How many children do you know who formulate an objective before they go out to play?
How many great scientists really formulated a hypothesis before their great idea? Do you ever tell yourself that you can’t do something because it’s not justified by a clear purpose? Do you ever blame yourself when you can’t achieve your highest goals despite your best efforts? Why do so many of us feel our creativity is stifled by the machine-like integration of modern society? We weren’t born for this. It isn’t healthy for us, and deep down we know that. Something is wrong at a fundamental level with the assumptions that justify where our time is invested.
Link to originalSetting objectives can actually be bad for creative achievement, innovation, or even achieving the objective itself that you wanted to achieve. It can get in the way because it closes your mind to all the other things that could lead in different directions that would actually be opportunistic for you. In other words, it can be deceptive to set an objective.
And we did a lot of research in AI that showed this algorithmically. But then we wrote this book for general audiences, not AI audiences—although it was meant to be interesting to AI audiences as well. We were hoping other people could appreciate it because we started to believe—Joel Lehman and I, my co-author who worked with me on novelty search—we started to believe that the lessons there aren’t just algorithmic, but are actually social.
In other words, they apply to the way we run institutions, the way people run their individual lives, the way we run educational systems, the way we run businesses and investment—everything. Because everything in this world is saturated in objectives, including, by the way, social networks. They are extremely objectively driven. They’re based on maximization principles: you maximize likes or you maximize follows, you try to maximize exposure by maximizing attention, and then you get more, and it’s reinforced. It’s very objective.
So it reflects a widespread, ubiquitous culture, which is worldwide, which is really interesting. It’s just like we all believe in this idol of objectives, that it should guide everything that you do. The book is arguing that there are other incentives and other gradients that you should follow, like especially interestingness. Not knowing where you’re going to end up, but knowing that this path looks really interesting for independent reasons because it opens up a whole new playground of possibilities, even though I don’t know what the payoff will be. That is very important to the advance of civilization, but it is not recognized in the way that we institutionalize everything that we do.
And so, the algorithmic insight led to this kind of social critique view, and that is why we wrote this book. Because we wanted to—we thought this is a big problem. Granting and funding agencies run on objectives. This is probably the most salient thing for us because we were researchers. So when we have to ask for money to do research, we have to tell them what our objective is, and we’d be evaluated based on the objective and whether it’s worth funding the research. This is completely backwards if what I’m saying is actually true, which I’m very confident that it is.
… It’s not just science funding; it’s investing, it’s the way that we run the country, the way we run education …I became the worldwide focal point for people who don’t like the fact that everything in the world is objectively driven. It’s like I was the place you go to complain about the system. And everybody thinks they’re in this system. I mean, I shouldn’t say everybody. Of course, there are some people who are just invested in objectives, but you’d be surprised how few that is. I thought at first the book would be very polarizing and that there would be these two sides and it would be super controversial. But I rarely meet someone who really is willing to stick up for objectives. That’s actually quite unusual.
So the book seems to be a relatively popular message that most people agree with. But it’s very paradoxical because a lot of the people who I talked to are people who are literally perpetuating this objective system, and they actually hate it, you know? So I started to realize this. But the reason that they perpetuate the system is because everybody feels like they’re locked into it because of the next level up. So you could talk to somebody who’s running some billion-dollar government federal lab or something, and they allocate money very objectively to projects. But if I talk to that person, they’re like, “I hate the way this whole system works. We would love to change things like the way that your book describes, but we answer to Congress, or we answer to an executive, or we answer to our investors.” It depends what the organization is, but everybody feels like they answer to someone, and the someone they answer to is objectively oriented, and so there’s no way to just do something radical and tamp down those objectives.
And so I got to meet people at all the levels—at the top levels, the bottom levels, everybody affected by this system—and they all hate it. They’re all sick of it. And even in their personal life, they feel like they can’t actually just do things because they want to just do them because they’re fun or to explore. They have to justify everything they do. This is particularly true of adults. The younger you go, the less this is true, which is one of the sad things. If you’re five years old, this is not true. You just go to the playground and you do whatever you want; you don’t care what it’s going to do for payoff. But this is basically sucked out of us over the course of our education because the education system is extremely objective.
