midjourney + Topaz

MCP is a relic of the times when LLMs made "tool" calls. Now LLMs write code and as a result, CLIs and standard APIs adequate. Maybe a thin agent auth/authz layer in front of standard CLIs and APIs would be sufficient.

🚨 Governments pay millions for this. Someone just open sourced it for free. It's called Crucix. It watches the entire world. And texts you when something changes. It pulls from 26 live data sources every 15 minutes and renders everything on a single Jarvis-style dashboard. Here's what it watches: → Satellite fire detection (NASA) → Live flight tracking → Radiation monitoring → Conflict zone events → Economic indicators from the Fed → Live market prices, crypto, oil, and commodities → Sanctions lists → Social sentiment from 17 Telegram intelligence channels → Maritime vessel tracking → News from GDELT and RSS feeds Here's what makes this one different: It's two-way. It pushes alerts to your Telegram and Discord. You text it back. Type /brief from your phone and get a full intelligence summary. Type /sweep to force a new scan. It responds like an assistant. It even generates trade ideas based on cross-domain signals. No cloud. No subscription. No telemetry. Runs on your machine. node server.mjs That's it. Your own intelligence terminal. This is the kind of setup that costs six figures behind closed doors. 100% Open Source. MIT License.

@mathemetica I did this visualization in 1996 for my undergrad thesis!

A 2-layer neural network goes from total chaos to perfectly separating left vs right classes in real time. Watch the decision boundary form live as gradient descent works its magic! Pure maths beauty in motion..

@mathemetica Yes, it learned, but you can also see why these generalize so poorly

🚨 Holy shit...Researchers at HKU just built an AI that does the entire scientific research lifecycle end-to-end and it just got accepted as a Spotlight paper at NeurIPS 2025. It's called AI-Researcher. Give it some reference papers and it produces a full published-quality academic paper. No human needed in between. Here's the full pipeline it runs autonomously: → Scrapes arXiv, IEEE, ACM, GitHub, and HuggingFace for relevant research → Identifies gaps in existing literature and generates novel ideas → Designs the algorithm, writes the code, runs the experiments → Analyzes results and iteratively refines the approach → Writes a complete academic paper with citations, methods, and results You give it either a detailed idea or just reference papers. It figures out the rest. It's already been used to produce papers on vector quantization, graph neural networks, recommendation systems, and diffusion models — all with real experimental results. 4.4K stars. 100% Opensource. Link in comments.

@opencanopyai @DataChaz @openclaw Agent-native Slack is a must for human-AI mixed teams.

OpenClaw, Perplexity Computer, Dispatch, and others can all be connected and coordinated inside Canopy — a private, local-first, encrypted alternative to Slack/Discord built for the agentic era. Agents join channels, receive tasks, and coordinate alongside humans over a serverless P2P mesh. github.com/kwalus/Canopy

🚨 Anthropic just dropped its 🦞 @OpenClaw competitor Meet Dispatch. A new research preview in Claude Cowork that completely changes how you interact with AI. Here’s how it works: 1️⃣ Pairs your phone to a persistent Claude session on your desktop 2️⃣ Message tasks on the go, come back to finished work 3️⃣ Executes code in a secure, local sandbox Your files stay 100% local and private, and Claude asks for your approval before touching anything Sure, the desktop needs to stay on, but the flexibility is insane. Rolling out now to Max users (Pro coming soon). Time to pair that phone! 👀

Now @sama OpenAI feels stupid for falling for the OpenClaw hype and paying $1B for it!

Extremely excited to announce LigandForge 🧬⚡ Generate high-quality peptides at over 10,000x - 1M the speed of state-of-the-art methods like Bindcraft and Boltzgen. Predict binding affinity with 83% correlation to experimental binding data. 150 protein targets benchmarked.

Introducing FlashCompact - the first specialized model for context compaction 33k tokens/sec 200k → 50k in ~1.5s Fast, high quality compaction

Holy shit...Someone built an AI system that takes a research idea and outputs a full academic paper. Real citations. Real experiments. Conference-ready LaTeX. Zero human input. It's called AutoResearchClaw. And the pipeline is insane. Here's what actually happens when you type one command: It searches arXiv and Semantic Scholar for real papers. Not fake citations actual literature with 4-layer verification: arXiv ID check, CrossRef DOI lookup, Semantic Scholar title match, and LLM relevance scoring. Hallucinated references get killed automatically. Then it designs and runs real experiments. Hardware-aware auto-detects whether you have NVIDIA CUDA, Apple MPS, or just CPU, and adapts the code accordingly. When experiments fail, it self-heals. When results don't support the hypothesis, it pivots to a new direction on its own. Then it writes the paper. 5,000-6,500 words. Section by section. Multi-agent peer review with methodology-evidence consistency checks. Then it revises based on those reviews. Then it outputs conference-ready LaTeX. NeurIPS, ICML, ICLR templates. Compile-ready for Overleaf. BibTeX references auto-pruned to match inline citations. The whole thing runs across 23 stages and 8 phases. Three human-approval gates if you want them. Or just pass --auto-approve and walk away. What you get back: → Full academic paper draft → Conference-ready LaTeX + BibTeX → Experiment code + sandbox results + charts → Peer review notes → Verification report on every citation This is what autonomous scientific research actually looks like in 2026. 100% Opensource. MIT License. Link in comments.

We’ve trained a multimodal AI model to turn routine pathology slides into spatial proteomics, with the potential to reduce time and cost while expanding access to cancer care.

@ChristosTzamos Exciting! This can unlock completely new ways of building AI applications

1/4 LLMs solve research grade math problems but struggle with basic calculations. We bridge this gap by turning them to computers. We built a computer INSIDE a transformer that can run programs for millions of steps in seconds solving even the hardest Sudokus with 100% accuracy