I have found Fable 5.1 to be a much more natural communicator than prior Claude models

The biggest issue i found was the gap between the tire and rim. Otherwise, the max version is the best so far!

I've found that adding the words - "tell me in simple words" manages to improve the output. But, i have to keep repeating that

Wow, is this really a side-gig?! I would have assumed this would need a team of engineers to run

Not dumb at all. It's a whole field of active research - Speculative Decoding. A recent paper goes one level deeper with Speculative Speculative Decoding - https://arxiv.org/abs/2603.03251

Oh man awesome! I’m so S-M-R-T

Compression is such an interesting field

Is model distillation also related?

Framer Motion has recently launched CSS Studio. It's a library that runs on your browser and gives you the ability to tweak the site directly in browser which fires off instructions for your coding agent to commit to code.

I have been thinking about better and faster ways to communicate with agents for UI related changes and this is the right direction I believe.

If it is a little bigger to incorporate a bigger chip antenna and some GPIO pins, it is going to be very useful for a lot of IoT projects!!

The XIAO series of ESP32s is exactly that.

They are 4x the size though, almost exactly double in both length and width.

https://wiki.seeedstudio.com/XIAO_ESP32C3_Getting_Started/

It's also got 15 times as many GPIO pins as the board in the fine article.

And this PCBA will be smaller than the battery in most applications anyway.

It only has 14 pins, 3 of which are 5v, 3.3v, and ground, so slight exaggeration :-) point taken though

These are nifty. I've used them in production, but if you want to make used of the charger it's difficult.

These are quite lovely. Ceramic SMD antennas are awesome.

Definitely would be more functional with more of the GPIOs exposed.

If you want an ESP32 dev board with GPIOs exposed there are dozens (or hundreds, maybe thousands) of other options out there. It makes sense not to expose them when you're going for the smallest possible footprint.

I don't know, I see enough space for four GPIOs there. Not holes, obviously, but pads should be very workable.

It could be even smaller without that USB C port and have more GPIO pads.

there is plenty of those already and not all too hard to make yourself, see LilyGo T01-C3

Its of format of original ESP8 so you get serial + 3 IO pins

Can anyone suggest a small module that supports 5 GHz WiFi?

Couldn't we get a low-res version of this info by tracking the active window using a cli tool? For linux, there are several options. Not sure about Mac.

Another approach is to run OCR on 1FPS screenshots. Everything runs locally without draining the battery like an LLM would.

You definitely could! I think it would just be harder to get good semantic understanding of what you did during a segment of time without LLMs.

Off topic, but I assume the name braintrust comes from Creativity, Inc. Amazing book by Pixar co-founder Edwin Catmull.

Relevant XKCD - https://xkcd.com/86/