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

Building Effective "Agents"

anthropic.com

Post reply on HN
Print view View original

121–130 of 130 posts

Re: Building Effective "Agents"

#121

Post by minasmorath »

simonw wrote: post #55
Animats wrote: post #50

Earlier quoted context omitted.

Yes, they have actionable definitions, but they are defining something quite different than the normal definition of an "agent". An agent is a party who acts for another. Often this comes from an employer-employee relationship. This matters mostly when things go wrong. Who's responsible? The airline whose AI agent gave out wrong info about airline policies found, in court, that their "intelligent agent" was considere…

Where did you get the idea that your definition there is the "normal" definition of agent, especially in the context of AI? I ask because you seem very confident in it - and my biggest frustration about the term "agent" is that so many people are confident that their personal definition is clearly the one everyone else should be using.

I searched for the definition of "agent" and none of the results map to the way AI folks are using the word. It's really that simple, because we're marketing this stuff to non-tech people who already use words to mean things.

If we're redefining common words to market this stuff to non-tech people, and then we're conveniently not telling them that we redefined words, and thus allowing them to believe implicit falsehoods about the product that have serious consequences, we're being disingenuous.

Re: Building Effective "Agents"

#122

Post by pvg »

minasmorath wrote: post #119
pvg wrote: post #117

Earlier quoted context omitted.

In what way is it 'disingenuous'? You think Norvig is trying to deceive us about something? I'm not saying you have to agree with or like this definition but even if you think it's straight up wrong, 'disingenuous' feels utterly out of nowhere.

It's disingenuous in that it takes a word with a common understanding ("agent") and then conveniently redefines or re-etomologizes the word in an uncommon way that leads people to implicitly believe something about the product that isn't true. Another great example of this trick is "essential" oils. We all know what the word "essential" means, but the companies selling the stuff use the word in the most uncommon way,…

with a common understanding ("agent") and then conveniently redefines or re-etomologizes the word in an uncommon way that leads people to implicitly believe something about the product that isn't true.

What is the 'product' here? It's a university textbook. Like, where is the parallel between https://en.wikipedia.org/wiki/Intelligent_agent and 'essential oils'.

Re: Building Effective "Agents"

#123

Post by minasmorath »

pvg wrote: post #122
minasmorath wrote: post #119

Earlier quoted context omitted.

It's disingenuous in that it takes a word with a common understanding ("agent") and then conveniently redefines or re-etomologizes the word in an uncommon way that leads people to implicitly believe something about the product that isn't true. Another great example of this trick is "essential" oils. We all know what the word "essential" means, but the companies selling the stuff use the word in the most uncommon way,…

with a common understanding ("agent") and then conveniently redefines or re-etomologizes the word in an uncommon way that leads people to implicitly believe something about the product that isn't true. What is the 'product' here? It's a university textbook. Like, where is the parallel between https://en.wikipedia.org/wiki/Intelligent_agent and 'essential oils'.

Oh, I have no issue with his textbook definition, I'm saying that it's now being used to sell products by people who know their normal consumer base isn't using the same definition and it conveniently misleads them into believing things about the product that aren't true.

Knowing that your target market (non-tech folks) isn't using the same language as you, but persisting with that language because it creates convenient sales opportunities due to the misunderstandings, feels disingenuous to me.

An "agent" in common terms is just someone acting on behalf of another, but that someone still has autonomy and moral responsibility for their actions. Like for example the airline customer service representative situation. AI agents, when we pull back the curtains, get down to brass tacks, whatever turn of phrase you want to use, are still ultimately deterministic models. They have a lot more parameters, and their determinism is offset by many factors of pseudo-randomness, but given sufficient information we could still predict every single output. That system cannot be an agent in the common sense of the word, because humans are still dictating all of the possible actions and outcomes, and the machine doesn't actually have the autonomy required.

If you fail to keep your tech product from going off-script, you're responsible, because the model itself isn't a non-deterministic causal actor. A human CSR on the other hand is considered by law to have the power and responsibility associated with being a causal actor in the world, and so when they make up wild stuff about the terms of the agreement, you don't have to honor it for the customer, because there's culpability.

I'm drifting into philosophy at this point, which never goes well on HN, but this is ultimately how our legal system determines responsibility for actions, and AI doesn't meet those qualifications. If we ever want it to be culpable for its own actions, we'll have to change the legal framework we all operate under.

Edit: Causal, not casual... Whoops.

Also, I think I'm confusing the situation a bit by mixing the legal distinctions between agency and autonomy with the common understanding of being an "agent" and the philosophical concept of agency and culpability and how that relates to the US legal foundations.

I need to go touch grass.

