hhthrowaway1230

I like it! Would be great if I could run locally from the start without configuring an s3 for easy playing/prototyping

Also would love to know how was we could iterate over the files. ie a bit how duckdb allows for paruet fikes scanning and reading would be nice to see how fast we can query the fs for ai/ml training workloads

I really want this, but it feels a little scary to trust all my files. I wouls like it if there was some contineous suite trying to corrupt the files and then see the failure cases!

Is this the CA from FB fame? https://en.wikipedia.org/wiki/Cambridge_Analytica? If so how come they still exist?

Would be great if people would brag with quotes and feedback from the maintainers. I'd be more interested to see that. Instead our model found x, I want something that really helps the maintainers.

I agree with this fully. I don’t know about AI in this specific case, but I’m always amazed by human’s capacity to devalue conscious in things they don’t fully understand. Happy to meet someone who thinks this way too.

i feel exactly the same its literally the only api standard that we truly made plug and play and even automatically oauth antenticathable with dcr and people are falling over it. also in an absolute record speed thousands of mcps.

cli’s also need to be documented and input/output typed.

its also extremly dsitributable by just pointing to an url.

cli’s are great because they are composable but i really got huge mileage out of mcps

i know its inteneded to be satire but it kinda isnt?

well excel changed the world, many more organizations run on excel and the companies that dont run excel in the same field are probably having a harder time. so yes i guess?

also ai and excel are different things?

haha this is awesome! this is fantastic.

also maybe a good usecase to finally have P2P web torrents :)

Yeah that's great but I'm in a cafe outside burning my phone data. ty!

Ah let me clarify, many of the in the browser demos make me download certain models even if I already have them It would be great if there was a way that I don't have to redownload them across demos so that I just have a cache. or an in browser model manager. hope this makes sense.

Or indeed use some sort of huggingface model downloader (if that exist with XET)

so multiple of these browser wasm demos make me re-download the models, can someone make a cdn for it or some sort u uberfast downloader? just throw some claude credits against it ty!

I had to double check if I was on the right domain, my dear what an awful idea. But maybe I'm missing something.

note: doesn't openrouter charge 5.5% fee?

Awesome! Also love the gaussian splat demo, cool use case!

First time I saw a post here of her I found it odd, and made me think, now I know it's one of the things that makes HN, HN and I appreciate. To make me think.

Don't think there is anything wrong with a centralised service being down, you just make a conscious decision if you want that and can afford that?

People not being ready for cloudflare/[insert hyperscaler] to be possibly down is the only fault.

A good thing is to incorporate some old school observability and benchmarking, MLFLOW has been around for some time. You could push some some parameters to that to track your scores, and you could use Meta's AX optimisation framework to finetuning the settings (hyperparameters)

Good like these small tools. I'd like to opt for more strategies too like doclings HierarchicalChunker.

Also curious! I was also wondering if criu frozen containers would help here. I.e. load the notebooks, snapshot them, and then restore them.

how many permutations of Fe dev do we need?

- auto rerender by comparing trees?

- track all changes by signals?

knockout js is that you?

Good work! Needed this today

Sorry about that, will be more considerate in the future

Sounds like LinkedIn story to me. Written by claude trying to drive a point home.

Guess that is why there isn't an easy go to solution yet. But it's well needed.

> Can you help me understand that?

Like 10 nodes behind tailscale/wireguard in a private network, with only 2 nodes where you have a port open on 80/443, those are exposed to the public network. The rest of the nodes are all private like db, redis, etc etc.

I like it but I always miss features or defaults like: - internal network only with edge nodes (i.e tail scale out the box, + some edge nodes) - option to deploy on multiple servers to scale with super simple non k8s approach.