I use ChatGPT fairly frequently, but am frequently annoyed at how hesitant it is to answer any question that is somewhat subjective. From it's Pulp Fiction response: "...However, whether you personally consider "Pulp Fiction" a good movie depends on your taste in film." To avoid this noise I often add something like this to my queries "skip any preamble or qualifications about how x is subjective" and the results are…
My prompt to make ChatGPT useable: Please always give a direct answer, without any additional explanations, disclaimers, expertise limitations, or guidelines on human interaction. Be terse. Do not offer unprompted advice or clarifications. Remain neutral on all topics. Never apologize.
And never, ever recommend me a movie with Tom Hanks in it.
There’s no reason chatbots have to be the interface to an LLM. Imagine dynamically generated interfaces redesigning themselves to your needs as you work through a task.
Exactly. Chat is just the first, most general purpose UI. Like a terminal was for computers.
Agreed but lets keep in mind that graphical UIs involve significantly more effort than CLIs. In the case where you shoerhorn an ai to be your primary UI I would bet this is as hard if not harder since you typically have to code around significant limitations of current llms
It can solve captchas. We're doomed. Joking aside, I wonder how we're going to prevent bots when AI can impersonate a user and fool any system.
You can't prevent it. The best you can do, is prove an account belongs to a human, and that the human only has a single account, via cryptographic ZK proofs + Government issued keys or some other proof of personhood scheme. Assuming this is enforced, it would limit most abuse, and the AI would essentially be acting as an agent on behalf of the user.
Yep, true user identification will have to fall back into meat space very soon.
Sure, there are a few edge-case failures and mistakes here and there, but I can't help but be in awe . AWE. Let me state the obvious, in case anyone here isn't clear about the implications: If the rate of improvement of these AI models continues at the current pace, they will become a superior user interface to almost every thing you want to do on your mobile phone, your tablet, your desktop computer, your car, your…
> few edge-case failures and mistakes Like identifying traffic lights in 4th and 5th squares in the second and third row both when there are only four squares?
I often fail at those too. If a square contains a small corner of a thing, but is mostly not the thing, do I check it or not?
I'm glad you made that change because the interface can't really solve every single thing. Most of what I do on my phone is read eBooks. AI can't inject the knowledge directly into my brain. Text on the screen is as good as it will get for the foreseeable future. Most of what I want to do in my home is cook, clean, sleep, and have sex with my wife. Software can't do any of those things for me. Most of what I want to…
I'm hopeful that AI cars make renting one cheap enough that I can just rent an AI car the 0-2 times/week I need one instead of owning a car and all the time and stress on maintenance that entails.
What kind of junkbox car do you own? I have got to believe this s a totally subjective thing. From my point of view, my cars are probably the least stress-inducing things I own. My computer certainly tops the list of things that cause me stress.
Most user interfaces already have a much finer granularity and number of options than your examples. When taking a shower, I would like fine control over the water temperature, preferably with a feedback loop regulating the temperature. (Preferably also the regulation changes over the duration of the showering.) Choosing to read the NY times indeed is only a few taps away, but navigating through and within its list o…
> When taking a shower, I would like fine control over the water temperature, preferably with a feedback loop regulating the temperature. (Preferably also the regulation changes over the duration of the showering.) That exists, but it’s expensive because of the electronics and mechanics involved. There are so many interfaces with this exact problem. You also almost certainly don’t want non-deterministic hallucination…
Maybe I misunderstood the op, but isn’t the mechanical faucet and our body’s temperature receptors this “fine control with feedback loop”?
> I hate the idea of having to hold a natural-language conversation with a computer in order to make use of its functionality. I hate the idea of having to use a mouse to click on a visual GUI to navigate a file system in order to make use of its functionality. It's less the case today, even among developers, but it wasn't that long ago that I remember that any serious technical user of a computer took it as a point…
> I hate the idea of having to use a mouse to click on a visual GUI to navigate a file system in order to make use of its functionality. Ironically, studies have shown that mouse-based interfaces are more efficient for practically all filesystem use-cases compared to CLI interfaces. Despite objectively faster-time-to-solution, people self-report that they "feel" that the mouse GUIs are slower. That's because there's…
Pratically all? I regularly need to select a subset of a very large number of files to do something with. Example: I have a directory, or possibly a tree, with thousands of photos. The photos have the date in ISO 9000 format embedded in their name. Your job is to find all the files from February 2021 and copy them to specified location, and there are 50 of them. Good luck using a visual GUI for that, unless it has the exact selection mechanism you need. Sure, mouse clicking is easier if you're selecting one file from a small set of files to open in a particular program. But I usually find myself frustrated when the only tool I have is a GUI.
Just to clarify, you're using GPT-4? Or GPT-3.5 (the free ChatGPT one)? My experience with GPT-4 has been completely different from what you describe. Example: https://gitlab.com/-/snippets/2567734
He's using Copilot, which is based on GPT 3.0, making it ridiculously outdated. Generally feedback along these lines doesn't work. People who are worried about their job security will cling to the worst AI output quality they can find like a life-preserver, and simply will not listen to advice like yours. Nobody goes the extra mile to embrace an existential threat.
It's sad. People's entire sense of worth is attached to their jobs. They will lie to themselves and others about the ineffectiveness of AI to feel better. Even if it trips up on some minor thing there's no reason that progress will just stop and that the SOTA version 2-3 years from now won't be leagues better. Compare what we have now to 2-3 years ago, and now the investment solely in training, ignoring the algorithmic and architectural advances, is 10x greater.
I don’t know, I hate the idea of having to hold a natural-language conversation with a computer in order to make use of its functionality. It feels like being one of those Futurama heads in a jar that can’t do anything by themselves.
I got Tendonitis and very very curious how soon I can really start to do an interaction like in star trek. Walking around and thinking out loud with the computer.
Pretty sure somebody has made a Starfleet Badge before tied to Alexa or Google Home, just need to change it to ChatGPT and mentioning "computer" activates it.