That’s wrong, you didn’t know that there’s another if/else statement required by them. That’s what the supercomputer is for.
That’s how you sound.
Edit: [Completely new information to me, completely different justification for using a supercomputer over a raspberry pi, now the third attempt (1 it required ocr, 2 forms have different structures, 3 logical relationships between data (if/else statements)).]
Don’t think that’s true. You can run the whole form through, come out with an identical pdf with searchable/copyable text. Even a completely novel form uses the same alphabet. Add some regex to pull out the fields you need to enter, and on failure give it to a human. All of that can be done with python on a raspberry pi. A decade ago.
I don’t think you need hardly any hardware to do ocr. USPS started doing reliable ocr on 80s hardware. You really think an ai cluster is necessary for that?
Anyways, cool anecdote, not an actual financial study or report, and very long-winded honestly.
Post-edit reply: wow, that’s kinda fucked up not to disclose that they disassembled it already. Looks like they found better uses. That’s your success story?
OK, but still, just a clarification like “I’m not buying nor will I ever buy nvidia chips, now here’s a thing I made with ai…” is enough context, in my opinion. Just blindly saying “ai is good for this” is promoting the bubble, as the vast vast majority of llm users are running nvidia chips [either locally or through cloud providers like Anthropic].
Also, whatever financials you showed to convince them it was a good investment, whatever type of business it is, I think it was bullshit. I haven’t seen any proof of efficiency gains at any company rollout of ai, certainly not on macs. Most companies are currently pulling back on token usage is my understanding. ROI has been unmeasurable so far. At best, you informed your clients explicitly this was a highly speculative purchase and may not benefit them.
Edit: []
You are in the 1% of llm users.
Do you think anybody is choosing m2s over nvidia? Everybody running on cpu dreams of being rich enough to do real gold digging on an ampere. Amd is the only direct competitor, an order of magnitude smaller, and supports fewer models. I don’t think any hobbyist has one of these alternatives at the top of their wishlist, they are substitutes.
Congrats, you are in the 1%. And that is exactly the type of additional context I think is necessary when discussing it, thank you.
LLMs are inextricably tied to nvidia gpus. Local or cloud, the technology exists to help the shovel salespeople. The gold diggers, everyone this tag is supposed to segregate, have been misled by corporations. Without their lies, and a pliant media, this tag would be unnecessary, and llms would be rolled out in a more limited and responsible way. To promote different uses of gold during a gold rush is going to inflate the bubble and enrich the rich, unless it is properly contextualized. Technology does not exist in a void, pretending it does digs us a deeper hole.
So there’s my answer: this wasn’t a test, or a learning experience. You can’t go back. The agent is a part owner of your server now, just like the title says. Fixing the race condition I pointed out, addressing the gaping security hole I informed you of, that’s not important. The next step is for the agent to add more greenfield features. That sounds absolutely careless, especially for an torrenting media server reachable from the internet. You’re playing with fire. Are you trying to do a good job with this hobby? To learn about how servers work, how the internet works? Or are you trying to do ‘science’ with llms and think you are above all sysadmin work, like every other ai bro in every other professional field?
I appreciate that, I spent time trying to write as clearly as possible, and it hurt to have someone, either through negligence or malice, completely misunderstand me. I still don’t see how the natural language part relates to creating systems without interfaces. An interfaceless system is nonsense, it doesn’t exist, it just betrays a lack of understanding. Even black holes have interfaces. The log files are an interface. The other interface you mentioned was actually a system to aggregate log files, and I just have to point out that systems are different from interfaces. The interface in that case would be the resulting directory of files, or maybe it could be a streaming interface directly into an llm. But anyways the thing that really bugged me was I was asking about the use indeterminate systems to replace solved deterministic problems, and your response was something along the lines of ‘yeah I agree, add more llm!’ and I would be upset if anybody passing through thought that you and I agreed on that.
I’m sorry if my comment came off as rude, I’m having a bad hair day.
Sorry I know you probably don’t want another tip from me, but the post did include the agent directly using the docker daemon, which runs as root typically. Because you didn’t mention running rootless docker or podman, your sudoers file probably allows the agent full access to root instead of preventing it.
I don’t think you understand what an interface is, I don’t think you understood my comment, and my suspicion is you probably can’t or won’t even if I try to help clarify.
Wow amazing, an llm that can generate text!
I’m still curious though if you are going to change your approach after this test.
What answer did you arrive at? Are you planning on ending the test?
I knew dockhand/portainer would do docker updates better, i knew auto updates can be setup via cron for os updates, etc.
Well, that could’ve been mentioned? Why did I have to bring that up? Nothing about the post is self reflective, it is entirely bragging. I get you didn’t write it, and that’s just how llms sound, but you did decide to post it.
Are you working at an ai startup or university? I asked op for their motivations, and comparisons to existing solutions seemed like the least of their concerns, maybe even unconsidered. But I guess it could be a fair answer from your pov if you are trying to test and improve llms. I just hope you’re getting paid for the research.
There is no comparison, I made the comparison myself. In all honesty I feel like they didn’t know about basic docker and linux concepts until my comment.
I guess I’m confused… The built in functionality seems like the easier way to accomplish the same, you seemed to have spent a large amount of time and are proud of this project, and wanted to share it, but also acknowledge that it’s worse than what already exists, and uses more resources idly. Why should anybody else do this?
Yes! GNU Shepherd >>> systemd, it’s older, wiser, and unbloated.
X11 is still my favorite though, no particular reason.
It seems the main use case is restarting docker containers, why not use the built-in healthcheck feature of docker? The automatic backup and upgrade are also confusing to me, operating systems come with that built in. I just don’t quite understand the point of replacing existing deterministic systems with a natural language interface, I would have trouble believing the logs at face value.
Edit: also your handling of current-alert.txt is a perfect example of a race condition, another potential source of indeterminism. An alert could be missed if the file is overwritten before being handled.
This is the only technical detail [about the need for an llm cluster] in the whole 500 word comment.
Edit: []