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

71–80 of 130 posts

Re: Building Effective "Agents"

#71

Post by pvg »

Animats wrote: post #50
simonw wrote: post #11

This is by far the most practical piece of writing I've seen on the subject of "agents" - it includes actionable definitions, then splits most of the value out into "workflows" and describes those in depth with example applications. There's also a cookbook with useful code examples: https://github.com/anthropics/anthropic-cookbook/tree/main/p... Blogged about this here: https://simonwillison.net/2024/Dec/20/building-…

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…

AI people have been using a much broader definition of 'agent' for ages, though. One from Russel and Norvig's 90s textbook:

"Anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators"

https://en.wikipedia.org/wiki/Intelligent_agent#As_a_definit...

Re: Building Effective "Agents"

#72

Post by adeptima »

simonw wrote: post #11

This is by far the most practical piece of writing I've seen on the subject of "agents" - it includes actionable definitions, then splits most of the value out into "workflows" and describes those in depth with example applications. There's also a cookbook with useful code examples: https://github.com/anthropics/anthropic-cookbook/tree/main/p... Blogged about this here: https://simonwillison.net/2024/Dec/20/building-…

100% agree. I did a research on workflows, durable execution engines in context of Agents and RAGs. Put some links in a comment to the article below

Re: Building Effective "Agents"

#73

Post by simonw »

JonChesterfield wrote: post #67
simonw wrote: post #55

Earlier quoted context omitted.

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.

Defining "agent" as "thing with agency" seems legitimate to me, what with them being the same word.

That logic doesn't work for me, because many words have multiple meanings. "Agency" can also be a noun that means an organization that you hire - like a design agency. Or it can mean the CIA.

I'm not saying it's not a valid definition of the term, I'm pushing back on the idea that it's THE single correct definition of the term.

Re: Building Effective "Agents"

#74

Post by furyofantares »

ggm wrote: post #47
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?

So if like me you have an interior dialogue, which is speaking and which is listening or is it the same one? I do not ascribe the speaker or listener to a lobe, but whatever the language and comprehension centre(s) is(are), it can do both at the same time.

Same half. My understanding is that in split brain patients, it looks like the one half has extremely limited ability to parse language and no ability to create it.

Re: Building Effective "Agents"

#75

Post by Filligree »

furyofantares wrote: post #45
tomrod wrote: post #44

Earlier quoted context omitted.

Brains are split internally, with each having their own monologue. One happens to have command.

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?

Neither of my halves need a monologue, thanks.

Re: Building Effective "Agents"

#76

Post by jeffreygoesto »

Animats wrote: post #50
simonw wrote: post #11

This is by far the most practical piece of writing I've seen on the subject of "agents" - it includes actionable definitions, then splits most of the value out into "workflows" and describes those in depth with example applications. There's also a cookbook with useful code examples: https://github.com/anthropics/anthropic-cookbook/tree/main/p... Blogged about this here: https://simonwillison.net/2024/Dec/20/building-…

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…

And "autonomous" is "having one's own laws".

https://www.etymonline.com/word/autonomous

Re: Building Effective "Agents"

#77

Post by wahnfrieden »

rybosome wrote: post #20
jascha_eng wrote: post #2

I put the agents in quotes because anthropic actually talks more about what they call "workflows". And imo this is where the real value of LLMs currently lies, workflow automation. They also say that using LangChain and other frameworks is mostly unnecessary and does more harm than good. They instead argue to use some simple patterns, directly on the API level. Not dis-similar to the old-school Gang of Four software…

I felt deeply vindicated by their assessment of these frameworks, in particular LangChain. I've built and/or worked on a few different LLM-based workflows, and LangChain definitely makes things worse in my opinion. What it boils down to is that we are still coming to understand the right patterns of development for how to develop agents and agentic workflows. LangChain made choices about how to abstract things that a…

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

Re: Building Effective "Agents"

#80

Post by throw83288 »

brotchie wrote: post #10

Have been building agents for past 2 years, my tl;dr is that: Agents are Interfaces, Not Implementations The current zeitgeist seems to think of agents as passthrough agents: e.g. a lite wrapper around a core that's almost 100% a LLM. The most effective agents I've seen, and have built, are largely traditional software engineering with a sprinkling of LLM calls for "LLM hard" problems. LLM hard problems are problems…

Unrelated, but since you seem to have experience here, how would you recommend getting into the bleeding edge of LLMs/Agents? Traditional SWE is obviously on it's way out, but I can't even tell where to start with this new tech and struggle to find ways to apply them to an actual project.
Post reply on HN