anotherandrew

This is a post near and dear to my heart. I too am looking for something markdown-centered, static, reasonable for code/technical content and that can embed not just photos but browser-side js graphs based on data within the markdown or REST calls. It’s been a few years since I went down this rabbit hole and I got lost very quickly. Thank you for posting, I’ll be revisiting over the next few days to see what the fediverse has to say!

I’m not sure how you would do that if you are asking about something you don’t have expertise in yet, as it takes the exact same authoritative tone no matter whether the information is real.

I agree – That’s why I’m chalking it up to some kind of healthy sense of skepticism when it comes to trusting authoritative-sounding answers by themselves. e.g. “ok that sounds plausible, let’s see if we can find supporting information on this answer elsewhere or, maybe ask the same question a different way to see if the new answer(s) seem to line up.”

So far, research suggests this is not possible (unsurprisingly, given the nature of LLMs). Introspective outputs, such as certainty or justifications for decisions, do not map closely to the LLM’s actual internal state.

Interesting – I still see them largely as black boxes so reading about how people smarter than me describe the processes is fascinating.

I don’t know if it’s just my age/experience or some kind of innate “horse sense” But I tend to do alright with detecting shit responses, whether they be human trolls or an LLM that is lying through its virtual teeth. I don’t see that as bad news, I see it as understanding the limitations of the system. Perhaps with a reasonable prompt an LLM can be more honest about when it’s hallucinating?

I too contributed fairly significantly over a long period of time, particularly on electronics.stackexchange.com. I generally just ignore the weak/low quality questions or vote them down. I might respond and ask them to fix the question if I felt charitable, but I never understood the “question nazis”.

Completely forgot about kiwix; I have that on my ipad and laptop, along with Dash which is like a modern day HELPPC.COM if anyone remembers that thing…

There are poor personality types everywhere, but I have found stackexchange/stackoverflow to be one of the better sources of user curated help. LLMs are a new and interesting avenue and I’ve had some good success with them too, but Stackoverflow was really, really good.

Grab a copy of the stackoverflow database and use it locally, or train your own local LLM on the datastore.

And if you can, donate to the Internet Archive – those people do really important work in today’s age of killing off old information and constant enshittification.

A couple things I’ve been working on

First, I spun up a larger VPS to consolidate two smaller ones. This time I dockerized almost everything. Still a docker newb, but karakeep, redmine, mbin, lemmy (still deciding which I want), davical. Asterisk and postfix/dovecot are probably gonna stay on the vps root. I’m using zfs and compression. Interestingly, the postgres database that everything is using seems to get better compression than the mail spool.

A couple weeks ago I picked up a NetApp 7 bay disk shelf for $30. It uses fibre channel (AT-FCX) controllers and I’ve never used that before. I grabbed a $7 FC HBA (QLE2560), a 2m cable and an m2-to-PCIe adapter meant for an eGPU. The idea is to see if I can’t get the RK3588 board I’m playing with to see it. I did something similar with a $50 Dell 12 drive bay and my old C6100.

for me, I wish there were a reasonable sized, 2 door EV pickup with an 8’ bed. I don’t want an SUV with a tiny bed but it seems that even in ICE vehicles, they only want to make gigantic 4 doors with small beds. You can find actual pickups but they’re kind of rare.

You could use KaraKeep (formerly Hoarder) with the Hoarder’s Pipette extension maybe?

A full archive of the Japanese TV show Supreme Skills. I can find bits and pieces but I don’t think I even have one complete season.