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

Agents need control flow, not more prompts

bsuh.bearblog.dev

Post reply on HN
Print view View original

71–80 of 348 posts

Re: Agents need control flow, not more prompts

#71

Post by isityettime »

dnautics wrote: post #58
isityettime wrote: post #56

Afaict all harnesses are wrong in this respect, some of them deeply so. Slash commands, for instance, are a misfeature. I should never have to wait for the chatbot finish a turn so that I can check on the status of my context window or how much money I've spent this session. Control should be orthogonal to the chat loop. Even things that have nothing to do with controlling the text generator's input and output are en…

> Slash commands, for instance, are a misfeature. I should never have to wait for the chatbot finish a turn so that I can check on the status of my context window or how much money I've spent this session. Control should be orthogonal to the chat loop. I get what you're trying to say but in practice architecting what you propose is considerably more difficult. Why not build it and try to get hired by one of the bigco…

I don't think the basic architecture principles are novel. The big AI labs and other large tech companies already have engineers who can see this, without a doubt. But the AI labs clearly don't care if their LLM agents are just big balls of mud, and the big tech companies priorities mostly lie elsewhere, too.

They just want features. They don't really care about duplicated work, so half of them reinvent the TUI rendering wheel. Pluggability is something that might be actually hostile to their interests in lock-in. And the AI labs probably think "after a couple more scaling cycles, our models will be so good that our agents can just rewrite themselves from scratch"; until they hit a compute or power wall, it always looks rational to them to defer rearchitecting.

Another real possibility is that if you work on an agent with a really clean architecture and publish it in hopes of getting hired by some AI company, all of them think "that looks great, but we don't want to rearchitect right now". Your code winds up in the training set, and a year and a half from now, existing agents can "one-shot" rewrites along the lines of your design because they're "smarter".

As for me, I'm not that interested, personally. There are other things I want to build and I'm working on those.

Re: Agents need control flow, not more prompts

#73

Post by nixpulvis »

rnxrx wrote: post #22

I wonder if a part of the problem isn't just the misapplication of LLMs in the first place. As has been mentioned elsewhere, perhaps the agent's prompt should be to write code to accomplish as much of the task in as repeatable/verifiable/deterministic a way as possible. This would hopefully include validation of the agent's output as well. The overall goal would be to keep the LLM out of doing processing that could b…

My agents often write themselves scripts. Isn't that effectively what you're asking for? Prompting for scripts can also be a useful time and accuracy tactic when you know it'll be a good fit for it.

Re: Agents need control flow, not more prompts

#74

Post by rglover »

> Babysitter: Keep a human in the loop to catch errors before they propagate.

This is the only way to guarantee AI usage doesn't burn you. Any automation beyond this is just theater, no matter how much that hurts to hear/undermines your business model.

A bird sings, a duck quacks. You don't expect the duck to start singing now, do you?

Re: Agents need control flow, not more prompts

#75

Post by onion2k »

suprfnk wrote: post #28
onion2k wrote: post #19

Agents are probabilistic systems. A common mechanism to get a reliable answer from systems that can have variable output is to run them several times (ideally in separate, isolated instances) and then have something vote on the best result or use the most common result. This happens in things like rockets and aviation where you have multiple systems giving an answer and an orchestrator picking the result. I've tried…

But then, if an agent picks the best response, how would you know that that is reliable?

You could get the agents to output something structured and then use a deterministic test if you're worried about that.

Re: Agents need control flow, not more prompts

#77

Post by kelseyfrog »

rglover wrote: post #74

> Babysitter: Keep a human in the loop to catch errors before they propagate. This is the only way to guarantee AI usage doesn't burn you. Any automation beyond this is just theater, no matter how much that hurts to hear/undermines your business model. A bird sings, a duck quacks. You don't expect the duck to start singing now, do you?

I'm not sure I agree. Like all stochastic processes, LLM errors can be quantified. That makes each use case a risk-reward tradeoff where users can decide if the tradeoff makes sense for them or not. There are scenarios where errors are acceptable because the risks are low or errors are acceptable or the rewards make up for them. This is a process engineer problem where business and technology specifics matter.

Re: Agents need control flow, not more prompts

#78

Post by cassianoleal »

edgarvaldes wrote: post #16
bwestergard wrote: post #3

I agree with the sentiment, but I think the conclusion should be altered. When you hit the limit of prompting, you need to move from using LLMs at run time to accomplish a task to using LLMs to write software to accomplish the task. The role of LLMs at run time will generally shrink to helping users choose compliant inputs to a software system that embodies hard business rules.

Some have expressed the opinion in this forum that the future of software lies in programs that are created and adapted at runtime, using genAI. I don't know how far we are from that.

So we're back to vim over ssh in production, only without a human with _some semblance_ of judgement in the loop?

Re: Agents need control flow, not more prompts

#80

Post by empath75 »

I have heard this sort of thing a lot from people working with agents, and I just think it's fundamentally misguided as a way to think of them, and if you work with them this way, you are probably setting money on fire for no reason because the tasks you are able to perform this way _don't need agents to begin with_.

You might use an LLM api call here as a translation or summary step in a deterministic workflow, but they are not acting as agents, because they lack _agency_.

The value of using an agent harness is precisely that they are _not deterministic_. You provide agents a goal, tools and constraints and they do the task they were asked to perform as best as they can figure out how to do it. You may provide them deterministic workflows as tools they can call, but those workflows, outside of the agent harness itself, should not constrain what the agent does. You are paying a lot of money for agent reasoning, not to act as an expensive data transformation pipeline.

It may be the case that a lot of agentic workflows are more properly done with fully deterministic workflows, but the goal there should be to _remove the agents entirely_ and spend those tokens on non deterministic tasks that require agentic decision making.

I do think there are fundamental limits to what agents are capable of doing unsupervised and there does need to be a lot more human guidance, observability and control over what they are doing, but that's sort of the opposite of embedding them in deterministic workflows, that is more of team integration/communication problem to solve.

Post reply on HN