1,530 karma · joined October 29, 2016
There are groups that would love to be in full control of visible information and parents rightly concerned about social media use by kids.
I just give an LLM a list of files, a set of steps and timestamps, a directory to work in and have it write a bash script that calls ffmpeg. I just view the source videos with VLC and get the timestamps I want.
I mostly use this to edit my YouTube videos and this really beats importing files, dragging things around and all that and it only takes a few minutes to edit now.
Initially I was lonely occasionally during the day but it went away. I'm now perfectly comfortable with no human contact except comments (like this) on the internet for very long stretches. My girlfriend went on a 3 week trip to visit family last year and I visited town twice and saw a friend once during that time and had one long phone conversation with a brother. It was a perfectly comfortable 3 weeks. I don't play video games.
I'm not recommending this way of life. It's probably more psychologically healthy to have people around and so I have to recommend trying to rebuild social connections as you can, but the point is for your situation, it gets much more comfortable as time passes. I don't want to say "it's all in your head" but something along the lines of that sentiment is kind of how it works I think. You do need something to do, a reason to get up in the morning. I garden and keep animals.
"Top Talent". Ya, no not generally. Not from H1B. May get OK talent from time to time.
I've been playing with various mineral amendments for years and produce some extremely tasty produce I have yet to see matched in stores (even the organic section).
It seriously got me laughing. Thanks.
But I wanted to build some desktop apps and look at arcGIS so I finally installed Windows 11 on a laptop my first Windows in nearly 2 decades.
This was a month ago and I haven't opened the laptop since. But I'm going to soon maybe!
Previously I tried to use Aider and openAI about 6 or 7 months ago and it was terrible mess. I went back to pasting snippets in the browser chat window until a few weeks ago and thought agents were mostly hype (was wrong).
I keep a browser chat window open to talk about the project at a higher level. I'll post command line output like `ls` and `cat` to the higher level chat and use Codex strictly for coding. I haven't tried to one shot anything. I just give it a smallish piece of work at a time and check as it goes in a separate terminal window. I make the commits and delete files (if needed) and anything administrative. I don't have any special agent instructions. I do give Codex good hints on where to look or how to handle things.
It's probably a bit slower than what some people are doing but it's still very fast and so far has worked well. I'm a bit cautious because of my previous experience with Aider which was like roller skating drunk while juggling open straight razors and which did nothing but make a huge mess (to be fair I didn't spend much time trying to tame it).
I'm not sold on Codex or openAI compared to other models and will likely try other agents later, but so far it's been good.
Reminds me of an offshore project I was involved with at one point. It had something like 7 managers and 4 years and over 30 developers had worked on it. The billing had reached into the millions. It was full of never ending bugs. The amount of "extra" code and abstractions and interfaces was stuff of legends.
It was actually a month or three simple crud project for a 2 man development team.
And yes, I do understand the code and what is happening and did have to make a couple of adjustments manually.
I don't know that reducing coding work justifies the current valuations, but I wouldn't say it's "not going all that well".
My guess is only a subset of the population is willing to both A) Use a substance like street fentanyl with known lethality. and B) Do so in a risky and unsafe manner (alone, no narcan, shooting instead of smoking, etc. etc.).
That subset of the population has already been decimated to the point we are seeing a decrease, and survivors have become more educated on how to use without dying.
"do llms give wrong information often?"
"Yes. Large language models produce incorrect information at a non-trivial rate, and the rate is highly task-dependent."
But wait, it could be lying and they actually don't give false information often! But if that were the case, it would then verify they give false information at a non trivial rate because I don't ask it that much stuff.
That being said, I do agree with your general point. These tools are useful for exploring topics and answers, we just need to stay realistic about the current accuracy and bias (eager to agree).