This is such an amazing piece of work — truly impressive! Hats off to you If it supports Ollama and local LLMs too, it'll be absolutely unbeatable!
Show HN: Clippy – 90s UI for local LLMs
41–50 of 300 posts
Re: Show HN: Clippy – 90s UI for local LLMs
#42Question for the devs in here...something I've been thinking about a lot recently. So I see that OP linked out to a public github repo...but when downloading the actual bundle, what's a quick way for me to determine that what I'm installing on my mac is actually the same as what's in the public repo? It's always seemed like a loophole to me ready for (potential) exploitation. >> Ship project. >> Link out Github repo…
Yeah, reproducible builds would be fantastic.
I sign my binaries on macOS with Apple codesign and notarize - and with Microsoft's Azure trusted signing for Windows. Both operating systems will actually show you a lot of warning dialogs before running anything unsigned. It's far from perfect - but I do wish we'd get more into the habit of signing binaries, even if open source.
Re: Show HN: Clippy – 90s UI for local LLMs
#43Earlier quoted context omitted.
Trademarks have to actually be used to remain enforceable, I think. Not sure MS could claim Clippy after all this time, not that they might not try.
Three fact that it's not a product anymore doesn't mean it's unused; a quick search says they at a minimum used it in 2021: https://www.microsoft.com/en-us/microsoft-365/blog/2021/07/0...
Wow, had no idea. Like a bad penny.
Re: Show HN: Clippy – 90s UI for local LLMs
#44Like phoenix, it rises from the ashes..
Re: Show HN: Clippy – 90s UI for local LLMs
#45IIRC correctly, Clippy’s most famous feature was interrupting you to offer advice. The advice was usually basic/useless/annoying, hence Clippy’s reputation, but a powerful LLM could actually make the original concept work. It would not be simply a chatbot that responds to text, but rather would observe your screen, understand it through a vision model, and give appropriate advice. Things like “did you know there’s an easier way to do what you’re doing”. I don’t think the necessary trust exists yet to do this using public LLM APIs, nor does the hardware to do it locally, but crack either of those and I could see ClipGPT being genuinely useful.
Re: Show HN: Clippy – 90s UI for local LLMs
#46It's weird that when clippy was new I found it to be everything that's wrong with UI design, and today I'm nostalgic for it
Nah, it's not weird. You said it yourself: nostalgia. It's human nature to romanticise the past. I bet you would hate it again if you used it today.
Re: Show HN: Clippy – 90s UI for local LLMs
#47Next up, "Rover" the dog from Microsoft Bob
https://fabulous.systems/posts/2024/06/if-i-ever-get-a-dog-i...
Re: Show HN: Clippy – 90s UI for local LLMs
#48This is a clear case of "Build Something People Want".
After all it was requested almost daily over at x.com
https://x.com/search?q=ai%20bring%20clippy%20back&src=typed_...
Re: Show HN: Clippy – 90s UI for local LLMs
#49IIRC correctly, Clippy’s most famous feature was interrupting you to offer advice. The advice was usually basic/useless/annoying, hence Clippy’s reputation, but a powerful LLM could actually make the original concept work. It would not be simply a chatbot that responds to text, but rather would observe your screen, understand it through a vision model, and give appropriate advice. Things like “did you know there’s an…
We are probably getting closer to that with the newer multimodal LLMs, but you'd almost need to take a screenshot on intervals fed directly to the LLM to provide a sort of chronological context to help it understand what the user is trying to do and gauge the users intentions.
As you say though, I don't know how many people would be comfortable having screenshots of their computer sent arbitrarily to a non-local LLM.
Re: Show HN: Clippy – 90s UI for local LLMs
#50IIRC correctly, Clippy’s most famous feature was interrupting you to offer advice. The advice was usually basic/useless/annoying, hence Clippy’s reputation, but a powerful LLM could actually make the original concept work. It would not be simply a chatbot that responds to text, but rather would observe your screen, understand it through a vision model, and give appropriate advice. Things like “did you know there’s an…
>and give appropriate advice
"It's time to work, Dave"