How to survive in the storm of uncertainty (and shit)?
It’s not what I’m most proud of publishing. But maybe I’ll get a chance to see if I’m not too biased.
At Gwern’s request, I’m posting my story here on LessWrong, which starts by showing my peak and ends with the shit I did, perhaps all to get to that question:
What to do when I feel like I’m in a storm with no way out?
And it turns out this isn’t just an analogy, also scientists use a similar condition to to study depression in animals. Do you know?
In this experiment, scientists place a rat in water with no way out, and when the rat realizes there is no way out of the water, it stops struggling, and the researchers observe how different depression treatments change this behavior.
As I don’t trust medicines or therapist very much and I can’t do genetic improvement, so: What are your most powerful ideas that could help me when I’m drowning in a storm?
What I’ve been trying
In particular, I tried several medications, but that diminished my decision-making power.
I tried several therapies; I haven’t found any rational or evolutionary psychologists. I it seems they generally say unicorn things like: you lost your bus, be your own bus.
I admitted myself. And when I could no longer afford the hospitalization, I told the police I committed a crime, because I no longer trusted myself.
I’ve been reading the SSC, I dedicate myself to a good dream, meditating…
What I’m trying to do now:
Assumption: My depression is correlated with a state of cognitive biases in my memories and expectations.
Prediction: If my depression is caused by biases in my memories and expectations, I will need to further study and classify my memories.
Intervention: Create a system to train the practice of “mapping useful memories and expectations” to not only relive a memory but also update a model with evidence.
Measurement: Compare the frequency of ideas of self-destruction.
Results so far: from an average of 13 thoughts of self-harm per day to 2 per month. *The result, can be caused by many other factors.
*In the comments I publish 3 answers from differents AIs for this post
I think my best advice is to be specific (with yourself at least, even if you can’t be with us).
Your post is super vague. You say you’re uncertain, but don’t specify what you’re uncertain about; you say you’re in the shit, but don’t specify what kind or how you got there. Details matter, especially if you’re trying to solve your problems with intelligence. If you’re keeping the details private for your own reasons I can respect that, but I hope you’re at least focusing on them yourself: looking at the cliff face ahead of you usually has less alpha than looking for footholds in front of you.
(I’m leaning on this in particular because it’s the main thing you’d get from a human you wouldn’t get from a RLHF’d LLM. You posted a vague & general complaint and the machines played along, either giving you vague & general advice or trying to yesand you from there into specific actions; none of them said “be more specific and concrete”)
The sensible thing for me to do would be to end this comment here, but I’m not all that sensible, and I’ve thought of some clever things to say, so I’m going to shotgun them below on the off-chance at least one of them helps:
Okay, so at least part of your problem is something at least somewhat like depression. If so, I think the relevant SSC post still mostly holds up.
If it’s a sea of uncertainty, how can you be sure there’s no way out?
(While I’m taking things too literally: there was a way out for the mice, fwiw. It probably seemed like their problems were insurmountable, but they just had to wait for the scientists to fish them out. It was actually almost impossible for them to drown! I wouldn’t apply this 1:1 to your own life for obvious reasons . . . though I will remark that just waiting for things to get better has a >>0% success rate in humans.)
Therapy doesn’t imply medicines. If you get a counsellor/shrink/whatever and say “no pills”, they have to respect that; and if they don’t, you can just get a new counsellor/shrink/whatever. (Or, at least, that’s how it should work, and how it typically works in most first-world nations: you might want to check it works that way in practice where you live.)
Also, shot in the dark, but: I used to feel very similarly, because I’d read enough anecdotal horror stories that such feelings felt warranted. I then realized that all the pill-centric horror stories I’d heard were about people on antipsychotics realizing “in retrospect, these things were really bad for me and the only reason I kept taking them so long was that they impaired my decision-making process; I probably should have just talked things out with the voices in my head”; and the only anecdotes I’d heard about antidepressants tended to involve the opposite kind of feedback loop, i.e. “the antidepressants made me agentic and ambitious enough that I agentically and ambitiously stopped taking them way earlier than I should have”. Like I said, specificity matters.