So I met people from all levels. I would meet diverse walks of life and also diverse age groups. I’d meet people like artists and doctors and retirement planners and military planners. I’ve met such a diversity of people. I met everything from the most senior person to a 14-year-old high school student. And the 14-year-old, I actually met because his grandmother found me from hearing some of my stuff and asked me if I would come talk to her grandson because he’s too obsessed with objectives.
It would take a conscious mass movement, a phase-transition in our collective thinking and organization (→ collective decision making) to change this.
Not only can you trust your gut instinct when it tells you something important is around the corner, but you should trust it, even if you can’t explain what that something is. You don’t need to make up a tortured reason to justify every little impulse you feel.
Link to originalAs soon as you formalize something, you block stepping stones and exclude the behavior of that might lead you to where you actually want to go.
See Kenneth O. Stanley - Novel Opportunities in Open-Endedness at UCL DARK for main points (on lessons from picbreeder).
Open-ended exploration is different from what we usually mean with exploration vs exploitation, because here the exploration is not random/unprincipled exploration, but very rich, and can actually be seen as a high dimensional form of exploitation.
Todo
→ impactful ideas are stepping stones onto many more interesting ideas
Link to original
→ following local gradients of interestingness → diverse exploration → serendipity
many ideas lead to nothing, but some ideas open up entirely new fields of inquiry
→ you don’t need to be the best in the world at any specific thing in order to achieve greatness, just the best at following your nose for the interesting (in fact if you set out to achieve any specific ambitiuous thing you’re less likely to achieve it … Why Greatness Cannot Be Planned)
→ Even if we were all equally smart, some people just by necessity are the ones who make the great discoveries, but they wouldn’t be made without the collective search process of all of us. “Genius is the summed production of the many, with the names of the few attached for easy recall.”
→ Just as there are no great causes behind earthquakes and great mass exinctions, great events in history do not require great men to bring them about.
drunkyard’s search
Also connects to https://www.julian.ac/blog/2025/09/27/giving-advice/
Some yappings form personal experience.
I often have this where I have like you know I want to read and really deeply understand the paper which leads me to go from X to Y to Z until I eventually end up at category theory so I kind of naturally have this branching diverging exploration process which is really good for um well getting a deep understanding and collecting stepping stones but at some point you do need to um focus on an objective again you know balancing exploration versus exploitation going from the particular to the general but also going back to the particular without which you’ll i mean you’ll still get places and if you’re really good at it maybe or according to this book even many more places but like there are real real constraints that eventually force you to make some trade-offs for the short or at least mid-term.
And the magic thing really is that if you do that this process of collecting stepping stones or opening doors it’s really amazing because you’re opening doors that you didn’t even know or couldn’t even anticipate it would open I mean to give one concrete personal example before I looked a bit deeper into probability theory I knew that it would lead to interesting places, like I had this feeling that it is a foundation I’m missing in order to more deeply understand some papers and concepts I’m learning about but I didn’t know it would connect to all these other things that I was currently exploring like I mean in retrospect it’s obvious but it would lead to things like deep connections to the free energy principle, variational auto encoders, evolutionary strategies and and many more things.
in spaces with power-law correlation structures (like most interesting search spaces), local gradients are uninformative about global structure, but self-similar patterns mean you can learn generalizable operators rather than paths.
→ Point objectives: “reach state X” → Goodhart’s law
→ Trajectory objectives: “follow path P” → still brittle
→ Process invariants: “maintain divergence/composability” → robust exploration
→Meta-learning: “learn to generate useful invariants” → open-endedness
“Get your head out of the clouds.” While the pressure to be practical clearly affects musicians, their stories reflect a wider cultural assumption: Following a path for its raw attraction is sillier than following it for its practicality.
“The willingness to switch directions throughout life or especially early life”
A silly personal little anecdote here again like I switched from the Technical University of Vienna to Johannes Kepler University or abandoning some paper replica due to bugs that I have a hard time fixing fixing. It’s not a finished product that I can show off as well as if I would have kept pursuing that path. The objective of finishing it at any cost or all cost but it’s still a stepping stone that taught me stuff and well making this sacrifice in a sense is not a sacrifice at all or I mean if you think about it in the sense of opening more doors for the future. Though this is not at all obvious beforehand or even while, or even, you know, it’s totally not obvious and that’s the hard part, judging, yeah, when it’s time to abandon something. Like it’s easier said than done. Sometimes it’s a bad decision. Sometimes you should just not give up and be relentless in finishing something. I guess that’s the hard part.
