In the context of LLMs memory can often mean a broadly defined, application-specific ability to detect, retain and re-use bits of useful context along the journey. In contrast to Persistence which is more like a DB with a schema and clear expectations, reliability, etc.
Totally agree. Persistence is a huge part of what we usually mean by state. Nothing stops this from plugging into a real database when needed. But also, nothing stops us from rethinking what a database even is, especially in a world where LLMs have growing context windows and can carry more state internally. Maybe persistence doesn’t always have to mean "write to disk."
good question. I think it'll be self-reinforcing, since the context keeps growing with everything the software has done for you, along with every interaction you’ve ever had with it.
honestly, kind of both. it started as a curiosity. I just wanted to see if it could even work. but after playing with it, I think there’s something deeper.
the most interesting part to me is the idea of apps that self-customize without being told to. they adapt based on how you use them and what you enter, not from settings or configuration. stuff that changes itself in real time, just by being used. we wouldn't build that kind of software today because it's too weird or specific. but with this, it just happens.
still super early and pretty rough, but it feels like a door opened a crack.
Speaking of the AirPods becoming actual hearing aides - how will we reconcile the fact that it is not socially acceptable to wear AirPods when speaking with someone?
Even if you get to explain ‘oh my AirPods are functioning as a hearing aide’ you likely won’t be able to explain that to other people noticing the conversation and thinking to themselves ‘oh that’s douchey, not taking our your AirPods when talking to someone’.
I just really wonder if this will be able to make wearing AirPods while talking to other people socially acceptable because the current presumption is likely that they are not behaving nicely.
In 1998 Assembly programmers who typically participated in Demo competitions did a series of size coding challenges. The first one was a Snake game (Nibbles), all in a DOS environment. The winning entry was 48 bytes long.
There were also some creative attempts that took less than 48 bytes and got disqualified. One of those encode the entire game in a series of empty folders using the folder names.
Edit: the original Hugo size coding competitions were created by Claus-Dieter Volko (Alias: Adok).
I recently utilized Netlify for this. My build was actually my scraper and I used their Scheduled Functions (cron) to trigger this build every so often.
Fantastic, thank you for implementing one of my future side projects.
I was planning to build a web-based version of Soulver with sharing/collaboration. I hope this can fill that spot for me.
One thing I couldn’t figure out by skimming through the article is who performs the actual authentication (checking if an item is counterfeit)? Is it the two founders? Do they have a team working on this?
Phrasing can always be better but the point is that there's a way to map your DNS to Netlify which is risky and Netlify hasn't made the aggressive decision of blocking it. They outline in their docs all the reasons why you shouldn't do it, provide instructions for how to avoid it and also offer (but do not require) a hosted DNS setup which avoids this pitfall by design.
Some folks still choose to use this way, some have no other choice for various reasons and some don't care/comprehend the potential pitfalls. I do believe most users avoid using a root domain name for their website.
Thanks, founder of Stackbit here. We currently support NextJS, Gatsby, Hugo and Jekyll with many more coming soon (e.g. Eleventy). One of our goals is being tech agnostic as we want to empower developers to pick the best tool for the job.