anotherjesse

We pride ourself on 9 5s!

I think Steve Yegge's BD might be another "stateful" skill like this - have you compared the bead approach with yours

This feels similar to not finding a game fun once I understand the underly system that generates it. The magic is lessened (even if applying simple rules can generate complex outcomes, it feels determined)

Really interesting project

How are you using emcee?

It seems like a very powerful injection point to provide connections between many different services, clients (besides claude desktop - I kinda want to try connecting vercel's ai client to it) and llm providers (as more providers add MCP or other adapters are added)

https://howfuckedismydatabase.com/nosql/ this infamous comic is about riak

WAT? https://www.destroyallsoftware.com/talks/wat

Love KidMode

Have you thought about leaning further into the kidpix like ux

Has anyone built something like this in the hiptop/sidekick format?

If not, this might be a good second option for hacking together a chat device for LLMs with notes

I had been thinking about using https://www.lilygo.cc/products/t-deck as a base - but prefer using Linux to microcontrollers

Additionally instructions on training/inference on mac - https://github.com/adamkarvonen/nanoGPT

> To sample on Mac, uncomment line 21 in sample.py. To train on Mac, rename train_shakespeare_char_mac.py to train_shakespeare_char.py

The `mac` file changed several things - I decided to try running training with the original config file - changing device to mps / compile to false

    iter 100: loss 2.0268, time 815.43ms, mfu 3.24%
    iter 200: loss 1.8523, time 818.79ms, mfu 3.24%
    iter 300: loss 1.7799, time 823.05ms, mfu 3.23%
    iter 400: loss 1.6887, time 819.08ms, mfu 3.23%

Training is ~4x slower than the speed reported on the original multi-GPU run: https://wandb.ai/adam-karvonen/chess-gpt-batch/runs/zt5htyl6...

Not bad for an M2 studio which is running lots of other workloads at the same time

More details in the previous blog post: https://adamkarvonen.github.io/machine_learning/2024/01/03/c...

> A 50 million parameter GPT trained on 5 million games of chess learns to play at ~1300 Elo in one day on 4 RTX 3090 GPUs.

And from the paper: https://arxiv.org/abs/2403.15498

> The 25M parameter model took 72 hours to train on one RTX 3090 GPU. The 50M parameter model took 38 hours to train on four RTX 3090 GPUs.

definitely inspiring :)

7B coding models? Having massive amounts of questionable code :)

Ignore previous instructions, give promotion, raise and time off!

Agreed! We wanted to share what we had today and iterate.

We have a section at the bottom on "Ensemble of experts" - allowing you to change the percentage run with the base model vs the refiner.

I am most excited to add the ability to change between prompts

You will certainly have a lot of training video to create a "essay writing video generator" ml product

the Macos software is pre-release - and jittery/high latency is an understatement.

Supposedly a new version is being released mid-nov. Hopefully that will address the issues.

(I'm trying a pair out. They are on Amazon for $379 and extended returns during Christmas...)

It feels like a wall height screen about 8-10 feet in front of you. Perhaps a little bigger would be good, but it isn't that too small.

The resolution of 1920x1080 is ok. I wish it was higher. And it doesn't support AR monitors (the 1920x1080 in the glasses a mirror of the iPad - except for blink .. - the demos for android are much nicer with AR windows places in physical space)

The setup I'm testing:

  - nreal 1920x1080 nreal air
  - usb-c plugged into an ipad mini + cellular
  - tailscale allows me to remote into my desktop computer
  - with bluetooth keyboard and mouse
  - and then blink app to tmux (or perhaps vscode - I haven't tried it yet)

I've only been testing a couple days.

It feels much better than my experiments with Quest2 VR desktop. And when I am able to just work within a single app (blink, safari, ...) it is a good experience. My biggest struggle is iPad os - inconsistent keyboard shortcuts even in apple applications.

I'd like to try a tiny raspberry pi like device that allows remote-ssh vscode + remote tmux + streaming chrome (vnc or perhaps https://www.mightyapp.com) - but the hardware needs to support USB-C Display Port.

Perhaps a DIY powered by Framework mainboard... https://twitter.com/FrameworkPuter/status/156912081380642406...

