How is this made!?

David L. Mayer, David Faber, Brian Hoods, Jonathan Turley and Jonathan Zittrain.

Tell me about these people and what they all have in common.

Try this prompt

You've completely misunderstood as others have pointed out to you. It's great that you want to learn about this stuff, but you have a long ways to go before you are at a point to talk authoritatively about it. The best thing for you to do now is to set aside all your preconceived notions and start from the beginning with an open mind. There is no point in talking authoritatively before you spend some time learning.

This is an issue with many humans I've hired, though. Maybe they try to cut corners and do a shitty job, but I occasionally check, if they are bad at their job, I warn them, correct them, maybe eventually fire them. For lots of stuff, AI can be interacted with in a very similar way.

This is so similar to many people's complaints with self driving cars. Sure, accidents will still be had, they are not perfect, but neither are human drivers. If we hold AI to some standard that is way beyond people then yes, it's not there, but if we say it just needs to be better than people, then it is there for many applications, but more importantly, it is rapidly improving. Even if it was only as good as people at something, it is still way cheaper and faster. For some things, it's worth it if it isn't even as good as people yet.

I have very little issues with hallucinations anymore, when I use an LLM to get anything involving facts, I always tell it to give sources for everything, and i can have another agent independently verify the sources before i see them. Often times I provide the books or papers that I want it to specifically source from. Even if I am going to check all the sources myself after that, it is still way more efficient then if I did the whole thing myself. The thing is, with the setups I use, I literally never have it make up sources anymore. I remember that kind of thing happening back in the days when AI didn't have internet access, and there really weren't agents yet. I realize some people are still back there, but in the future(that many of us are in) its basically solved. There is still logic mistakes and such, that stuff can't be 100% depended on, but if you have a team of agents going back and forth to find an answer, then you pass it to another team of agents to independently verify the answer, and have it cycle back if a flaw is found, many issues just go away. Maybe some mistakes make it through this whole process, but the same thing happens sometimes with people.

I don't have the link on hand, but there have been studies done that show gpt3.5 working in agentic cycles perform as good or better than gpt4 out of the box. The article I saw that in was saying that basically there are already people using what gpt5 will most likely be just by using teams of agents with the latest models.

I think having it give direct quotes and specific sources would help your experience quite a bit. I absolutely agree that if just use the simplest forms of current LLMs and the "hello world" agent setups that there are hallucination issues and such, but lots of this is no longer an issue when you get deeper into it. It's just a matter of time until the stuff that most people can easily use will have this stuff baked in, it isn't anything that is impossible. I mean, I pretty much always have my agents tell me exactly where they get all their information from. The exception is when I have them writing code because there the proof is in the results.

Yeah, it's trajectory thing. Most people see the one-shot responses of something like the chatgpt's current web interface on openai's website and they think that's where we are at. It isn't though, the cutting edge of just what is currently openly available to people is things like CrewAI or Autogen using agents powered by things like Claude Opus or Llama 3, and maybe the latest gpt4 update.

When you use agents you don't have to baby every response, the agents can run code, test code, check latest information on the internet, and more. This way you can give a complex instruction, let it run and come back to a finished product.

I say it is a trajectory thing because when you compare what was cutting-edge just 1 year ago, basically one-shot gpt3.5 to an agent network with today's latest models, the difference is stark, and when you go a couple years before that to gpt2, it is way beyond stark. When you go a step further and realise that there is lots of custom hardware being built(basically llm ASICs-traditionally a ~10,000x speedup over general use gpus), you can see that soon having instant agent based responses will be the norm.

All this compounds when you consider that we have not hit a plateau and that we are still seeing that better datasets, and more compute, are still producing better models. Not to mention that other architectures, like state-based Mamba, are making remarkable achievements with very little compute so far. We have no idea how powerful thinks like Mamba would be if they were given the datasets and training that the current popular models are being given.

It is amazing to watch someone's mind melt like this just because the truth of their food source is pointed out to them. This is a full-blown insane comment.

Yeah, it would be great to catch that one psycho, but it would be way better to catch the psychos that do this all day every day. I think that's the point they were trying to make.

Wow! These are awesome. Where can I buy the seeds?

Yeah the current popular LLMs, absolutely they are, you couldn't be more right.

We were talking about "AI" though. Are you implying that you think some day AI might be capable of creativity, and that creativity isn't strictly a human trait?

Yeah, I've just set up a hotkey that says something like "back up your answer with multiple reputable sources" and I just always paste it at the end of everything I ask. If it can't find webpages to show me to back up its claims then I can't trust it. Of course this isn't the case with coding, for that I can actually run the code to verify it.

From monyet.cc most of the comments in this thread are missing.