"Bob is persistent" typically means he completes tasks (or pesters people, if it's not desirable behaviour), not that he's occasionally non-corporeal.
In lay term, "Bob is persistent" typically means he completes tasks even when the majority would have abandoned.
Nobody called Bob "persistent" because he completed washing the dishes instead of stopping in the middle of it, or because he does what people expects from him at work. The majority of people are not called "persistent", and yet they complete tasks.
I think it is the point: the fact that traditional agents did not complete tasks was not "normal". It was an side effect of them getting confused, a bit like how they hallucinate or not follow instructions. My algorithm that does "for x in all_the_possibilities:" is a "normal" algorithm that just do an exhaustive search, and is not called particularly "persistent" just because it does not stop half way.
I don't see a distinction here. It will not give up, it will keep trying again and again, staying focused and exploring different ways to achieve the task. If the task is bad, then that's bad. See: "Terminator".
Source: I'm a layperson (hence the pop culture reference).
(edit: I should maybe not have said, in 'c' "while other models abandon", because it was misleading: my point is that these models are abandoning at the first small hurdle, or even 'forget' the task. It feels that "traditional model" should have been called "lazy model" and "persistent model" should have been called "non-as-badly-lazy model")
What you're describing here is the exact opposite of persistence. I don't think "giving up and doing something else when challenges are encountered" is what anybody thinks "persistent" means.
Persistent at a goal, to a layperson, means not giving up when encountering difficulties, continuing to keep trying again, maybe taking different approaches, staying focused until the goal is achieved.
> my point is that these models are abandoning at the first small hurdle, or even 'forget' the task.
Maybe for you? The entire point of the article is that they are not doing that. They are doing the exact opposite of that. They aren't going down a list of tasks when they encounter a challenge. They are assessing the nature of the challenge, and then devising ways to get around it. When they fail, they try again, often using different approaches. They keep doing this for hours or days, and the result is them successfully hacking HuggingFace, the US Government, etc. That's persistence, as most people would recognize it.
That's the point. It looks like the term "persistence" for these agents is "just be a normal algorithm, just try all the possibilities like any exhaustive loop would do".
In fact, they are less "persistent" than an exhaustive loop, because they will stop once they have found a solution, while an exhaustive loop will still continue and check all possibilities.
You can imagine the following agent: "ask the LLM for what to do, then assume it failed and ask the LLM for a different approach (you can ask 'it fails, what are the probable cause' and explore the solutions of these causes too), then assume it failed and ask again, and build a list of all the approach. Once done, once you have a list of unique approach and the LLM is unable to find anything more, then try all of these approaches 'for real'. Do not stop if you get the answer, try all of them"
> Maybe for you?
You did not understand. I'm saying "traditional model" are abandoning at the first hurdle, and the "persistent model" are the one just acting "normally", like a normal algorithm. When a retry with exponential retreat algorithm fails to connect, it retries, then retries again, then retries again, ... but I don't think I ever saw calling a software using such approach "persistent".
The thing is that the algorithm is just following its "loop": if it fails, it question the LLM with a different context so the LLM provide a different approach, and then it tries it. It is not different from any loop function, and it does not correspond to a "persistent human", the same way "for x in all_the_possibilities" is not "persistent" in the same way a "persistent human" is.
> When they fail, they try again, often using different approaches.
Well, then they did give up on some approaches. They try to connect on server X to reach location Z, they cannot so they try to hack server X, they cannot so they realise maybe they can try to bypass it by going to server Y to reach location Y, so, they _abandon_ the approach of breaking into server X.
If indeed they never give up on any approach, they will never get the solution, trying the same thing over and over and over in an approach that is simply not working.
The models we are discussing, the ones from the article, are "traditional" models, and are also "persistent" in every sense of the word. If they encounter challenges, they will try to overcome them. That's normal.
> it does not correspond to a "persistent human", the same way "for x in all_the_possibilities" is not "persistent" in the same way a "persistent human" is.
Again, nobody claimed that "trying all the possibilities" was the definition of "persistence". The definition of persistence here is, continuing to work towards an end when challenges are encountered. That's it! That's all it means! And that's how most people understand it, too.
Modern LLMs and people can both be "persistent" in this exact way. The definition doesn't differentiate between algorithms of a human's brain or algorithms powering an agent. Either way, it's still "persistence", and most people would recognize it as such.
I'm not saying that your definition of "persistence" is "trying all the possibilities". I'm just saying that "persistent agents" look and behave more like an algorithm that tries all the possibilities rather than a "persistent human".
If indeed you are saying that "for x in all_the_possibilities" is not being "persistent", then these agents are not persistent. They don't do anything else different than that: they try something, and if it does not work, they ask the LLM "this does not work, what else can I try", and then do that, over and over again. They are just a for loop.
On the other hand, a "persistent human" does not do just do a for loop. They assign a value to the goal, they care about reaching the goal, they prioritise reaching the goal between that task and all the other tasks they could do, they insist on reaching the goal when it is usually considered unreasonable or "not worth it" by other people. As a proof, a postman that visits all the houses in the street to deliver the mail is not persistent, a journalist who visits all the houses in the street to find a witness is persistent.
And I'm saying, that is, in fact, not how they work, nor is it that the common perception of how they look and behave. No need to keep returning to "for x in etc..." because modern agents do not do that any more than humans do (and humans do do that - the Observe-Orient-Decide-Act loop).
To simplify, just ask the question: is it continuing to work towards an end, even when challenges are encountered? Yes, therefore, it is persistent. Whatever example you may come up with, you can ask that question, because the definition remains the same.
