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

11–20 of 165 posts

Re: Agents Are Not Enough

#11

Post by nyrikki »

kgeist wrote: post #6
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.

I think most users have a fixed set of workflows which usually don't change from day to day, so why not just use LLMs as a macro builder with a natural language interface (and which doesn't require you to know the product's UI well beforehand): - you ask LLM to build a workflow for your problem - the LLM builds the workflow (macro) using predefined commands - you review the workflow (can be an intuitive list of comma…

So visual programming x.0?

I am pretty sure PLCs with ladder logic are about the limits of the traditional visual/macro model?

Word-sense disambiguation is going to be problematic with the 'don't need to learn' part above.

Consider this sentence:

'I never said she stole my money'

Now read that sentence multiple times, puting emphasis on each word, one at a time and notice how the symantic meaning changes.

LLMs are great at NLP, but we still don't have solutions to those NLU problems that I am aware of.

I think to keep maximum generality without severely restricted use cases that a common DSL would need to be developed.

There will have to be tradeoffs made, specific to particular use cases, even if it is better than Alexa.

But I am thinking about Rice's theorm and what happens when you lose PEM.

Maybe I just am too embedded in an area where these problems are a large part of the difficulty for macro style logic to provide much use.

Re: Agents Are Not Enough

#12

Post by htrp »

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…

agents are the 2020s version of data science in the 2010s

Re: Agents Are Not Enough

#13

Post by bob1029 »

kgeist wrote: post #6
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.

I think most users have a fixed set of workflows which usually don't change from day to day, so why not just use LLMs as a macro builder with a natural language interface (and which doesn't require you to know the product's UI well beforehand): - you ask LLM to build a workflow for your problem - the LLM builds the workflow (macro) using predefined commands - you review the workflow (can be an intuitive list of comma…

> you review the workflow (can be an intuitive list of commands, understandable by non-specialist) - to weed out hallucinations and misunderstanding

This is the idea that is most valuable from my perspective of having tried to extract accurate requirements from the customer. Getting them to learn your product UI and capabilities is an uphill battle if you are in one of the cursed boring domains (banking, insurance, healthcare, etc.).

Even if the customer doesn't get the LLM-defined path to provide their desired final result, you still have their entire conversation history available to review. This seems more likely to succeed in practice than hoping the customer provides accurate requirements up-front in some unconstrained email context.

Re: Agents Are Not Enough

#14

Post by kgeist »

dingnuts wrote: post #8
kgeist wrote: post #6

Earlier quoted context omitted.

I think most users have a fixed set of workflows which usually don't change from day to day, so why not just use LLMs as a macro builder with a natural language interface (and which doesn't require you to know the product's UI well beforehand): - you ask LLM to build a workflow for your problem - the LLM builds the workflow (macro) using predefined commands - you review the workflow (can be an intuitive list of comma…

>- you review the workflow (can be an intuitive list of commands, understandable by non-specialist) so you define a DSL that the LLM outputs, and that's the real UI >- you don't need to learn a product's UI, you just formulate your problem using natural language yes, you do. You have to learn the DSL you just manifested so that you can check it for errors. Once you have the ability to review the LLM's output, you wil…

I never said the user must be exposed to a DSL, I think you're overcomplicating it for the sake of overcomplicating. DSL can be used under the hood by the execution engine, but the user can be exposed to a simpler variant of it, either by clever hardcoded postprocessing of known commands when rendering the final result for human review, or maybe use the LLM itself to summarize the planned actions (although it can hallucinate while summarizing, but the chance is miniscule, especially if a user can test a saved workflow). My point was mostly about two things:

1) "it's unpredictable each time" - it won't be, if a workflow is saved and tested, because when it's run, no LLM is involved anymore in decision making

2) I did remove the UI, because I don't need to learn the UI, I just formulate my problem and the LLM constructs a possible workflow which solves my problem out of predefined commands known to the system.

Sure this is most useful for more complex apps. In our homegrown CRM/ERP, users have lots of different workflows depending on their department, and they often experiment with workflows, and today they either have to click through everything manually (wasting time) or ask devs to implement the needed workflow for them (wasting time). If your app has 3 commands on 1 page then sure, it's easier to do it using GUI.

Also IMHO it can be used alongside with GUI, it doesn't need to replace it, I think it's great for discoverability/onboarding and automation, but if you want to click through everything manually, why not.

Re: Agents Are Not Enough

#15

Post by svieira »

kgeist wrote: post #14
dingnuts wrote: post #8

Earlier quoted context omitted.

>- you review the workflow (can be an intuitive list of commands, understandable by non-specialist) so you define a DSL that the LLM outputs, and that's the real UI >- you don't need to learn a product's UI, you just formulate your problem using natural language yes, you do. You have to learn the DSL you just manifested so that you can check it for errors. Once you have the ability to review the LLM's output, you wil…

I never said the user must be exposed to a DSL, I think you're overcomplicating it for the sake of overcomplicating. DSL can be used under the hood by the execution engine, but the user can be exposed to a simpler variant of it, either by clever hardcoded postprocessing of known commands when rendering the final result for human review, or maybe use the LLM itself to summarize the planned actions (although it can hal…

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).

Re: Agents Are Not Enough

#16

Post by kgeist »

svieira wrote: post #15
kgeist wrote: post #14

Earlier quoted context omitted.

I never said the user must be exposed to a DSL, I think you're overcomplicating it for the sake of overcomplicating. DSL can be used under the hood by the execution engine, but the user can be exposed to a simpler variant of it, either by clever hardcoded postprocessing of known commands when rendering the final result for human review, or maybe use the LLM itself to summarize the planned actions (although it can hal…

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 reading the raw DSL really required for the majority of cases?

Re: Agents Are Not Enough

#17

Post by deadbabe »

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.

They are deterministic at 0 temperature

Re: Agents Are Not Enough

#18

Post by curious_cat_163 »

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…

Yes, and the definition works reasonably well for the core arguments they are making in Section 5.

I suspect they'll follow up with a full paper with more details (and artifacts) of their proposed approach.

Re: Agents Are Not Enough

#20

Post by jvans »

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-...

this is a great write up, thank you
Post reply on HN