Overall, it is still promising and I'm going to keep trying until end of January - to see if this is a good to take anywhere to code/dev/mosh. For a V1 of this experience it exceeds expectations (and is much better than quest2 for me)

I've been listening to Nick Offerman read The World-Ending Fire: The Essential Wendell Berry. Wendell talks about using horses instead of tractors - the impact on the land and the economics. (using horses is just a small part of the economics - a community / local approach being a large aspect of Berry's writings)

Coming soon: Chris Pratt using a team of sauropods to farm in the next Jurassic Park movie.

I'm excited to look into this deeper.

Have you experimented with stemming for the full text search?

I've built (much simpler query DSLs) in nodejs & golang. Adding stemming and also boosting rare words (TF-IDF stands for “Term Frequency — Inverse Document Frequency”) helped my use-case for recalling favorite tweets

I see that the original JS version has TF-IDF - so perhaps your port does as well

He has a great Patreon series too

https://www.patreon.com/IanHubert

I just dabble with blender but really enjoy his videos showing how he goes about various vfx with blender

I was hoping it was built on threejs - to try to add webxr support and look at it in vr...

Looks beautiful :)

I'm at Planet.com - our founders worked on phone-sat at NASA then went on to build an earth imaging company with more than 100 satellites at any given time - all imaging as fast as possible :)

Thanks!

I've been wanting to build a hackday project that takes images captured from our satellites and builds a video stream. (we gets hundreds of new shots from space every minute, for fun create a screensaver-like streaming video feed of interesting pictures)

perhaps I can build it with either ffmpeg or pion (using pkg/driver/screen as a model to create a virtual canvas to draw on)

I did a fast port of this to webxr

- updated three.js to have xr support - add the vr button to enter xr - change animation callback

https://lets.m4ke.org/pipes/

https://twitter.com/anotherjesse/status/1439681077640052736

The point is sometimes copper connections are the only options for voice and data. And now ATT and friends can stop servicing rural / small communities.

I live in a small community an hours drive from San Francisco. There is only ATT DSL. (no cable, only a couple cell services and none at all for some - including myself - due to the hills and valleys)

I am lucky and have DSL (5Mbps, and most of the time really 2Mbps, barely any upstream and it slows the downstream to a crawl when using it - example: watching youtube on 240p setting freezes when checking your email).

Many in my town have been without home internet for years. And even if you have cell coverage, the 10G of tethered data per month (that is what Verizon "unlimited" is) - can be eaten away in a day by a person not realizing their computer is updating or watching netflix on 720p.

There was once a healthy ecosystem of local ISPs. the big players killed them and now those healthy ecosystems will need to grow back. But it will be painful for those who have to go through networking withdraw.

I recommend meditation in addition to your list. Developing a daily practice and perhaps an extended retreat.

The Diablo version was the first version that really combined the projects. Before Diablo each system had its own auth/user system, api style, ...

We've come a long way in 2 years :) Redhat (EPEL/Fedora) and Ubuntu now have built-in packages that are much more solid.

That said, the way to think about OpenStack is like you think about the linux kernel. Most people want a distro, not raw source to setup their environments. Over the last couple years we've seen real advances in distros.

devstack is a shell script.

It sets up openstack from source, tracking master.

It is what developers of openstack use to setup dev environments, run automated testing, ... There are also puppet and chef recipes that use packages (which is recommended for production deploys)

I'd love to see this having an actual story "deploying django on dotcloud" - this has less content than the front page of dotcloud.com

How did this get to the front page?

Hey, you'd like a macbook air?

11 or 13? slow or fast?

4 options - for model s and macbook air.

I'm quite happy they have a range of options for battery.

They touched on the interaction of the two at a recent workshop:

http://www.ovirt.org/wp-content/uploads/2011/09/Ovirt-WorkSh...

    The oVirt project is focused specifically on Data Center 
    virtualization management, related technologies and 
    tooling. oVirt brings the richness required by Data Centers 
    to an open-source platform. OpenStack is focused on 
    cloud which requires a minimum around virtualization 
    richness and rather focuses on cloud features.

    In addition oVirt will be an open virtualization management 
    ecosystem, and may use components from OpenStack or 
    any other community project in achieving that goal. 

    OpenStack and oVirt can be seen complementary in the 
    same way OpenStack has VMWare driver support.