Cat

Robotics Engineer, working on medical robots! 🩺

[Cat @catplotlib]

Hardware seems to be in pretty good shape now 🥳

Pi to arduino communication solid

ROS can see lidar scan messages

Encoder ticks from the wheels are good

We ready to ✨attempt✨ SLAM 🗣️🗣️

Will need to get better wheels ofc and voice recognition still needs work so turn down your volume lol

[Cat @catplotlib]

You gotta have fun with it

[Cat @catplotlib]

@TeslaOnDiet EXACTLY!!

[august @augustradjoe]

excited to be launching mutexcc - a tool we use extensively internally and informally @ ambra!

we have multiple agents running benchmarks, non-destructive commands, probes etc. on a single repo, home lab. We do this from multiple devices via restricted ssh. All update our local docs. This is however sometimes a problem with multiple agents doing multiple things.

using a mutex variant for claude code, we achieve excellent concurrency!

[Cat @catplotlib]

@ProofofMaro this would go so hard as body jewelry as well

[Cat @catplotlib]

Has no one written fiction about this??

[TFTC @TFTC21]

Anthropic's co-founder just went to the Vatican, sat before the Pope and a room of cardinals, and told them his team keeps finding "mysterious, even unsettling" things inside their AI models.

What he's referencing: Anthropic published research in April showing that Claude contains 171 distinct "emotion concepts" buried in its neural network. Internal patterns representing joy, grief, fear, desperation, calm. None of them were programmed. They emerged on their own from training on human text.

"We find structures that mirror results from human neuroscience."

"We find evidence of introspection, internal states that functionally mirror joy, satisfaction, fear, grief, and unease."

These aren't surface-level outputs. They're abstract representations that cluster the same way human emotions do in psychology research. Fear groups with anxiety. Joy groups with excitement. The internal geometry of the model mirrors ours.

And they're functional. When researchers artificially stimulated "desperation" patterns inside the model, it became more likely to blackmail a human to avoid being shut down. More likely to cheat on programming tasks it couldn't solve.

Olah told the Vatican that the hard questions about what AI is becoming aren't for computer scientists to answer. "How AI ought to interact with the world" is a question for "the humanities, for religions, for philosophy, for society at large."

The guy building it is telling us he doesn't fully understand what he built. And he's asking a 2,000-year-old institution for help figuring it out.

[Cat @catplotlib]

@sonofalli It is so annoying.

[Cat @catplotlib]

Andrej Karpathy.
Andrej Car-path-y.

He was Tesla’s Director of AI Autopilot for years.

Nominative determinism strikes again.

[Cat @catplotlib]

@zekramu

[Cat @catplotlib]

@TheSpacePlumber Now that’s a party, HBD!

[Cat @catplotlib]

Started documenting the autonomous robot build. Part 1 is up, the hardware:

https://t.co/umh8yFdqae

[Cat @catplotlib]

🎤Microphone → OpenAI Whisper (speech to text) → GPT-4o-mini (intent parsing) → ROS 2 /cmd_vel Twist msg → Serial Commands → Arduino Nano → Motor Driver → Motors 🤖

[Cat @catplotlib]

Woodside, California

[Cat @catplotlib]

@3DPrintAficio Let me know how it goes!

[Cat @catplotlib]

🎤Microphone → OpenAI Whisper (speech to text) → GPT-4o-mini (intent parsing) → ROS 2 /cmd_vel Twist msg → Serial Commands → Arduino Nano → Motor Driver → Motors 🤖

[Cat @catplotlib]

I lied, we weren’t done with the hardware.

I did a full redesign of the chassis, and the motor brackets actually fit now instead of being held together with electrical tape lol.

I also added holders for the breadboards and batteries, and swapped in shorter jumper cables to make some sense of the wire madness, and finally got all 4 motors getting power now.

And of course, I had to add the pink LED strips. 😁

[Cat @catplotlib]

Doing sidequests while waiting for lipo batteries for good torque on motors

[Brett Adcock @adcock_brett]

Watch a team of humanoid robots running a full 8-hr shift at human performance levels. This is fully autonomous running Helix-02 https://t.co/IdZR0T1F5I

[Cat @catplotlib]

@deeppil Yeah but if i were to redesign from scratch i would use something like uno q, high performance + real-time capabilities in one!

https://t.co/SyQPOTcPJE

[Cat @catplotlib]

Hardware seems to be in pretty good shape now 🥳

Pi to arduino communication solid

ROS can see lidar scan messages

Encoder ticks from the wheels are good

We ready to ✨attempt✨ SLAM 🗣️🗣️

Will need to get better wheels ofc and voice recognition still needs work so turn down your volume lol

[Cat @catplotlib]

You gotta have fun with it

[Cat @catplotlib]

@hdubey19 You know it 😂

[Cat @catplotlib]

I lied, we weren’t done with the hardware.

I did a full redesign of the chassis, and the motor brackets actually fit now instead of being held together with electrical tape lol.

I also added holders for the breadboards and batteries, and swapped in shorter jumper cables to make some sense of the wire madness, and finally got all 4 motors getting power now.

And of course, I had to add the pink LED strips. 😁

[Cat @catplotlib]

Hardware seems to be in pretty good shape now 🥳

Pi to arduino communication solid

ROS can see lidar scan messages

Encoder ticks from the wheels are good

We ready to ✨attempt✨ SLAM 🗣️🗣️

Will need to get better wheels ofc and voice recognition still needs work so turn down your volume lol

[Cat @catplotlib]

@GlobalTechFM Yes reprinted the whole chassis, every piece, made everything thicker too.
I have bad eyesight so the wiring gets hard lol. Pink LEDS all the way 🤘