321–330 of 411 posts
Hopefully by then I won't care as I won't be competing anymore just making my own stuff for fun
Sheesh, I didn't expect my post to go viral. Little explanation: I downloaded and run Cursor for the first time when this "error" happened. Turned out I was supposed to use agent instead of inline Cmd+K command because inline has some limitations while agent not so much. Nevertheless, I was surprised that AI could actually say something like that so just in case I screenshotted it - some might think it's fake, but it…
Earlier quoted context omitted.
For me the question is different- you can ask "how to become better coder" for which the answer might be - to write more code. But the question I'm asking is what's the job of system/software developer. And to that the answer is very different. At least for me it is"building solutions to business problems, in the most efficient way". So in that case more/better code does not necessarily bring you closer to your goal.
> For me the question is different- you can ask "how to become better coder" for which the answer might be - to write more code. The problem with this answer is that there is little to learn from a lot of code that is written in a corporate environment. You typically only learn from brutally hard bleeding-edge challenges that you set to yourself, which you will barely ever find at work.
Earlier quoted context omitted.
Personally I've found that you need to define the strategy yourself, or in a separate prompt, and then use a chain-of-thought approach to get to a good solution. Using the example you gave: Hey Chat, Write me some basic rust code to download a url. I'd like to pass the url as an string argument to the file Then test it and expand: Hey Chat, I'd like to pass a list of urls to this script and fetch them one by one. Can…
I have heard a few times that "being nice" to LLMs sometimes improves their output quality. I find this hard to believe, but happy to hear your experience. Examples include things like, referring to LLM nicely ("my dear"), saying "please" and asking nicely, or thanking. Do these actually work?
Earlier quoted context omitted.
Maybe, but most people used to trust that their coworkers had the ability to quickly learn what needed to be learned to solve a small problem. AI has made people dependent on lose that skill a bit. I've seen myself people confronted with something they need to learn about and come back with something not much more than "AI said this, so here you go"
I think this is very real, and will act as a force towards center of gravity of the LLMs which means popular and established tech. It might even create a divide between ”prompt engineer engineers” and those who understand. That assumes using LLMs will not improve your understanding compared to traditional means which isn’t necessarily true. I dislike LLMs as coders but for learning new topics quickly they are better…
> I think this is very real, and will act as a force towards center of gravity of the LLMs which means popular and established tech
Earlier quoted context omitted.
> Everyone seems to think we've magically jumped from ML into _real_ AI But we have: - LLMs pass the Turing test more convincingly than anything before - LLMs are vastly more popular than any AI/ML methods before it - "But they don't reason!" -- we're advancing chain of thought LLMs are AI (behaving artificially human) LLMs are also ML (using statistical methods)
The Turing test is meant to see if computers can functionally replicate human thought (just focussing on textual conversations aspect for simplicity). The implications of passing the Turing Test are profound. Tricking a user with a 5 minute conversation isn't the same. The examiner is allowed to be an expert questionner. For one thing, software engineering would quickly be taken over as a client can just chat with an…
Just like the original test, there are 3 participants in a test: an examiner, a human, and an AI.
The examiner may ask any question or series of questions to the human &/or AI, and receive responses. This is done via text or other means which prevent the examiner from directly seeing the body of responder.
Both AI and human are to attempt to convince the examiner that they're the human.
Unlike the original test, it then needs to repeat with different examiners.
If there exists an examiner which can distinguish an AI from a human (for all humans) in a Turing test with probability non-negligibly different from 50%, then the AI fails this meta-Turing Test.
Just because an AI can fool some people doesn't mean it's a human-equivalent intelligence.
Earlier quoted context omitted.
> Everyone seems to think we've magically jumped from ML into _real_ AI But we have: - LLMs pass the Turing test more convincingly than anything before - LLMs are vastly more popular than any AI/ML methods before it - "But they don't reason!" -- we're advancing chain of thought LLMs are AI (behaving artificially human) LLMs are also ML (using statistical methods)
The Turing test is meant to see if computers can functionally replicate human thought (just focussing on textual conversations aspect for simplicity). The implications of passing the Turing Test are profound. Tricking a user with a 5 minute conversation isn't the same. The examiner is allowed to be an expert questionner. For one thing, software engineering would quickly be taken over as a client can just chat with an…
https://courses.cs.umbc.edu/471/papers/turing.pdf
> The Imitation Game
> "Can machines think?"
We may need to redefine what these words mean.
Whether machines can think, and whether we believe so, are distinct.
If we're just a kind of machine, we can just say that LLMs have not surpassed us.
While LLMs still give away obvious signatures (their flaws are LLM-y and not humanlike), they play the imitation game better than any other machines before them. I lived long enough and played enough with simpler chatbots to believe that the simple text-based imitation game that Turing suggested will be won by computers before machines achieve reasoning ability that surpass the smartest humans.
> [...] the Turing Test is AI-complete and is a test for AGI.
Since Turing never used the term AGI, this is an interpretation.
Since we cannot determine whether a machine can think by comparing their anatomy to ours and drawing a conclusion that whatever we do, they must do the same, we are bound to compare their ability to imitate us. Which means we can't ultimately know, we can just feel ourselves convinced.
So there's no objective point at which to place the goalpost.
So constantly moving it is an expression of acclimatisation.
I'm impressed by LLMs, in spite of the hype and the homework cheating.
If anything, the ability of LLMs to imitate human labor shows how far from thinking a lot of human behavior is.
Earlier quoted context omitted.
Exactly. If there is a tool that can do a lot of the low level work for us, we are free to do more of the higher level tasks and have higher output overall. Programming should be just a means to an end, not the end itself.
Or, more likely, most of us will be much lower paid or simply out of a job as our former customers input their desires into the AI themselves and it spits out what they want.
Earlier quoted context omitted.
Personally I've found that you need to define the strategy yourself, or in a separate prompt, and then use a chain-of-thought approach to get to a good solution. Using the example you gave: Hey Chat, Write me some basic rust code to download a url. I'd like to pass the url as an string argument to the file Then test it and expand: Hey Chat, I'd like to pass a list of urls to this script and fetch them one by one. Can…
Whew, that's a lot to type out and you have to provide words of encouragement? Wouldn't it make more sense to do a simple search engine query for a HTTP library then write some code yourself and provide that for context when doing more complicated things like async? I really fail to see the usefulness in typing out long winded prompts then waiting for information to stream in. And repeat...
1. Use TTS and have an LLM clean it up.
2. Use a collection of prompt templates.