101–110 of 112 posts
For me: A local model to plug in to Apple photos to look for metadata inconsistencies in my photo librar, add missing location information, add dates from those old scanned photos with the date on the corner.
Earlier quoted context omitted.
Do you not think that’s what the post meant? That it could work for us rather than them?
They probably won’t though. The commercial LLMs will be tuned to work for them as well soon. And your local LLM won’t be allowed to scrape the internet since it’s all locked down now.
On your request 12 > A local screen recording app but it uses local models to create detailed semantic summaries of what I’m doing each day on my computer. This should then be provided as context for a chat app. I want to ask things like “Who did I forget to respond to yesterday?” I've been using Rewind for a year now, and it's nowhere near as useful as it should be. I am building something like this but unfortunatel…
Not just for this article, but from most ideas/articles around LLMs, I feel like they aren't "thinking with portals" enough. We have "portal gun" tech (or at least, that's what's being marketed), and we're using it as better doors.
Could you give a quick example so we can "catch" the way of thinking you mean a little easier?
I guess it's more "following through to its logical conclusion", but I'm more of a cynic.
A few of them imply a vision model which can control your keyboard and mouse. Offline-only of course. It could help with most tech support questions. We could select text and ask to fact check or explain to layperson or search more. It could get around cookie banners and dark patterns. It could do my time tracking and tell me to get off HN and optimize Pomodoro-style breaks. It could write scripts after watching me s…
Feeling this one hard. Especially frustrating given how AWS has introduced multiple competing (mediocre) services to do this and they are all difficult to either discover and setup, or chat-based (Q).
Earlier quoted context omitted.
> Any app that ever claimed to tell you what "Hemingway would say about this blog post" would evidently be lying — it'd be giving you what that specific AI model generates in response to such a prompt. First, 100% agreed. That said, I found myself pondering Star Trek: TNG episodes with the holodeck, and recreations of individuals (e.g. Einstein, Freud). In those episodes - as a viewer - it really never occurred to me…
In that context, the computer was solving for a faithful representation. In our case, the computer is solving for most likely sequence of words to appear in conversations with a similar context - which not remotely the same thing.
Was it, though?
They had Newton (died 1727) playing playing poker (invented at some point during the early 19th century), repeating the myth that the apple fell on his head and then reacting insulted when Data says "that story is generally considered to be apocryphal".
More generally:
In TNG, Holo-Moriarty claimed to be sentient and to have experienced time while switched off despite Barclay saying that wasn't possible, much like LLMs sometimes write of experiencing being bored and lonely between chat sessions despite that not being possible given how they work.
In DS9, there was a holo-village made out of grief, and when it got switched off to reveal the one real person who had made it, while the main cast treated all the holograms as people, that creator himself didn't. Vic Fontaine was ambiguous, being a hologram who knew he was a hologram but still preferring to keep his (fake) world to its own rules and eventually kicking Nog out of the fake world when it was becoming clear Nog was getting too swept up in the fantasy.
In Voyager, the Doctor was again ambiguously person and/or program, both fighting for his moral rights as an author in a lower-stakes echo of TNG's Measure of a Man, and also Janeway being unsure if he was stuck in a loop or making progress with grief about the death of Ensign Never-Before-Mentioned-In-This-Show.
On the topic of "24. A Sony Walkman-style device that you can give to children so they can ask questions to an LLM...", I would strongly caution against this: - short of AGI, what a child will hear are explanations given with authority, which would probably be correct a very high percentage of the time (maybe even close to or above 99%), BUT the few incorrect answers and subtles misconceptions finding their way in th…
>> child will hear are explanations given with authority, which would probably be correct a very high percentage of the time (maybe even close to or above 99%), BUT the few incorrect answers and subtles misconceptions finding their way in there will be catastrophic for the learning journey because they will be believed blindly by the child. Much better results than asking a real teacher at school, though.
An AI walkman removes this aspect of the interaction. As a parent, this is not something I would want my children to use regularly.