hhthrowaway1230
hhthrowaway1230 on Hacker News
Wow! Now all we need is Fasttracker 2 and then 90's music revival is done!
Great work. Don't forget to check the demo songs and TGV kilomix from bar 30 or smth.
Posted by
hhthrowaway1230 on Saturday September 19, 2026 @10:37AM
from the ask-hn dept.
Hi HN!As a freelancer, I usually do a requirements workshops + one or two months of development in the pre-ai era. Which was enough to pay the bills and save up. Now I can do things in a matter of days. Do I charge my clients the old time + rate, or just the new reality (which means I'd need more gigs in order to make the same amount of money)Would love to hear your answers, cause charing them...
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!
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!
Posted by
hhthrowaway1230 on Wednesday March 11, 2026 @12:47PM
from the ask-hn dept.
Looking for a truly opensource alternative to collect oauth tokens and do integrations with in a unified api for agents.I.e many integrations with single place where users can connect their integrations. Preferably just a single lightweight app, with some proxy api.Thank you all!
Posted by
hhthrowaway1230 on Saturday February 21, 2026 @04:52PM
from the coroot.com dept.
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.
Posted by
hhthrowaway1230 on Tuesday November 25, 2025 @05:15AM
from the ask-hn dept.
Right now looking at MLFlow/Braintrust but find it hard to compare acrosss versions of agents, and a/b testing of agents, and mcp tools. Also obvious things like runaway agents (stuck in a loop), or token/spend optimalisation.What do you all use?
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.
Posted by
hhthrowaway1230 on Friday November 14, 2025 @09:05AM
from the dittytoy.net dept.
Posted by
hhthrowaway1230 on Friday November 07, 2025 @10:40AM
from the arxiv.org dept.
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?