Agents need control flow, not more prompts
bsuh.bearblog.dev
Agents need control flow, not more prompts
1–10 of 348 posts
Re: Agents need control flow, not more prompts
#2If you're trying to get reliability and determinism out of the LLM, you've already lost
Re: Agents need control flow, not more prompts
#3I 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.
Re: Agents need control flow, not more prompts
#4I mean we have Langgraph, BAML etc
Re: Agents need control flow, not more prompts
#5Generally agree with this stance case in point: the breakthrough in ai coding was not that AI intelligence increased as much as that a lot of the core process execution moved out of the LLM prompt and into the harness.
Re: Agents need control flow, not more prompts
#6agreed - this is what we’ve been trying to build at scale.
Re: Agents need control flow, not more prompts
#7[dead]
Re: Agents need control flow, not more prompts
#8Are you the guy who used to write MapleStory hacks?
Re: Agents need control flow, not more prompts
#9It's the right direction, but control flow introduces limitations within a system that is quite adaptable to dynamic situations. The more control flow you try to do, the more buggy edge cases that pop up if done poorly.
Still have yet to see a universal treatment that tackles this well.
Re: Agents need control flow, not more prompts
#10This is why I frequently refer to "next generation AIs" that aren't just LLMs. LLMs are pretty cool and I expect that even if we see no further foundational advancement in AIs that we're going to continue to see them exploited in more interesting ways and optimized better. Even if the models froze as they are today, there's a lot more value to be squeezed out of them as we figure out how to do that.
However, there are some things that I think need a foundational next-generation improvement of some sort. The way that LLMs sort of smudge away "NEVER DO X" and can even after a lot of work end up seeing that as a bit of a "PLEASE DO X" seems fundamental to how they work. It can be easy to lose track of as we are still in the initial flush of figuring out what they can do (despite all we've already found), but LLMs are not everything we're looking for out of AI.
There should be some sort of architecture that can take a "NEVER DO X" and treat it as a human would. There should be some sort of architecture that instead of having a "context window" has memory hierarchies something like we do, where if two people have sufficiently extended conversations with what was initially the same AI, the resulting two AIs are different not just in their context windows but have actually become two individuals.
I of course have no more idea what this looks like than anyone else. But I don't see any reason to think LLMs are the last word in AI.