What's the latency like? Is the llm used to create an instruction set for the robot? How is it interrupted for reflex actions like controlling stumbling?
The LLM right now tells a much lower level neural network controlling the legs, arms and head what and how to move at a ~ 500Hz freq, which controls thing like the stumbling. All motor joints and IMU inputs are given to an ONNX-based RL-trained NN which then outputs motor movements (scary since its works well for the scenarios where its has been trained, but it goes in unexpected ways for untrained scenarios).
In any case latency is acceptable for navigation I guess, but avoiding moving obstacles is definitely a no-go right now.
Thanks! This is encouraging. I try to use Claude Code for producing client facing presentations that are static html files with charts, tables, and annotations. It never gets the tone correct and phrases things so weirdly - it drives me mad. I have to really fight it to stop it writing insights in a flowery and verbose way
What exactly makes it proactive? I created a similar system that ran on a ticker, but then could also set itself to run in n seconds in the future. RSI came from the actions available to the system and granting the ability to modify itself. The prompt was a string of messages made from static and dynamically generated sections (like memories or plans of tasks or outputs from actions taken on the previous turn). It worked really well
I've done this with the Libre 2 sensor. I added Gemini to it. It gets like 2 weeks of readings at once, and the user can "chat to their data". I added a meals tool as well, where the user can photo their meal, and the ai estimates the impact on the readings.
It's so helpful to offload some the thinking about the condition to ai, all these people moaning about 'muh safety' don't get it. T1D suffers have to think about it all day all the time. A person doesn't have their own blood glucose data in their head.
I never reveal it at work, there are morons out there that have opinions like "I'm starsign x, and if you're y, then we won't get along". It's so frustrating
Recently my wife and I looked up our signs. I guess we aren’t compatible at all! Someone should have told us a decade ago and saved us from 10 years and counting of happiness.
They’re kinda fun but I hope people aren’t making big decisions out of them.
Has anyone tried buying art from Etsy recently? It's very difficult to find something that is actually original. Etsy is full of super hero Chinese knockoff poor quality shite
Be careful with OKCupid. I'd been using it on and off for a while and recently I got a notification saying that my email address on my account had been changed, then 2 minutes later, that my password had. You don't need to confirm anything to change the email on your account! Not even click an email link!
I was panicking
I was still receiving phone notifications despite not being to log into the app. I could see that messages were being sent and received but couldn't access my account. I believe that others are being scammed using my account
I quickly changed all other passwords and contacted OKC immediately. It's been a week now with no response. OKC have lost a paying customer for life
You mean you can change the email without a password? Why would it be a problem if they require your password but nothing else in order to change your email?
What's the latency like? Is the llm used to create an instruction set for the robot? How is it interrupted for reflex actions like controlling stumbling?