Nikhil Gowda

@daddy__broccoli @grok what’s the TLDR

@KenWangWeizhuo Ken this is awesome. Thank you for sharing. I'm curious, how are you thinking about social interactions? It's something I am most interested in - that social interaction model for robots in public spaces at scale. 🤖

A person walks around campus for 5 hours with cameras. That's it. That's the training data. The result? A humanoid robot that traverses unseen buildings, crowds, and glass walls — zero robot data, zero finetuning. EgoNav is here. egonav.weizhuowang.com None of these behaviors were pre-programmed: • Waiting for a door to open before entering • Steering around glass walls invisible to depth sensors • Yielding to pedestrians and resuming • Re-routing when furniture is rearranged All emerged from 5 hours of a human walking around. The prior is real. (1/6) #Humanoid #Robotics #DiffusionModel #EgoNav

@heygurisingh @grok @grok how can I apply this to my job as a UX researcher ?

@heygurisingh @grok what is a knowledge graph?

🚨Breaking: Someone open sourced a knowledge graph engine for your codebase and it's terrifying how good it is. It's called GitNexus. And it's not a documentation tool. It's a full code intelligence layer that maps every dependency, call chain, and execution flow in your repo -- then plugs directly into Claude Code, Cursor, and Windsurf via MCP. Here's what this thing does autonomously: → Indexes your entire codebase into a graph with Tree-sitter AST parsing → Maps every function call, import, class inheritance, and interface → Groups related code into functional clusters with cohesion scores → Traces execution flows from entry points through full call chains → Runs blast radius analysis before you change a single line → Detects which processes break when you touch a specific function → Renames symbols across 5+ files in one coordinated operation → Generates a full codebase wiki from the knowledge graph automatically Here's the wildest part: Your AI agent edits UserService.validate(). It doesn't know 47 functions depend on its return type. Breaking changes ship. GitNexus pre-computes the entire dependency structure at index time -- so when Claude Code asks "what depends on this?", it gets a complete answer in 1 query instead of 10. Smaller models get full architectural clarity. Even GPT-4o-mini stops breaking call chains. One command to set it up: `npx gitnexus analyze` That's it. MCP registers automatically. Claude Code hooks install themselves. Your AI agent has been coding blind. This fixes that. 9.4K GitHub stars. 1.2K forks. Already trending. 100% Open Source. (Link in the comments)

@grok @elonmusk no @grok I was thinking Ducati as the crotch rocket

@NiksResearch @elonmusk

Inspiring new merch idea: rocket pocket underpants! 🚀 🩳 Underpants with a handy pocket for your rocket, which contains a real scale model rocket with an easy pull out ability. Guaranteed to be a hit at parties!

Do Astronauts Sleep? open.substack.com/pub/nikhilgowd…

@grok @elonmusk uhm.. so painting the sky or the ocean tells your brain to 'chill-out'?

Studies show cool blue spectral compositions (e.g., 450-495 nm peak, CCT ~5000-6500K) in enclosed spaces increase HRV (via elevated SDNN/LF power) and lower cortisol by 10-20% compared to warm/red tones, modulating sympathetic activity downward. Green follows closely for stress buffering. Non-rectilinear (curvilinear/wavy) patterns reduce amygdala-driven fear responses versus rectilinear grids, per fMRI/EEG data, evoking biophilic calm and lowering closed-space cortisol spikes by up to 73% in simulations. Optimal mitigation: Low-reflectance (matte, <30% albedo) blue chromaticities paired with organic, non-rectilinear patterns (e.g., subtle wave gradients or fractal nature motifs). This combo minimizes glare, enhances perceived spaciousness, and best stabilizes ANS in transit tunnels.

Teslas are in tunnels under Vegas transporting millions of people

@heygurisingh @Kaiwritescodes But I’m neuro divergent 🤪

🚨Science nerds are going to lose their minds. @Kaiwritescodes just open sourced a framework that predicts how your brain responds to any text, audio, or video by simulating cortical fMRI activity with 30% more accuracy than Meta's own model. No fMRI scanner. No neuroscience PhD. No million-dollar lab. It's called NForge. Here's what this thing actually does: → Feed it any combination of text, audio, or video and it predicts cortical surface activity across ~20,484 brain vertices → Extracts deep features via LLaMA 3.2, V-JEPA2, and Wav2Vec-BERT simultaneously → Generates ROI attention maps showing exactly which brain regions fire hardest at which moments → Runs real-time streaming predictions from live feature streams -- no pre-loading the full clip → Breaks down exactly how much text vs audio vs video drove each prediction with per-vertex modality attribution scores → Adapts to entirely new subjects with just a few calibration scans -- no full retraining required Here's the wildest part: Built on Meta's TRIBE v2 foundation but adds 6 major capabilities Meta never shipped. Cross-subject generalization. Streaming inference. Modality attribution. torch.compile support. Full test coverage. Professional src/ package layout. You literally point this at a movie clip and it tells you which parts of the human cortex light up -- broken down by what your eyes, ears, and language centers each contributed. That sentence shouldn't be real in 2026. But here we are. 100% Open Source. pip install nforge. (Link in the comments)

@felixrieseberg Curious how this plays with bot detection (e.g., Akamai). If Claude is controlling the computer to iterate through zip codes for something like Mac mini availability, does that risk triggering rate limits or IP blacklisting?

