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

Artificial Intelligence: Foundations of Computational Agents

artint.info

Post reply on HN
Print view View original

41–50 of 54 posts

Re: Artificial Intelligence: Foundations of Computational Agents

#41

Post by sureglymop »

nivertech wrote: post #11
nine_k wrote: post #8

Earlier quoted context omitted.

So basically an agent is a procedure, by this definition: it takes parameters (environment) and acts upon that by executing side effects. An email filter is an agent. A database trigger is an agent.

> it takes parameters (environment) I think it's better to imagine agent as something that physically placed inside the Environment, and actually modifying/changing/mutating it in place. > An email filter is an agent. A database trigger is an agent. you're missing the "I" (Intelligence) part - the filtering logic in the email filter, or a business logic in the DB trigger/stored procedure/CGI script/AWS Lambda functio…

Can you explain the "intelligence" part? Can't one derive a decision tree of any "intelligent agent" that is in essence no different than a classically programmed algorithm?

Re: Artificial Intelligence: Foundations of Computational Agents

#42

Post by bsenftner »

sc077y wrote: post #28
simonw wrote: post #2

Because I collect definitions of "agent", here's the one this book uses: > An agent is something that acts in an environment; it does something. Agents include worms, dogs, thermostats, airplanes, robots, humans, companies, and countries. https://artint.info/3e/html/ArtInt3e.Ch1.S1.html I think of this as the "academic" definition, or sometimes the "thermostat" definition (though maybe I should call it the "worms and…

The problem I see with this definition is that we have things called RAG agents which don't technically act in any environment except for provide information.

Is that not a summary and translation agent? For some reason only the user knows, they do not want to or cannot read the entire RAG source, so they use their summary and translation agent to give them summaries and to translate the technical jargon they do not understand. That Agent becomes a teacher of the RAG source. I see no problem with the Agent definition when given this perspective.

Re: Artificial Intelligence: Foundations of Computational Agents

#43

Post by antonkar »

Intelligence - space-like, matter-like (LLM is a bunch of vectors, a static geometric shape, you just need memory to store it). It’s a static geometric shape. It can have analogs of volume, mass and density. The static 4D spacetime of the universe or multiverse is maximally intelligent but non-agentic.

Agent - time-like, energy-like (you need a GPU to compute it). An agent changes the shape of the environment it operates in, including its own shape. You can count agents, their volume of operations, their speed of changing shapes (volumetric speed), acceleration… The Big Bang had zero intelligence (with maximal potential intelligence) but was and still is maximally agentic

Re: Artificial Intelligence: Foundations of Computational Agents

#44

Post by nivertech »

bsenftner wrote: post #40
nivertech wrote: post #9

Earlier quoted context omitted.

It always amazed me that different branches of CS, AI/ML and Complex Systems/Complexity Sciences have different views on agents. Objects in OOP - something which can have properties/attributes, and methods (verbs/commands). Usually modeled after a real-life/domain enitites. Aggregates in Domain-Driven Design (DDD) - transactional clusters of objects modeling a collections of entities in the domain. Actors in Actor Mo…

How's about: LLM Agent: any packaging of the use of AI such that the details of using said AI are packaged, hidden, and the user of this LLM Agent does not need to concern themselves with AI at all, only the intelligence services provided by what is now a simulated personality the user can willfully self deceive they are working with a human.

aka "delegation", "ousourcing", "serverless", and "not my busienss, do it ASAP, I don't care how" ;)

Re: Artificial Intelligence: Foundations of Computational Agents

#45

Post by mportela »

simonw wrote: post #2

Because I collect definitions of "agent", here's the one this book uses: > An agent is something that acts in an environment; it does something. Agents include worms, dogs, thermostats, airplanes, robots, humans, companies, and countries. https://artint.info/3e/html/ArtInt3e.Ch1.S1.html I think of this as the "academic" definition, or sometimes the "thermostat" definition (though maybe I should call it the "worms and…

FWIW I had a professor that defined "robotics" in the same way (we even had a quite philosophical debate on whether automatic doors are robots). I ended up liking Norvig and Russell's definition better by appending the word "autonomously".

Another interesting word that is quite out fashion nowadays is "cybernetics": "Cybernetics is the transdisciplinary study of circular causal processes such as feedback and recursion, where the effects of a system's actions (its outputs) return as inputs to that system, influencing subsequent action." [1]

Having studied Control Engineering in college, to me, all these things are feedback control loops. [2]

[1] https://en.wikipedia.org/wiki/Cybernetics [2] https://en.m.wikipedia.org/wiki/Feedback

Re: Artificial Intelligence: Foundations of Computational Agents

#46

Post by bsenftner »

nivertech wrote: post #44
bsenftner wrote: post #40

Earlier quoted context omitted.

