They've got an openai + anthropic compatible endpoints. I got far enough to run some tests on the openai endpoint, albeit with some finagling (their /models list is empty, my tool auto-configures using that, was an initial stumble).
what model did you try it with? I agree and also push back a bit: How will we know when the LLMs reach the point of handling it if no one takes the leap? I applaud more people sludging through the slop and hauling their slop buckets around.
An example is Fable being released. I felt like the most complex thing I was willing to sludge through was having it clone llama-server's web UI with my own opinions (I really like the original, kudos to them). And the initial skeleton was working so well I felt like I had sunk the tokens and committed to getting it the rest of the way: https://inkcap.click
I'll agree and expand on "weird restrictions" -- I used to check the claude usage graphs multiple times a day to see where I'm at on my weekly budget. With gpt 5.5 I don't think I'm working differently but haven't felt the need to check anything because I think I've hit my limit... once? on some egregious edge case scenario iirc
Probably not _as_ good, but you can run gemma 4 for the ears/brain (accepts audio input), and kokoro TTS for the mouth. You want something like silero VAD sitting in front of the LLM so you aren't passing wasteful audio to gemma 4, so you send only voice activity segments. I type all this because I tried it out recently as a Zork experience, seeing how creative Gemma 4 12B could be. It was surprisingly good!
The best project I found to throw it at was cloning llama-server's web UI essentially in one shot. I'm not sure what I'll do with 5 extra days, maybe try to imagine some complex features. I'm no longer surprised at how much seems to work in these "new brain what can it do?" test, and instead think the risk is feeling like I have to take it the rest of the way once I've sunk the token cost :| https://inkcap.click
Lately I've been following https://loco.rs/ as it aims for a rails-like experience, complete with generators for workers, controllers, etc. I've only had time to experiment but it's the closest I've gotten to feeling rails-y in rust.
> In 2024, everyone looking for a code editor knows how to extract a tar.gz right?
I'll raise my hand and say I still get the `tar` terminal command options confused and have to pause and figure out the file format I'm dealing with and the options. So, no, I usually don't know, and have to look it up in the manpage/help. "Was it -xvfz for this one? Shit I just did this recently..."
I helped write what might be a similar API gateway prototype in rails (made a DB query and decorated downstream requests with auth/role/etc headers). You might have threadpool/process/concurrency tuning to do. Even then, I don't think rails is a good solution for what is essentially an HTTP proxy, and I would've pushed for a different tool if time wasn't an issue. Rails was fast to build, I'll give it that. We ended up getting downstream service to $1M ARR so rails wins out against my "let me write it in XYZ language/framework" again somehow.
Came to upvote this. I think that github component in particular worked really well for me on a recent experiment. Server-rendered HTML can use custom components in our fancy world today! It's a feel-good place to be compared to just a decade ago imo.
I'll throw out the the GTFS transit standard involves publishing zipped CSVs representing your DB tables regularly. There are nice things about it and downsides IMO. This is how google map's transit directions function -- they rely on agencies to publish their schedules regularly in zipped CSVs I think.
One downside is that dev experience is pretty bad in my opinion. It took me years of fiddling in my free time to realize that if you happen to try to use the CSVs near a schedule change, you don't know what data you're missing, or that you're missing data, until you go to use it. My local agency doesn't publish historical CSVs so if you just missed that old CSV and need it, you're relying on the community to have a copy somewhere. Similarly, if a schedule change just happened but you failed to download the CSV, you don't know until you go to match up IDs in the APIs.
I still have my OG backlit kindle. It's showing its age with a tiny tear that lets backlight through, but I'm still pushing through books on it. I'd be curious how these newer E-ink displays have improved, wonder what the refresh rate (hz?) is on them.
just in case I confused: i'm not sure mold helps with the size of that directory :D. I was commenting on how big my rust repo is really, just saying that mold seems to help big builds like mine