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

Agents Are Not Enough

arxiv.org

Post reply on HN
Print view View original

21–30 of 165 posts

Re: Agents Are Not Enough

#21

Post by hitchstory »

GiorgioG wrote: post #3
bob1029 wrote: post #2

I think the goldilocks path is to make the user the agent and use the LLM simply as their UI/UX for working with the system. Human (domain expert) in the loop gives you a reasonable chance of recovering from hallucinations before they spiral entirely out of control. "LLM as UI" seems to be something hanging pretty low on the tree of opportunity. Why spent months struggling with complex admin dashboard layouts and web…

re: LLM as UI: Given that I don't trust LLMs to be deterministic, I wouldn't trust them to make the correct API call every time I tell it to do X.

I dont either, but this can be mitigated by adding guard rails (strictly validating input), double checking actions with the user and using it for tasks where a mistake isnt world ending.

Even then mistakes can slip through, but it could still be more reliable than a visual UI.

There are lots of horrible web UIs i would LOVE to replace with a conversational LLM agent. No #1 is jira and so is no #2 and #3.

Re: Agents Are Not Enough

#22

Post by svieira »

kgeist wrote: post #16
svieira wrote: post #15

Earlier quoted context omitted.

The bit you are missing is that "known to the system" is not enough, as the consumer I need to _verify the logic_, which means that at some level, I do have to read the DSL (just as I have to read the Java, not, in general, the actual assembly emitted by the JIT). Which means that the DSL is actually the product here (though the LLM may make it easier to learn that DSL and in some cases to write something in it).

1) You don't need to read the DSL in the raw form if you use a language model to convert it to a few paragraphs in natural language. 2) You can test the created workflow on a bunch of test data to verify it works as intended. After a workflow is created, it's deterministic (since we don't use LLMs anymore for decision making), so it will always work the same. Sure we can expose DSL to power users as an option, but is…

1. Now you have two problems (did the writer translate what I said correctly and did the summarizer translate what the writer wrote correctly).

2. This is absolutely true and it does help somewhat. However, writing the test cases is now your bottleneck (and you're writing them as a substitute for being able to read a reliable high-level summary of what the workflow actually is).

Re: Agents Are Not Enough

#23

Post by swyx »

simonw wrote: post #7
adpirz wrote: post #5

Earlier quoted context omitted.

You posted on X a while back asking for a crowdsourced definition of what an "agent" was and I regularly cite that thread as an example of the fact that this word is so blurry right now.

I really need to write that up in one place - closest I've got is this section from my 2024 review https://simonwillison.net/2024/Dec/31/llms-in-2024/#-agents-...

didnt your summary https://gist.github.com/simonw/beaa5f90133b30724c5cc1c4008d0... pretty much cover it?

Re: Agents Are Not Enough

#24

Post by BalinKing »

deadbabe wrote: post #17
GiorgioG wrote: post #3

Earlier quoted context omitted.

re: LLM as UI: Given that I don't trust LLMs to be deterministic, I wouldn't trust them to make the correct API call every time I tell it to do X.

They are deterministic at 0 temperature

(Disclaimer: I know literally nothing about LLMs.) Wouldn't there still be issues of sensitivity, though? Like, wouldn't you still have to ensure that the wording of your commands stays exactly the same every time? And with models that take less discrete data (e.g. ChatGPT's new "advanced voice model" that works on audio directly), this seems even harder.

Re: Agents Are Not Enough

#25

Post by nowittyusername »

With time, they will get a lot better. IMO, the biggest hurdles the agents currently lack is good implementation of function calling capabilities. LLM's should be used as reasoning engines and everything else should be offloaded to tool use. This will drastically reduce hallucinations and errors in math and all the other areas.

Re: Agents Are Not Enough

#26

Post by behnamoh »

simonw wrote: post #4

This paper does at least lead with its version of what "agents" means (I get very frustrated when people talk about agents without clarifying which of the many potential definitions they are using): > An agent, in the context of AI, is an autonomous entity or program that takes preferences, instructions, or other forms of inputs from a user to accomplish specific tasks on their behalf. Agents can range from simple sy…

People have been talking about agents for at least 2 years. Remember when AgentGPT came out? How's that going so far? Agents are just LLMs with structured output, which often happens to be a JSON with info about a function arguments to be called.

Re: Agents Are Not Enough

#27

Post by ripped_britches »

I can imagine really powerful agents this year or next in theory. Agents meaning (not a thermostat) a system that can go complete some async tasks on your behalf. But in practice I don’t have any idea how we will solve for prompt injection attacks. Hopefully someone cracks it.

Re: Agents Are Not Enough

#28

Post by georgestrakhov »

IMHO, the word agent is quickly becoming meaningless. The amount of agency that sits with the program vs. the user is something that changes gradually.

So we should think about these things in terms of how much agency are we willing to give away in each case and for what gain[1].

Then the ecosystem question that the paper is trying to solve will actually solve itself, because it is already the case today that in many processes agency has been outsourced almost fully and in others - not at all. I posit that this will continue, just expect a big change of ratios and types of actions.

[1] https://essays.georgestrakhov.com/artificial-agency-ladder/

Re: Agents Are Not Enough

#29

Post by cratermoon »

simonw wrote: post #4

This paper does at least lead with its version of what "agents" means (I get very frustrated when people talk about agents without clarifying which of the many potential definitions they are using): > An agent, in the context of AI, is an autonomous entity or program that takes preferences, instructions, or other forms of inputs from a user to accomplish specific tasks on their behalf. Agents can range from simple sy…

We're at the phase of the hype cycle where "agent" means whatever the marketing materials want it to mean.

Re: Agents Are Not Enough

#30

Post by cratermoon »

ripped_britches wrote: post #27

I can imagine really powerful agents this year or next in theory. Agents meaning (not a thermostat) a system that can go complete some async tasks on your behalf. But in practice I don’t have any idea how we will solve for prompt injection attacks. Hopefully someone cracks it.

"AI will soon be able too..."
Post reply on HN