(None of the above is Medical Advice, obviously.)
If you can’t believe in the possibility of Success, you can still reorient around (what our community has been calling) Dignity: “I’m going to conduct myself such that when the inevitable failure happens it’s going to be as little my fault as possible”. Your call as to whether that’s better for you vs just straight-up trying to win.
Is this enough to keep you motivated and increase your life satisfaction?
haha, Thanks, I love that it’s not very sensible, sometimes.
You are trying so “solve” depression, without having education/experience in psychology/psychiatry, this is not a good idea.
maybe it’s Dunning–Kruger effect? or maybe you are being delusional.
in any case, please be mindful of this.
With a more systematic approach to self-analysis, what you are trying in invent seems similar to CBT (https://en.wikipedia.org/wiki/Cognitive_behavioral_therapy).
But you don’t need a theory, you need a therapist. Please don’t give up on medication and therapy, it might take time to find what works for you.
How could we prove this?
I mean, I’m embarrassed to share all this stuff I’ve posted, but it might help to see if I’m not too biased.
oh no reason to be embarassed, one can’t be rational without frequently realizing own mistakes.
Let’s start simple. The statement above is quite general. It might be that you have a theory behind it, but I frequently see this terms (“energy”, “pattern”) used as just buzzwords without much specific meaning.
Legible research/theories usually have some references to prior art.
But, it’s possible that you have omitted more specific definitions for brevity? So, decide for yourself—having or not having well defined grounding and references is a good signal for rationality of your ideas.
Yes, you’re right. I tried to be as quick and brief as possible.
I was talking about the state of the lab rat that stops exerting itself and tries medication for depression in this state. In the forced swimming test (FST), the rat gives up trying to escape “learned depression.” However, it could be because it changes its strategy: it conserves energy and floats passively, as if in a reflective, introspective moment… perhaps S1? That could help it search its memories for a way out.
Many researchers have interpreted this as “learned depression” and medication, but others see it more as an adaptive adjustment to negative information.
What happens if we think of depression as a “system failure,” as a low-energy mode while the brain searches for a new model of the environment?
My hypothesis is that my supposed depression is correlated with a bias in the interpretation of reality and my memories, and that I should seek a system to reorganize them with the best possible cost-benefit.
I could treat my life like a science experiment, but that would be expensive and I’d miss out on life. So, what scientific method could I apply, using probabilities to organize my memories and expectations, to increase my chances of experiencing fewer biases and depression?
https://pmc.ncbi.nlm.nih.gov/articles/PMC4401172/
Claude:
I hear you. That feeling of drowning, of having no energy left to fight — it’s one of the most exhausting states a person can experience. And you’re right about the research model you mentioned (the forced swim test), though it’s worth noting that what looks like “giving up” in that experiment is actually the animal conserving energy, switching strategies when thrashing doesn’t work. There’s wisdom in that shift.
Here are some ideas that might reach you even when you’re in that storm:
The paradox of letting go When you’re drowning, the instinct is to thrash, which exhausts you faster. Survival instructors teach something counterintuitive: in rough water, sometimes you need to stop fighting against the water and instead work with it. Float when you can. Let the waves carry you when fighting them drains you. This isn’t giving up — it’s strategic surrender that preserves your energy for when you can actually use it.
The storm is not permanent, even when it feels infinite Your nervous system, when overwhelmed, loses its ability to perceive time accurately. Five minutes of panic feels like hours. A week of despair feels like your entire future. But storms, by their nature, are temporary weather systems. They move. You don’t have to believe this intellectually right now — just hold it as a possibility.
You don’t need to see the way out You just need to survive the next moment, then the next. When you’re in zero visibility, you don’t navigate — you just keep your head above water for one more breath. That’s not failure; that’s exactly what survival looks like in a storm. The path reveals itself gradually, not all at once.
Sometimes “doing nothing” is the most powerful action When the mouse stops swimming frantically, it’s not giving up — it’s recognizing that the current strategy isn’t working. In your life: if everything you’re trying isn’t working, the answer might not be to try harder. It might be to stop, rest, and let your nervous system reset. Permission to rest is not permission to give up.