Re: Building Effective "Agents"

#124

Post by kordlessagain »

th0ma5 wrote: post #111
simonw wrote: post #104

Earlier quoted context omitted.

I've written extensively about myths and misconceptions about LLMs, much of which overlaps with the observations in that post. Here's my series about misconceptions: https://simonwillison.net/series/llm-misconceptions/ It doesn't seem to me that you're familiar with my work - you seem to be mixing me in with the vast ocean of uncritical LLM boosting content that's out there.

I'm thinking of the system you built to watch videos and parse JSON and the claims of that having a general suitability, which is simply dishonest imo. You seem to be confusing me with someone that hasn't been asking you repeatedly to address these kinds of concerns and the above series are a kind of potemkin set of things that don't intersect with your other work.

> dishonest Potemkin

It's like criticizing a "Hello World" program for not having proper error handling and security protocols. While those are important for production systems, they're not the point of a demonstration or learning example.

Your response seems to take these examples and hold them to the standard of mission-critical systems, which is a form of technical gatekeeping - raising the bar unnecessarily high for what counts as a "valid" technical demonstration.

Re: Building Effective "Agents"

#125

Post by simonw »

th0ma5 wrote: post #111
simonw wrote: post #104

Earlier quoted context omitted.

I've written extensively about myths and misconceptions about LLMs, much of which overlaps with the observations in that post. Here's my series about misconceptions: https://simonwillison.net/series/llm-misconceptions/ It doesn't seem to me that you're familiar with my work - you seem to be mixing me in with the vast ocean of uncritical LLM boosting content that's out there.

I'm thinking of the system you built to watch videos and parse JSON and the claims of that having a general suitability, which is simply dishonest imo. You seem to be confusing me with someone that hasn't been asking you repeatedly to address these kinds of concerns and the above series are a kind of potemkin set of things that don't intersect with your other work.

You mean this? https://simonwillison.net/2024/Oct/17/video-scraping/

To my surprise, on re-reading that post I didn't mention that you need to double-check everything it does. I guess I forgot to mention that at the time because I thought it was so obvious - anyone who's paying attention to LLMS should already know that you can't trust them to reliably extract this kind of information.

I've mentioned that a lot in my other writing. I frequently tell people that the tricky thing about working with LLMs is learning how to make use of a technology that is inherently unreliable.

Update: added a new note about reliability here: https://simonwillison.net/2024/Oct/17/video-scraping/#a-note...

Second update: I just noticed that I DID say "You should never trust these things not to make mistakes, so I re-watched the 35 second video and manually checked the numbers. It got everything right." in that post already.

> You seem to be confusing me with someone that hasn't been asking you repeatedly to address these kinds of concerns

Where did you do that?

Re: Building Effective "Agents"

#126

Post by ahmadawais »

rybosome wrote: post #85
wahnfrieden wrote: post #77

Earlier quoted context omitted.

The article does not mention the LangChain framework. LangGraph is a different framework, have you tried it?

Yes, our previous lead dev built a lot of our infra using LangGraph. I've been slowly ripping it out since assuming ownership of this part of the codebase. I've been replacing LangGraph with simple primitives, relying on native Python constructs, etc. For example, instead of building this verbose graph of computation with LangGraph, you can just...call functions in the order you want them. Or declare them async, add…

Couldn’t agree more. Btw what’s your use case?

Re: Building Effective "Agents"

#127

Post by ahmadawais »

melvinmelih wrote: post #51

While I agree with the premise of keeping it simple (especially when it comes to using opaque and overcomplicated frameworks like LangChain/LangGraph!) I do believe there’s a lot more to building agentic systems than this article covers. I recently wrote[1] about the 4 main components of autonomous AI agents (Profile, Memory, Planning & Action) and all of that can still be accomplished with simple LLM calls, but ther…

This was fun to read. Thanks for sharing. Our memory agents are built somewhat like this but way too much going on in there to make them prod ready.

Re: Building Effective "Agents"

#130

Post by furyofantares »

tomrod wrote: post #113
furyofantares wrote: post #45

Earlier quoted context omitted.

I don't think there's reason to believe both halves have a monologue, is there? Experience, yes, but doesn't only one half do language?

[0] https://www.youtube.com/watch?v=fJRx9wItvKo [1] https://thersa.org/globalassets/pdfs/blogs/rsa-divided-brain... [2] https://en.wikipedia.org/wiki/Lateralization_of_brain_functi... You have two minds (at least). One happens to be dominant.

That all supports what I said, right? If almost everyone has almost all of their language functionality lateralized to one side of the brain then you'd have at most one inner monologue.

(At least) two minds: yes. Two inner monologues: no.

Post reply on HN