HackerTrans
TopNewTrendsCommentsPastAskShowJobs

pianopatrick

131 karmajoined vorig jaar
I teach piano lessons. Have been teaching myself to code for a while and writing software that helps my business.

github.com/patrickjh

Submissions

Simple AI agent in POSIX shell

github.com
2 points·by pianopatrick·7 dagen geleden·1 comments

A prototype of an event driven JavaScript framework

github.com
2 points·by pianopatrick·7 maanden geleden·1 comments

comments

pianopatrick
·19 uur geleden·discuss
Well, you could use jsDoc to hold your types instead of writing them in typescript. The typescript compiler can still check types in jsDoc comments but you do not need a build step and the javascript you ship to the browser would be the same you write in your editor.
pianopatrick
·20 uur geleden·discuss
This month I worked on my own AI agent written in POSIX shell. It's been surprisingly useful for debugging command line problems on an old laptop running linux, like fixing an apt problem.

https://github.com/patrickjh/ssa
pianopatrick
·23 uur geleden·discuss
Seems to me this would get easier or harder depending on how you write the code. Like if you write the code in something standard and unchanging like POSIX shell scripts or C99 or ES5 javascript, at least the ecosystem won't change out from under you. If you use rust or python or a bunch of node.js dependencies then you might have to edit the project just to keep up with ecosystem changes.
pianopatrick
·eergisteren·discuss
Do you have any rough stats on how many total tokens per day you end up using with this setup?
pianopatrick
·3 dagen geleden·discuss
Just spit balling: could you have the agent pre warm the cache as part of your workflow? Like at the start of working on the code have the agent run a compile in the background. That way when the agent is ready to "really" compile there is a warm cache
pianopatrick
·3 dagen geleden·discuss
You should not underestimate how confusing those CLI tools are to people who have never used them before.

For example, I would argue that for someone with no experience, figuring out how to copy a file from one folder to another is easier in Windows Explorer than learning how to use cp.
pianopatrick
·3 dagen geleden·discuss
Let's assume AI is only good at software and math.

If we can use AI to write lots of good software for cheap, that software can automate away a lot of jobs.

So AI does not have to take the jobs directly, software written by AI can.

Especially if that works for software for robots.
pianopatrick
·4 dagen geleden·discuss
I'm curious but don't know much about the internals of LLMs - could you use a similar architecture with other models that have "layers"? I mean, could you have one layer do its work, then remove that layer from RAM, load the next layer from disk, and have that layer activate on the result of the first layer?
pianopatrick
·4 dagen geleden·discuss
Seems like for a hobby project $1 or $2 per task would add up a bit, depending on how many tasks you need to do. I mean it makes sense for a software company
pianopatrick
·5 dagen geleden·discuss
You can look at the mount command and the "sync" option: https://man.openbsd.org/mount

If you're really curious about it, Michael Lucas wrote a full book about the OpenBSD file system.
pianopatrick
·5 dagen geleden·discuss
I believe that while the file system does not have journaling, that can be offset by applications. I.e. I think the SQLite Write Ahead Log would still protect you against data loss even if there's no journal in the file system, assuming you set various settings correctly. So I think it kinda depends on how the applications store data.
pianopatrick
·7 dagen geleden·discuss
Over the last week I wrote a simple AI agent using ~1000 lines of POSIX sh. Makes sandboxing scripts an AI wants to run on your computer relatively straightforward. Lets you prompt the AI by llama.cpp or curl to an OpenAI API endpoint. Feels like a unix util.
pianopatrick
·10 dagen geleden·discuss
If we assume everyone has access to the same AI tools and those tools do help improve output a lot then you get the same prisoner's dilemma as ads.

The people using the AI tools to improve their output will set higher consumer expectations for their product or service. If you do not also use AI, you will not be able to keep up, and so you will lose business over time.

So you have to pay for AI just to keep up with the other people who pay for AI.

But then if everyone is paying for and using AI to improve their product or service, no one can steal market share from each other. So you are all now paying a lot and AI is doing a lot and the buyers are getting better results, but that does not necessarily lead to better financial results in terms of market share, revenue, costs or profits for the business that is now using AI
pianopatrick
·15 dagen geleden·discuss
If people wanted to get really serious you could use a cell phone jammer and have students pass through a mini EMP at the door.
pianopatrick
·15 dagen geleden·discuss
Seems to me that feature requests are not all that unique either.

Seems to me you can get feature requests from user feedback.

I also expect someone will figure out a way to have AI "use" your software and suggest features
pianopatrick
·19 dagen geleden·discuss
There does not seem to be a big penalty for going slow anyways. People seem to just switch on cost as soon as a model can do a task well enough. There do not seem to be strong network effects or vendor lock in.

Seems to me that going slow is the better long term tactic. China can just let the USA pay the high R&D costs to figure out what works, then just copy what works.
pianopatrick
·21 dagen geleden·discuss
I wasn't there but this seems like the same feelings people would have had in the Rust Belt when the first factories started closing and getting a job started getting harder.
pianopatrick
·21 dagen geleden·discuss
An interesting question for me is "can the LLMs predict what humans want?".

Like if you show the LLM a page, can the LLM review the page and then spit out a review that is close to what a human would say about the page?
pianopatrick
·22 dagen geleden·discuss
You could think of the top as translation too. Translate user feedback into a profitable business model. Then translate that business model into a series of projects to make the business model happen.

AI can certainly look at more user feedback than executives can...
pianopatrick
·26 dagen geleden·discuss
Yes, but we were smarter. We may not have the same result against things that are stronger, faster and smarter.

Personally, I think the test for "how safe is Artificial Intelligence" is not how Intelligent it is, but instead how Artificial it is.

Servers in data centers are not that dangerous to people in the physical world. Robots that are smarter, faster and stronger might be.