pretty sure nodal energy market trading, duck curve arbitrage is the whole profit play for the tesla power wall/autobidder and the Base Power startup coming out of ERCOT. There is definitely a land rush from energy firms and GIS guys to front run land purchasing near solar buildouts and to build as much grid scale battery storage as possible. The percent swings can be huge. Also a huge rush for this in the Northeast now that the offshore wind contracts have been cancelled.
Verify that Krisp’s noise-cancellation layer doesn’t break our existing VAD / turn-detection when the mic is surrounded by steady, broadband noise.
Test setup:
Open garage; dirt bike idling next to the phone to keep ~90 dB background.
iPhone 16 Pro running the current Sen TestFlight build.
No external mic; Wi-Fi slightly constrained due to distance from router.
What to watch in the clip:
-Whether speech remains intelligible while the engine’s running.
-Quick async function call with google search grounding.
-Sync between the frame overlay and the spoken prompt/response.
How Sen Works?
Voice+Vision input sent at 1fps to LLM. We use daily webrtc transport and pipecat for media handling. fly.io deployment and pipecat cloud with krisp noise integration.
Why this matters?
Sen is a camera-first assistant aimed at trades and field work; the mic is rarely in a quiet office. Robust noise handling is table stakes before we widen the beta.
Try it / reproduce
iOS TestFlight link is available at our website www.withsen.com - Feedback on failures or weird edge cases is welcome.
Hiring a prolific designer, won't buy you the next iPhone. In fact, $6b would have been better spent on the supply chain, the manufacturing intelligence in Asia, and the dirty and difficult work of producing hardware. People forget, how much work is actually needed to produce some innovation like this at scale.
I built/building a realtime voice+vision app called Sen, its currently live in beta and streams frames over webrtc. It's fast and smart, but Im super curious to see how these models do as we get closer to the metal. I can see these running on-device in the future with super fast ttfb.
Do you have a write up of the tech stack and setup? Or willing to give the gist here?
I'd like to make a private Qwen or similar for my kids to prompt with a button and voice control. It doesn't need vision... Although eventually that'd be very cool.
I also ran across an interesting robot toy demo today that had voice built in. it was whimsical and seemed like it was aimed towards primary education and kids. Someone here might know the name.
You can use Ollama or LM Studio, both in API mode, to return the responses. I believe they offer audio support, but I'm not entirely sure.
However, if you're looking for instruction following (like an agent), I've tried to implement my own agent and have lost faith. Even GPT-4.1 will regularly gaslight me that no, it definitely ran the tool call to add the event to my calendar, when it just didn't. I can't get any more adherence out of it.
can you elaborate on how context7 handles document indexing or web crawling. If i connect to the mcp server, will it be able to crawl websites fed to it?
I'm Pete, and I've built Sen, a real-time visual intelligence app designed to help people solve practical real-world problems.
Through testing I've found Sen is best at guiding users through tasks like car maintenance, electrical work, plumbing, boating, DIY projects, and challenges faced in industrial services and skilled trades. My mission with Sen is to make complex tasks simple, through hyper relevant instructions.
Visual intelligence is rapidly becoming the next major frontier in this AI wave, and I'm incredibly excited by the potential of this modality.
I'm currently raising a $50 million round through postcards and mail(a deliberate nod to the human element in our tech driven world). Details can be found through our new parent organization at www.camerasearch.ai.
If you're interested in building or investing as we grow to millions of users, I'd love to connect and speak with you.