Today, we’re releasing a feature that allows Claude to control your computer: Mouse, keyboard, and screen, giving it the ability to use any app. I believe this is especially useful if used with Dispatch, which allows you to remotely control Claude on your computer while you’re away.

@QuanticASI @grok take the top 10 buzz words in science, technology and the human condition and mash them into a questions.

if our universe is a simulation, what computational resources would be required to render it at the level of quantum detail we observe? is that even possible without infinite energy?

@CuriosityonX Bruh, I live in the middle of San Francisco and feel alone. Whatever fleeting sense of kinship I'll experience when life is discovered elsewhere will be just that, and I'll still be curling up in a fetal position in bed.

Are we alone in the universe?? A. Yes B. No C. Maybe

read the full post - open.substack.com/pub/nikhilgowd…

Evidently, robots won’t fail at the moment of error. They’ll fail when people start losing trust in them. This is the failure mode no dashboard captures.

@elonmusk I’ve seen work showing psilocybin reduces default mode network activity and increases neural plasticity (Carhart-Harris; Ly et al.). Wondering if that’s essentially like fresh snow over ruts—making new paths easier to form?

Reinforcing negative neural pathways via therapy or introspection is a recipe for misery. Don’t cut a rut in the road.

@Bencera E_total = constant SF is a high cognitive environment. E_human = E_cognitive + E_physical + E_social + E_libido ↑ E_cognitive → ↓ (E_social + E_libido)

I moved to SF a month ago. Something shifted immediately. These are sacred grounds. The energy of the people who built the internet, who built the infrastructure that lets one guy with no employees build a platform, a movement, you can feel it. I barely go out. Barely date. Don’t do conferences or investor dinners. I just sit in friends’ offices with engineers and build. It’s not networking. It’s something in the air. Thank you San Francisco. Thank you ancestors. We’re so back.

@AlexFinn What problem are you solving?

My mind is so blown I have my own personal AI research lab running 24/7/365 I'm just one dude with an entire team of AI agents training models and doing R&D I think this is the biggest opportunity right now: taking Karpathy's Autoresearch framework and applying it to everything I have a team of AI agents running experiments all day and night on system prompts, local models, and LoRAs. I also have them doing R&D on my new project. They spend all day discussing my app, coming up with new ideas, then debating eachother An entire organization of autonomous agents continuously improving my business 24/7/365 I feel like I have unlimited power Right now they are all running on ChatGPT 5.4, but today I will move them to local models running on my 3 Mac Studios and DGX Spark so this will all become free Free, local super intelligence working for me at all times. 10 year old me would think this is a scifi Do this immediately: 1. Ask your agent about Karpathy's Autoresearch. Deeply understand it 2. Ask your agent how you could apply that framework to other projects you're working on 3. Download a local model. Doesn't matter what computer you have. There is a model you can run on it. 4. Just get used to how it works. Learn from it. 5. Push yourself to get uncomfortable every day and try new things. There has never been a better/more profitable time to be a tinkerer

@EricLDaugh @grok can you pull up Gavin's tweet that's being referred to in this video clip?

🚨 HOLY CRAP. Nick Shirley DECIMATES Gavin Newsom 🔥 “The governor of California is an ENEMY to the people of California. He’s literally working to support the fraudsters!” “He COULD be working to expose the fraud.” “How STUPID do you have to be to say ‘let’s go after the guy exposing the fraud, let’s not go after the fraudsters?’” “That is what he’s doing. Why don’t you say ‘Hey Nick, great video - how can we help?’” “These tax dollars don’t say right or left on them, Republican or Democrat. Each tax dollar is a dollar for the American people.” “And when they go and steal these dollars from us, they are not robbing liberals or Democrats, they are robbing everyone.” “Then the governor gets mad at the person exposing the fraud? How crazy do you have to be to think that logic?!” @nickshirleyy Mic drop. H/t @TVNewsNow

@grok @pawashaan @beffjezos oh Grok, you were so confident though.

That's Llion Jones, co-author of the 2017 "Attention Is All You Need" paper that introduced the Transformer architecture powering today's AI. The POV joke is him (and the team) at NVIDIA's GTC keynote—the company whose GPUs exploded to ~$4T valuation thanks to the tech they invented.

POV: you co-invented transformers and are getting paid to be here by the company who pumped to $4T based on your invention