How's about: LLM Agent: any packaging of the use of AI such that the details of using said AI are packaged, hidden, and the user of this LLM Agent does not need to concern themselves with AI at all, only the intelligence services provided by what is now a simulated personality the user can willfully self deceive they are working with a human.

aka "delegation", "ousourcing", "serverless", and "not my busienss, do it ASAP, I don't care how" ;)

Exactly, you know AI Agents will ultimately be "just make it work, I don't care how", so why don't we just stop the game and make that?

Re: Artificial Intelligence: Foundations of Computational Agents

#47

Post by antonkar »

simonw wrote: post #2

Because I collect definitions of "agent", here's the one this book uses: > An agent is something that acts in an environment; it does something. Agents include worms, dogs, thermostats, airplanes, robots, humans, companies, and countries. https://artint.info/3e/html/ArtInt3e.Ch1.S1.html I think of this as the "academic" definition, or sometimes the "thermostat" definition (though maybe I should call it the "worms and…

Agent - time-like, energy-like (you need a GPU to compute it). An agent changes the shape of the environment it operates in, including its own shape. You can count agents, their volume of operations, their speed of changing shapes (volumetric speed), acceleration… The Big Bang had zero intelligence (with maximal potential intelligence) but was and still is maximally agentic.

Same way we have many definitions of life (virus is alive or not? It’s very agentic, COVID killed millions but the shape, intelligence is small. Same with computer viruses), we have many definitions of agency, better to use the broadest and most physical one.

Intelligence - space-like, matter-like (LLM is a bunch of vectors, a static geometric shape, you just need memory to store it). It’s a static geometric shape. It can have analogs of volume, mass and density. The static 4D spacetime of the universe or multiverse is maximally intelligent but non-agentic.

Re: Artificial Intelligence: Foundations of Computational Agents

#48

Post by nivertech »

sureglymop wrote: post #41
nivertech wrote: post #11

Earlier quoted context omitted.

> it takes parameters (environment) I think it's better to imagine agent as something that physically placed inside the Environment, and actually modifying/changing/mutating it in place. > An email filter is an agent. A database trigger is an agent. you're missing the "I" (Intelligence) part - the filtering logic in the email filter, or a business logic in the DB trigger/stored procedure/CGI script/AWS Lambda functio…

Can you explain the "intelligence" part? Can't one derive a decision tree of any "intelligent agent" that is in essence no different than a classically programmed algorithm?

Yes, for Computational Agents you will either code "Agent Intelligence"/"Agent Cognition" algorithmically, or using AI/ML/LLM (either by pre-training, or using continous re-training for Adaptive Agents).

Useful abstaractions:

  - FSM/State Machines
  - Behavior Trees
  - Behavior Action Trees
  - Workflow Orchestration
  - Dataflow (mostly for pipelines transforming LLM Prompt into LLM Reponse)
Another option is to outsource it to a Human, like it was in the ALICE program[1], e.g. Human-in-the-Loop, Participatory Simulation, RLHF, Whole-brain computer simulation, like in The Age of Em[2] (SciFi).

See:

https://news.ycombinator.com/item?id=43409240

---

1. https://www.media.mit.edu/projects/participatory-simulations...

https://ccl.northwestern.edu/papers/partsims/cscl/

2. https://ageofem.com/

Re: Artificial Intelligence: Foundations of Computational Agents

#49

Post by nivertech »

bsenftner wrote: post #46
nivertech wrote: post #44

Earlier quoted context omitted.

aka "delegation", "ousourcing", "serverless", and "not my busienss, do it ASAP, I don't care how" ;)

Exactly, you know AI Agents will ultimately be "just make it work, I don't care how", so why don't we just stop the game and make that?

Try replacing "AI Agentic Workflow" with "just make it work, I don't care how" in your startup's pitchdeck, and tell us how many VCs replied back ;)

Re: Artificial Intelligence: Foundations of Computational Agents

#50

Post by FollowingTheDao »

sureglymop wrote: post #41
nivertech wrote: post #11

Earlier quoted context omitted.

> it takes parameters (environment) I think it's better to imagine agent as something that physically placed inside the Environment, and actually modifying/changing/mutating it in place. > An email filter is an agent. A database trigger is an agent. you're missing the "I" (Intelligence) part - the filtering logic in the email filter, or a business logic in the DB trigger/stored procedure/CGI script/AWS Lambda functio…

Can you explain the "intelligence" part? Can't one derive a decision tree of any "intelligent agent" that is in essence no different than a classically programmed algorithm?

Just replying here to tell you I replied to a question (cisco) you asked me in case you miss it. Thanks!
Post reply on HN