Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Companies of one, what is your tech stack?

news.ycombinator.com

Post reply on HN
Print view View original

111–120 of 206 posts

Re: Ask HN: Companies of one, what is your tech stack?

#111

Post by gingerlime »

lee101 wrote: post #33

I run https://text-generator.io competing with OpenAI. I used to use kubernetes on Google cloud, but now run it from my house behind a CloudFlare tunnel believe it or not Using my own GPUs allows me to undercut them with around 10x cheaper pricing. The product is built with some open source and some retrained models, it analyses input links or linked images with tesseract/unified IO / OFA / beautiful soup so it can a…

OT but can these AIs generate text based on existing corpus? eg helpdesk system that suggests responses to (human) agents based on previous (human) questions and replies or a bank of frequent saved snippets/replies.

edit: or find previous conversations with high similarity

Re: Ask HN: Companies of one, what is your tech stack?

#112

Post by lee101 »

farmin wrote: post #34
lee101 wrote: post #33

I run https://text-generator.io competing with OpenAI. I used to use kubernetes on Google cloud, but now run it from my house behind a CloudFlare tunnel believe it or not Using my own GPUs allows me to undercut them with around 10x cheaper pricing. The product is built with some open source and some retrained models, it analyses input links or linked images with tesseract/unified IO / OFA / beautiful soup so it can a…

This is so cool

Thank you! Means a lot :)

Re: Ask HN: Companies of one, what is your tech stack?

#113

Post by RulerOf »

tothrowaway wrote: post #85

I run several SaaS apps on a single big OVH server. It handles 6 million non-cached requests per day. The backend stack is pretty basic: Django/Python, MySQL, redis (pub/sub) for websockets. But the secret sauce is OpenResty. I use Lua scripts to do more sophisticated page caching (because the builtin nginx caching is so primitive), DDoS protection, handling websockets, offloading long running requests, and routing b…

OpenResty has a clever answer to just about every problem.

Re: Ask HN: Companies of one, what is your tech stack?

#115

Post by lee101 »

gingerlime wrote: post #111
lee101 wrote: post #33

I run https://text-generator.io competing with OpenAI. I used to use kubernetes on Google cloud, but now run it from my house behind a CloudFlare tunnel believe it or not Using my own GPUs allows me to undercut them with around 10x cheaper pricing. The product is built with some open source and some retrained models, it analyses input links or linked images with tesseract/unified IO / OFA / beautiful soup so it can a…

OT but can these AIs generate text based on existing corpus? eg helpdesk system that suggests responses to (human) agents based on previous (human) questions and replies or a bank of frequent saved snippets/replies. edit: or find previous conversations with high similarity

Right now the text generation API can be used to do the conversational stuff along with a massive amount of other stuff like classification or adding questions about what is in text or how proper would respond to things for analysis purposes.

There's an embeddings API for text/code/images that can bed used for the similar snippets stuff if you bring your own vector search engine like milvus etc, but eventually I'll support uploading sets of documents and do the finding relevant snippets behind the scenes so you can ask these kinds of questions e.g. so people can do custom site specific FAQ answering bots etc.

There's an example in the playground of shorter autocomplete which is another way of helping agents too that it supports

Re: Ask HN: Companies of one, what is your tech stack?

#116

Post by nelsonic »

hdra wrote: post #77
nelsonic wrote: post #67

Earlier quoted context omitted.

@hdra did you capture your LiveView experience somewhere e.g. a learning log (blog post). I would love to read it as I’m sure everyone in the Phoenix team would. Thanks!

I'm embarrassed to say that writing about that has been on my Soon™ list for quite a while ;)

Brain dump some bullet points as an outline that you can later expand on. You have no idea how helpful it will be to other people including your future teammates. ;-)

Re: Ask HN: Companies of one, what is your tech stack?

#119

Post by lee101 »

nwienert wrote: post #79
lee101 wrote: post #33

I run https://text-generator.io competing with OpenAI. I used to use kubernetes on Google cloud, but now run it from my house behind a CloudFlare tunnel believe it or not Using my own GPUs allows me to undercut them with around 10x cheaper pricing. The product is built with some open source and some retrained models, it analyses input links or linked images with tesseract/unified IO / OFA / beautiful soup so it can a…

Nice signup flow. Just tonight I was wanting GFN-GAN + a more light/noise/color cleanup ML model combined to restore old photos. Gluing a couple together would be super useful.

Yea, images/video is interesting, I think combining textual instruct and dalle/other models would be interesting so you could describe literally "restore this old photo and upscale+colorize it".

Was thinking of ways to do that kind of thing, I think unified IO is a good start at some flexibility but still lots of peices missing.

In the world of video training your own video filters based on editing a few frames is quite common E.g. something like nuke copycat or using ebsynth etc.

There's likely some new wave of DSLs or visual workflow builders coming that are either more ml friendly and or specific to building a conversational system/ image editing pipeline etc

Re: Ask HN: Companies of one, what is your tech stack?

#120

Post by nicbou »

aaronbrethorst wrote: post #24

Hosting on Render. Stack: Postgresql+Rails+Hotwire. I really dig Stimulus and Turbo Frames. It took me a little while to really wrap my head around Turbo Streams. I think the documentation is pretty bad compared to the rest of the Hotwire stack, but—holy moly—once I had it working, it's really like a superpower for front-end development. Using Turbo Streams reminds me a bit of the sort of 'head exploding' moments I h…

Your landing page is great. It's very straightforward.
Post reply on HN