Aider is in development for almost 2 years now. Publishing another tool that "offers significant improvements" will have to catch up first.
Having options is a good thing, and approaching the dev agent problem space from a different perspective will help with pushing ideas in other products as well.
There is always room for more tools. How many database exist? Front end frameworks? Languages? Backend frameworks? Analytics packages?
To think that in this space there is only one solution and all others are just outright failures or not worth doing is weird thinking as that isn't normally how it works. There are usually multiple niches and success/revenue strategies.
I strongly think this is the future of software development. And thus there will be many winners here.
There's llms.txt [0], but it's not gaining much popularity.
My web framework of choice provides these [1], but they're not easily injected into the LLM context without much fuss. It would be a game changer if more LLM tools implemented them.
I've had the same thoughts on those. Maybe it also allows them to gather data on whether/how people interact with a webpage itself, which may be an indicator for its quality.
Hmm I’d like to hear more from Kagi on this. They make a point of not logging searches by their subscribers. If this widget is available to non-subscribers outside of Kagi.com, do the same privacy-first principles apply?
In addition to the initial loading time noted by the other posters:
You may want to use the same inference engine or even the same LLM for multiple purposes in multiple applications.
Also, which is a huge factor in my opinion, is getting your machine, environment and OS into a state that can't run the models efficiently. It wasn't trivial to me. Putting all this complexity inside a container (and therefore "server") helps tremendously, a) in setting everything up initially and b) keeping up with the constant improvements and updates that are happening regularly.
Yes, too much water on the beans can lead to water gathering on the burrs, which can lead to rust on the burrs.
I use the teaspoon method (just the handle), cover it in water and stir the beans a couple of times. Just a single data point, but I've done this for 2 years at ~2.5 shots a day with no sign of rust on the burrs. YMMV
Hey folks! I'm a motivated, generalist full stack software developer that builds on strong, practical fundamentals. I'm always looking to learn something new and expand my knowledge. I write software for more than 2 decades now, and currently focus on sustainable and accessible web development.
I'd love to find a remote position with a positive impact on the world, and a place where I can build awesome stuff with awesome people. I'd welcome a part-time position as well, if possible.
Hey folks! I'm a motivated, generalist full stack software developer that builds on strong, practical fundamentals. I'm always looking to learn something new and expand my knowledge. I write software for more than 2 decades now, and currently focus on sustainable and accessible web development.
I'd love to find a remote position with a positive impact on the world, and a place where I can build awesome stuff with awesome people. I'd welcome a part-time position as well, if possible.
This. And proper line breaks help a lot, too. There's a reason single line breaks are ignored.
> People have mentioned tables here, and...yeah, they're messy, ...
IIRC, the "original" markdown does not include tables. They've been added by GitHub (I think), because it made sense for them, and many parsers started to adopt. I agree they are not easily readable in "source mode". It helps to properly align stuff, though, but it's a PITA.
> proper line breaks help a lot, too. There's a reason single line breaks are ignored.
Documents that don't hard-wrap (they could opt to hard-wrap without consequence, to your point), when viewed somewhere that doesn't make it trivial to engage soft-wrap, are much more of an issue than the tag barf mentioned earlier, IMHO.
These lanes and pull outs aren't common everywhere. When I visited NZ, it took me a day or two to realize they had a purpose. RVers usually are not driving in their home country.
I just recently tried to use the side lane in DK to let others pass (set signal, decelerate, pull over as far as possible). It actually confused the other drivers so much that they didn't dare to take over, even when there was lots of space to do so.
Seconded, I was really confused until I watched a video shared. Never seen one of those in my life and I've done a lot of back road driving on the east coast. Typically we'll just have labeled passing zones.
Having options is a good thing, and approaching the dev agent problem space from a different perspective will help with pushing ideas in other products as well.