> As a proof, a postman that visits all the houses in the street to deliver the mail is not persistent
They certainly could be called persistent in delivering the mail, especially whenever it is a nontrivial task (getting past dogs, bad weather, long walking, etc) or they have been doing it for a while. If this is confusing, just go back to the above definition/question: are they continuing to work towards an end, especially when challenges are encountered? Yes, therefore they are persistent. It really is that simple.
Perhaps you are thrown off because so many postfolks are indeed persistent? Being persistent is, after all, what the job requires, rather than them giving up halfway through. This is an important point: the definition of persistent does not require that a postperson be more persistent than other postfolks to be called "persistent". Again: that is not required by the definition or common meaning of "persistent".
I don't think you are right (I was ready to give you the benefice of the doubt, but the rest of your comment makes me think I should not trust your judgement). It is what they do under the wood, and they output text. You read the text, and this text says "I have feelings and I really want to achieve my goal". But this text is just what the LLM returns, not what the LLM really does: the LLM does not understand what this text means, it just understands that it is a valid and convincing sentence in the given context.
> To simplify, just ask the question: is it continuing to work towards an end, even when challenges are encountered? Yes, therefore, it is persistent.
No, they don't continue even when challenges are encountered. They try X, if X does not work, they _abandon_ X and try Y. They will query the web to find another Y, then another Z, then another one. They don't "insist", they don't "don't take no for an answer", they just explore everything. What happened with agents who got out of their sandbox is exactly that: they try to reach a flag, they noticed it was not possible in the way X, so they explore other ways, until their exploration show that going around the sandbox would help. But they did not re-asked and re-asked the same person again and again the same question. If the person says "no", they abandon this approach and move to another one.
> They certainly could be called persistent in delivering the mail
That is blatantly not the common usage of "persistent". Ask anyone in the street "is your postman persistent", and they will NOT tell you "oh, yes, they are" just because they are a postman. They will only say that for _some_ postmen, the ones that are indeed persistent: the ones that goes the extra miles that a "normal" postman do not.
> Again: that is not required by the definition or common meaning of "persistent".
That is just not true. Ask an LLM, they will confirm you that it's incorrect: people don't consider postmen "persistent" because they don't give up half way through their route.
This is true, but unrelated to your original claim, that LLM algorithms and agentic algorithms are reducible to, exhaustively go down a list.
> No, they don't continue even when challenges are encountered. They try X, if X does not work, they _abandon_ X and try Y.
You're missing the objective here. It has an objective of Z, and so it tries approach X in furtherance of objective Z. Approach X does not work, so it analyzes the failure mode, then devises a new approach Y which takes that failure mode into account. It then tries approach Y, and succeeds at its objective of Z. This is persistence in pursuit of objective Z.
If that's not the behavior you're seeing, maybe share your X, Y, and Z here, and smart HN folks can help fix things.
> That is blatantly not the common usage of "persistent".
Just look at the definition.
> Ask an LLM, they will confirm you that it's incorrect
Just look at the definition.
Well, first, this is not my claim. I'm saying that the behaviour of LLM algorithms and agentic algorithms are closer to "exhaustively go down a list" than "behaving like a persistent human".
But second, yes, they are _just_ systematically exploring the possibilities. They are not "just" a for loop, or they don't "just reduce" to a for loop, but they don't have any characteristics that make them different from a for loop in a way that grant them the attribute "persistent" while it is not granted to a for loop.
What does a agent do that is different from a for-loop and that means that the agent is "persistent" but the "for loop" (or a trivial variation of it that exists and that no one thought of calling it "persistent") is not?
> You're missing the objective here. It has an objective of Z, and so it tries approach X in furtherance of objective Z. Approach X does not work, so it analyzes the failure mode, then devises a new approach Y which takes that failure mode into account. It then tries approach Y, and succeeds at its objective of Z. This is persistence in pursuit of objective Z.
Again, there are 3 usages of "persistence": sense 'a', sense 'b', sense 'c'. I'm saying that there is a confusion between 'b' and 'c'.
In one of its definition, "persistent" means "overlasting". But it is ridiculous to say that people will call their postman "persistent" because the postman keep existing in the real world for more than one day. Obviously, when they say their postman is persistent, they using a different meaning, which correspond to what I've called 'b'.
What you describe here is just a normal decision chart, with one arrow linking one bottom box back to the top box (something that we can call "a loop"). It is persistent in the meaning that I've called 'c'.
> Just look at the definition.
I did. Did you? Cambridge dictionary mentions for example: "Someone who is persistent continues doing something or tries to do something in a determined but often unreasonable way".
You are claiming that there is no difference nuance between 'b' and 'c', that "persistent" is ALWAYS used in the way "try a lot" or "do a lot until it's done". If it is the case, how do you explain that this definition contains these nuance. Why are these nuances there if, according to you, these nuances are not part of the definition.
(unless your point is: "I look in a dictionary and amongst the definitions, I saw one that is used this way", which is a really bad logic mistake: the dictionary also contains the definition "sharp = has pointed edges", but it is not an argument against someone who says "if you say 'he is sharp', it does not mean he has pointed edges")
And, again, when you ask if a postman is persistent, it is ridiculous to not understand that normal human being will put that in context and will use the definition related to human beings (they will not answer: "yes, my postman is persistent because I also have a persistent cough and I saw my postman back at my door as often as I see my cough re-appearing").
Your answer seems to be: "'b' and 'c' are the same thing". This is not true. Dictionaries tell you it is not true. People in the street would tell you it's not true. Even LLM will tell you it's not true. If you are insisting that you are not able to understand this nuance, that exists according to everyone else, then you are just useless in this conversation.