I am building a private text editor that runs LLMs locally https://manzoni.app/
Ask HN: Is anyone doing anything cool with tiny language models?
341–350 of 356 posts
Re: Ask HN: Is anyone doing anything cool with tiny language models?
#342Earlier quoted context omitted.
> I don't know. HN in a nutshell: I've built some cool tech but have no idea if it is helpful or even counter productive...
Real HN in a nutshell: People who don't build stuff telling people who do build stuff that the thing they built is useless :P It's a hacker forum, let people hack! If anything have a dig at OP for posting the thread too soon before the parent commenter has had the chance to gather any data, haha
Great attitude! I recently built a tool for my wife that uses an LLM to automate a task. Is it production ready? Definitely not. But it saves her time even in its current state.
Re: Ask HN: Is anyone doing anything cool with tiny language models?
#343https://gophersignal.com – I built GopherSignal! It's a lightweight tool that summarizes Hacker News articles. For example, here’s what it outputs for this very post, "Ask HN: Is anyone doing anything cool with tiny language models?": "A user inquires about the use of tiny language models for interesting applications, such as spam filtering and cookie notice detection. A developer shares their experience with using O…
RSS plz?
Re: Ask HN: Is anyone doing anything cool with tiny language models?
#344https://gophersignal.com – I built GopherSignal! It's a lightweight tool that summarizes Hacker News articles. For example, here’s what it outputs for this very post, "Ask HN: Is anyone doing anything cool with tiny language models?": "A user inquires about the use of tiny language models for interesting applications, such as spam filtering and cookie notice detection. A developer shares their experience with using O…
RSS plz?
Hey, thanks for checking out GopherSignal! RSS is a great idea—I’ll be starting on it this weekend. Appreciate the suggestion!
Re: Ask HN: Is anyone doing anything cool with tiny language models?
#345https://gophersignal.com – I built GopherSignal! It's a lightweight tool that summarizes Hacker News articles. For example, here’s what it outputs for this very post, "Ask HN: Is anyone doing anything cool with tiny language models?": "A user inquires about the use of tiny language models for interesting applications, such as spam filtering and cookie notice detection. A developer shares their experience with using O…
can you install this into a discord? i volunteer to help. I've been wanting a text-based hackernews chat with alternative moderation.
Hey, thanks for reaching out! The idea of integrating GopherSignal with Discord as a bot or feature is super cool, and I’d love to make that happen. I haven’t worked with Discord bots or automation before, so I’d definitely take you up on your offer to help out with that. If you want to connect, my email is kjzehnder3 [at] gmail [dot] com. Thank u!
Re: Ask HN: Is anyone doing anything cool with tiny language models?
#346Earlier quoted context omitted.
Logical fallacies are oftentimes totally relevant during anything that is not predicate logic. I'm not wrong for saying "The Surgeon General says smoking is bad, you shouldn't smoke." That's a perfectly reasonable appeal to authority.
It's still a fallacy, though. I hope we can agree on that part. If you have something map-reducing audio to timestamps of fallacies by who said them it makes it gamified and you can use the information shown to decide how much weight to give to their words.
btw i have verified that whisper-diarization works, at least on my machine, so all this needs is an LLM finetuned on rhetoric and the type of logic used when discussing fallacies. I know a lot of people like to call it "formal logic" or whatever, but the way i understood it both in college and from my own reading of the books is that the only true formal logic is tautological, everything else is varying shades thereof. Blatant appeals to emotion, uninformed native advertising (appeal to authority, others), Argumentum ad baculum (aside: if you typo that it means a specific bone in the male canine's body and i think that's hardly an accident.)
I got no idea how to finetune or train an LLM. i know how to run inference, lots of it. I also know how to scan and OCR texts, and feed a data ingestion pipeline. I know how to finetune a stable diffusion model, but i doubt that software works with language models...
Re: Ask HN: Is anyone doing anything cool with tiny language models?
#347Earlier quoted context omitted.
I mean you're not op but his comment was saying > Interesting idea. But those say what’s in the commit. The commit diff already tells you that. The best commit messages IMO tell you why you did it and what value was delivered. Which doesn't include what was done. Your example includes both which is fine. But not including what the commit does in the message is an antipattern imho. Everything else that is added is a b…
Many changes require multiple smaller changes, so this is not always possible. For me the commit message should tell me the what/why and the diff is the how. It's great to understand if, for example, a change was intentional or a bug. Many times when searching for the source of a bug I could not tell if the line changed was intentional or a mistake because the commit message was simply repeating what was on the diff.…
I don't know when do you think I wrote that "the how" was needed because of course it's not needed. Again, OP wrote about just having "the why" in the message which is bad imho and you need "the what" there as well. As per your commit, the title is "fix crash when enabling pass-through port" which is exactly what I mean - it says what was done in a clear manner.
Re: Ask HN: Is anyone doing anything cool with tiny language models?
#348I am building GitHub-Copilot style AI autocomplete in any text field on your Mac. The point is to have the AI fill in all the redundant words required by human language, while you provide the entropy (i.e. the words that are unique to what you are trying to express). It is kind of a "dance" between accepting the AI's suggested words and typing yourself to keep it going in the right direction. Using it, I find myself…
Can vouch for cotypist - it's great!
Re: Ask HN: Is anyone doing anything cool with tiny language models?
#349Earlier quoted context omitted.
Do you find that it actually generates varied and diverse stories? Or does it just fall into the same 3 grooves? Last week I tried to get an LLM (one of the recent Llama models running through Groq, it was 70B I believe) to produce randomly generated prompts in a variety of styles and it kept producing cyberpunk scifi stuff. When I told it to stop doing cyberpunk scifi stuff it went completely to wild west.
Someone mentioned generating millions of (very short) stories with an LLM a few weeks ago: https://news.ycombinator.com/item?id=42577644 They linked to an interactive explorer that nicely shows the diversity of the dataset, and the HF repo links to the GitHub repo that has the code that generated the stories: https://github.com/lennart-finke/simple_stories_generate So, it seems there are ways to get varied stories.
I was wondering where the traffic came from, thanks for mentioning it!
Re: Ask HN: Is anyone doing anything cool with tiny language models?
#350I built an Excel Add-In that allows my girlfriend to quickly filter 7000 paper titles and abstracts for a review paper that she is writing [1]. It uses Gemma 2 2b which is a wonderful little model that can run on her laptop CPU. It works surprisingly well for this kind of binary classification task. The nice thing is that she can copy/paste the titles and abstracts in to two columns and write e.g. "=PROMPT(A1:B1, "If…
Tried it out, very cool! Fun to see it chugging on a bunch of rows. Had a weird issue where it would recompute values endlessly when I used it in a table, but I had another table it worked with so not sure what that was about
Probably would want to run with Manual calculation set on your sheet if using this.