Who would have thought that so many disparate scenarios would follow this strange yet fundamental principle? The key is to be open to change, to a shifting landscape where appearances can be deceiving yet liberating at the same time. The great achievers are willing to abandon their original objectives and spring for opportunity when it arises. What is important in these scenarios is to avoid locking into rigid commitment to the original ambitious objective, and instead remaining mindful and open to where the present stepping stone might lead. Sometimes all it takes is sensing potential—whether it be in becoming a musician or finding a new way to cook—even if the true nature of that potential is still unknown.
pointless (a popular word for having no clear objective)
You would think that the best breeders would be the ones who conceived an objective image (i.e. something they want to evolve) and then bred towards it, but it turns out to be the opposite—the best discoveries on Picbreeder are always the ones that are unplanned.
unplanned random
structured exploration.
If our objective function forobtaining a picture like the Car is “how car-like is it?” then the Alien Face would be graded poorly because alien faces are definitively not cars. But the Alien Face in fact was the stepping stone to the Car, which shows you why always comparing where you are to where you want to be is potentially dangerous.
In pic breeder there is no final objective, the search process is not aiming to discover some ultimate picture.
Collecting stepping stones isn’t like pursuing an objective because the stepping stones in the Picbreeder collection don’t lead to somewhere in particular. Rather, they are the road to everywhere. To arrive somewhere remarkable we must be willing to hold many paths open without knowing where they might lead. Picbreeder shows that such a system is possible.
The notion of weakness, maximization or adaptability, composability.
Survive and reproduce can be more naturally seen as a constraint on evolution. In other words, it is a kind of minimal criterion that all creatures must satisfy to continue evolving.
A constraint like interestingness, learnability, efficiency, speed, novelty, diversity, complexity, …
Novelty can often act as a stepping stone detector because anything novel is a potential stepping stone to something even more novel. In other words, novelty is a rough shortcut for identifying interestingness: Interesting ideas are those that open up new possibilities. And while it might sound wishy-washy to go looking for “interesting” things, interestingness is a surprisingly deep and important concept. In the words of the famous philosopher Alfred Whitehead: “It is more important that a proposition be interesting than it be true.”
Novelty (and interestingness) can compound over time by continually making new things possible. So instead of seeking a final objective, by looking for novelty the reward is an endless chain of stepping stones branching out into the future as novelty leads to further novelty. Rather than thinking of the future as a destination, it becomes a road, a path of undefined potential. This non-objective perspective captures better the spirit of processes like Picbreeder, evolution in nature, and human innovation—ratcheting processes that build stepping stone upon stepping stone, branching and diverging ever outward to everywhere and nowhere in particular.
Consensus seeking and creativity are fundamentally opposed.
The drive towards super generalist models is somewhat misguided. Yes, we want models that are able to learn, to explore and learn from their experience but it might not be the easiest path to try to create agents that are capable of everything everywhere all at once but but to create specialized agents, niches, and so on.
And I mean of course the underlying architecture and training approaches can or maybe it would be nice if they followed the same or similar recipes but yeah I mean that’s a trade-off between how bespoke your solution is or how bespoke you can afford your solution to be.
Novelty is a much riche signal than distance to an objective.
Rather than relying on a false compass, novelty only asks us to compare where we are with where we’ve been.
In short, objectives mean sailing to a distant destination with an unknown path while novelty requires only steering away from where we’ve been already. Deviating from the past is simpler and richer with information because we can look at the whole history of past discoveries to inform our judgment of current novelty. So it’s not unreasonable to believe that novelty is a meaningful engine for progress.
Another clue to the importance of novelty in innovation is that humans tend to be very sensitive to it. Often we feel the urge to explore a particular path or idea despite being unsure where it might lead. Our intuitions and hunches often prod us in directions that might not be justified objectively but still lead to something different or interesting. So it’s no coincidence that the concept of interestingness comes up naturally when discussing novelty. When an idea feels genuinely novel, that’s often enough to make us curious. The idea interests us even if its ultimate purpose is unclear.
This insight connects to another common myth about achievement. This myth of
serendipity is that serendipity is an accident.
novelty search
deception
stepping stone
open-ended
serendipity
Kenneth O. Stanley
Joel Lehman