Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Large Language Models Are Human-Level Prompt Engineers

openreview.net

Post reply on HN
Print view View original

21–30 of 54 posts

Re: Large Language Models Are Human-Level Prompt Engineers

#21

Post by heyitsguay »

lukasb wrote: post #6
famouswaffles wrote: post #2

Capable enough LLMs are human level for lots of things. Reinforcement learning from ai feedback is a thing (the anthropic claude models use that). Strictly speaking, it's not necessary to have humans in the loop for a lot of these things. Some are hesitant to admit we've created human level general intelligence but saying otherwise doesn't really hold up to scrutiny.

I see people saying things like this but I have yet to see anyone show data for a non-trivial workflow with human-level accuracy over a wide range of inputs, without a human in the loop.

LLMs are having a moment in 2023 like self driving cars were having in 2015. Some really cool demos following a lot of hard work, too much hyperbolic speculation that mass real-world job-destroying deployments are right around the corner, not enough appreciation of how few commercial applications are ok with 99% (or even 99.9%) accurate solutions. Real value being created, but still requiring lots of human ingenuity and grunt work to unlock it.

As a decent first-order metric - follow the ratio of companies getting money for using LLMs to do something, to companies getting money for providing LLMs and associated tooling to others. The bigger that ratio gets, the more real world impact LLMs are having.

Re: Large Language Models Are Human-Level Prompt Engineers

#22

Post by bravogamma »

bugglebeetle wrote: post #8

I can’t find the link to the paper right now, but after reading about how LLMs perform better with task breakdowns, I vastly improved my integrations by having ChatGPT generate prompts that decompose a general task into a series of tasks based on a sample input and output. I haven’t needed to make a self-refining system (one or two rounds of task decomposition and refinement resulted in the expected result for all in…

Will you share examples for prompts that “vastly improved” your integrations?

Re: Large Language Models Are Human-Level Prompt Engineers

#23

Post by Avicebron »

nemo44x wrote: post #17
api wrote: post #13

Earlier quoted context omitted.

I am not convinced we have cracked AGI. I just would no longer make a large bet that we have not. We won’t know until an AGI actually starts to act like one. In other words we won’t know until we know and then we are suddenly there. That doesn’t mean I’m on the doomwagon. I feel kind of weird and contrarian but I am just not that afraid of AGI. For the foreseeable future AGI should be much more afraid of us. Imagine…

Fwiw, a majority at OpenAI believes GPT5 will achieve AGI, depending on how you define it, according to Sam Altman.

And I'm sure him saying that has nothing to do with marketing

Re: Large Language Models Are Human-Level Prompt Engineers

#24

Post by Buttons840 »

Headlines like this hint towards AI improving itself. Prompting itself in this case. But as we see in reinforcement learning, algorithms that act and improve themselves are not new. The interesting thing will be weather or not they eventually "collapse".

For example, if an RL algorithms is performing well on an Atari game, you can stop the training and just let the agent run for years and the performance will remain about the same. However, if you allow the agent to continue training, it's not clear whether it will (1) continue improving, (2) stay about the same, or (3) collapse and perform much worse and never recover. I'm not an RL expert, but I've spent a lot of time experimenting and implementing the algorithms myself and I've seen all 3 of these scenarios play out, and I'm never quite sure what's going to happen so long as I allow the training to continue.

GTP4 will remain GTP4 forever, and that's amazing, but just because GTP4 is stable and amazing while it's not in training mode, doesn't mean it will remain stable if we allow it to bootstrap and prompt itself and prepare its own training data, etc.

Re: Large Language Models Are Human-Level Prompt Engineers

#25

Post by famouswaffles »

heyitsguay wrote: post #21
lukasb wrote: post #6

Earlier quoted context omitted.

I see people saying things like this but I have yet to see anyone show data for a non-trivial workflow with human-level accuracy over a wide range of inputs, without a human in the loop.

LLMs are having a moment in 2023 like self driving cars were having in 2015. Some really cool demos following a lot of hard work, too much hyperbolic speculation that mass real-world job-destroying deployments are right around the corner, not enough appreciation of how few commercial applications are ok with 99% (or even 99.9%) accurate solutions. Real value being created, but still requiring lots of human ingenuity…

almost nothing involving NLP requires solutions anywhere near that accuracy rate. I've seen the self driving comparisons a lot but they straight up make little sense.

there's a reason microsoft's various copilot suites have already popped up (365, X, Bing). massive value to be gained already in the here and now.

Re: Large Language Models Are Human-Level Prompt Engineers

#26

Post by goosinmouse »

Tade0 wrote: post #15
kaesar14 wrote: post #4

This is pretty alarming tbh. Anyone already making a pivot out of SWE?

In a sense, Yes - to scoring function engineer. But in seriousness - language models may be scaling in sophistication exponentially with time, but software engineering problems scale in complexity (on average) exponentially with lines of code. The base of this exponential function isn't large, but it's more than 1. In the end there's a need for someone who understands what they're doing. Personally, I use ChatGPT to…

It's hard to not think that scaling and complexity problems will be solved very shortly with new models. Already when i run into my 25 per 3hr limit with GPT-4, my productivity goes from extremely productive to "may as well just do it myself" when i switch back to GPT-3.5.

Re: Large Language Models Are Human-Level Prompt Engineers

#27

Post by axiom92 »

bugglebeetle wrote: post #8

I can’t find the link to the paper right now, but after reading about how LLMs perform better with task breakdowns, I vastly improved my integrations by having ChatGPT generate prompts that decompose a general task into a series of tasks based on a sample input and output. I haven’t needed to make a self-refining system (one or two rounds of task decomposition and refinement resulted in the expected result for all in…

For those curious about self-refining systems: https://selfrefine.info/ (our recent work).

Re: Large Language Models Are Human-Level Prompt Engineers

#29

Post by famouswaffles »

lukasb wrote: post #6
famouswaffles wrote: post #2

Capable enough LLMs are human level for lots of things. Reinforcement learning from ai feedback is a thing (the anthropic claude models use that). Strictly speaking, it's not necessary to have humans in the loop for a lot of these things. Some are hesitant to admit we've created human level general intelligence but saying otherwise doesn't really hold up to scrutiny.

I see people saying things like this but I have yet to see anyone show data for a non-trivial workflow with human-level accuracy over a wide range of inputs, without a human in the loop.

How is reinforcement learning without a single human in the loop not non-trivial?

Re: Large Language Models Are Human-Level Prompt Engineers

#30

Post by skepticATX »

nemo44x wrote: post #17
api wrote: post #13

Earlier quoted context omitted.

I am not convinced we have cracked AGI. I just would no longer make a large bet that we have not. We won’t know until an AGI actually starts to act like one. In other words we won’t know until we know and then we are suddenly there. That doesn’t mean I’m on the doomwagon. I feel kind of weird and contrarian but I am just not that afraid of AGI. For the foreseeable future AGI should be much more afraid of us. Imagine…

Fwiw, a majority at OpenAI believes GPT5 will achieve AGI, depending on how you define it, according to Sam Altman.

Did he actually say this? Do you have a source?
Post reply on HN