Viewing profile — FezzikTheGiant

hey hn, wanted to share something i've been working on for a bit. most focus apps like opal are static. they block a list of websites and that’s it. once you start a timer, you’re …

genuinely what's the point of this comment? are you allergic to cool stuff? honestly curious as to what you were trying to achieve by this comment. nowhere in this post does the au…

fair enough

what's the cost difference between groq/cerebras vs using something else for inferencing open source models? I'm guessing the speed comes at a cost?

i think lots of apps are going to go in the adaptive/generate ui direction - even if it starts a lot simpler than generating the code

would you be willing to pay for something that essentially is google inbox - but a separate web view client with more personalization/better search?

I've been working on designing a more intuitive UI that emphasizes user control and simplicity in email. The idea is to make email fun and not the cluttered mess that we are used t…

Hi HN, I am working on a personal project where I'm trying to create an email GUI that I can use for myself. For this, I want to store all my emails in a pinecone index. I want to …

are you using whisper at the backend

Would people be willing to pay for a gmail plugin that takes a stab at combatting ai email spam? something like Mailman [1] but with an LLM layer for detecting AI slop? [1]: https:…

Would you be willing to pay for a gmail plugin that takes a stab at this? something like Mailman [1] but with an LLM layer for detecting AI slop? [1]: https://mailmanhq.com/

A website where different open source models battle each other super Mario bros style - could be cool.

Could you name some?

The generative agents paper takes a pretty decent shot at this I think

I agree on the most part, but I still think some pretty cool games can come up with local LLMs. Suck up for example, though not local afaik, is a pretty cool one.

This is something I was considering as well - thanks

Can you explain further? Why would it not be free if it's running locally

So that the user doesn't have to download anything else - it's packaged with the app itself. And the app uses it to run inference. Is this possible?

Was playing around with this model - why does it return 2 or 3 responses when I ask it for one? I asked it for a json response and it generates 2 or 3 at a time. What's with this.

Thanks! This is helpful. I was thinking about the phi models - those might be useful for this task. Will look into how those can be run locally as well

What? chill out buddy - there's such a thing as timezones I was just sleeping

Since there are some models that can run on most consumer hardware (eg. the phi models) - is there a way to distribute LLMs packaged with whatever app. you're building? So the user…

Is there a way to reliably package these models with existing games and make them run locally? This would virtually make inference free right? What I think is, from my limited unde…

how did you generate the data

yeah that's what I'm saying - it would eliminate inference costs. What I was asking is how feasible is it to package these local llms with another standalone app. For ex. a game