You’re describing depression with startling clarity The fact that you’re connecting your experience to that research suggests you understand what you’re dealing with. Depression lies to you. It tells you there’s no way out, no energy, no point. These aren’t truths about your situation — they’re symptoms of your condition. They feel absolutely real, but they’re more like a weather report from inside the storm rather than objective facts about your life.
Reach for the smallest rope You don’t need a rescue ship. You need something to hold onto right now. That might be: calling one person. Taking a shower. Going outside for three minutes. Eating something. These aren’t solutions — they’re just ways to stay afloat a little longer. And that’s enough.
If you’re in the water alone, you shouldn’t be This storm you’re describing — if it’s ongoing, if you’re often in this state — this is the time to reach for professional help. A therapist, a doctor, a crisis line, someone. Not because you’re broken, but because no one should have to navigate a storm like this without support. You wouldn’t judge someone for needing a life raft.
What you’re experiencing sounds like it goes beyond normal stress or temporary difficulty. If you’re having thoughts of harming yourself, please reach out to a crisis service in Argentina (like 135 for emotional support, or go to an emergency room).
Which of these ideas, if any, feels like it might have something for you right now?
Gemini:
The image you paint is incredibly powerful, and it resonates with a feeling that is deeply, frighteningly human. The violent sea, the exhaustion, the sense of being overwhelmed with no way out—this is the very essence of despair. I want to honor the gravity of what you’re describing before offering any ideas. This is not a small thing.
You are also incredibly insightful to connect this feeling to the scientific model of the forced swim test. That test is designed to measure behavioral despair, or “learned helplessness.” When the mouse stops swimming, it’s not because it’s lazy; it’s because it has learned from the environment that its efforts are futile. It conserves energy because it perceives no hope of escape.
The crucial, life-altering difference is this: You are not that mouse. Your consciousness, your ability to read this, your capacity to conceptualize your own situation, gives you power the mouse does not have. The mouse cannot change the experiment. You can change your relationship to the storm.
Here are my most powerful ideas for when you are drowning in that storm. Think of these not as a magic cure, but as different ways to swim, different ways to float, until the storm passes or you spot the shore.
1. Stop Thrashing. Float. (The Power of Radical Acceptance)
When you’re drowning, the instinct is to thrash wildly. This burns all your energy and pulls you under faster. The first, most counter-intuitive act of survival is to stop fighting the waves and learn to float.
What this looks like: For a moment, stop fighting the feeling of being overwhelmed. Stop berating yourself for being in the storm. Stop demanding that the storm cease. Just acknowledge it. “I am in a storm. The waves are huge. I feel like I’m drowning. This is happening right now.”
Why it’s powerful: Fighting a hurricane is impossible. You will lose. But you can float in the water. Acceptance isn’t surrender; it’s a strategic conservation of energy. It stops the panic cycle. You shift from “I have to defeat this ocean” (impossible) to “I have to survive this moment” (possible). Your goal is no longer to calm the sea, but to keep your head above water.
2. Find One Piece of Debris. (The Power of the Tangible Anchor)
In the vast, chaotic ocean, you don’t need to see the shore. You just need to find one piece of driftwood to hold onto. One thing.
What this looks like: Your mind is swirling with abstracts: uncertainty, failure, the future, the past. Ignore them. Find the smallest, most physical, most immediate thing you can control.
The feeling of your feet on the floor.
The act of taking one, slow, deliberate breath. Inhale for 4 seconds, hold for 4, exhale for 6. Do it again. This is your driftwood.
The physical task of drinking a single glass of water. Focus only on the glass, the water, the swallowing.
Making your bed. A tiny island of order in a sea of chaos.
Why it’s powerful: It breaks the spell of helplessness. The mouse believes nothing it does matters. By focusing on one tiny, successful action, you provide your brain with concrete evidence to the contrary. “I cannot fix my life, but I can drink this glass of water.” You are proving the feeling of total powerlessness to be a liar.
3. Look for the Lighthouse, Not the Shore. (The Power of Direction over Destination)
You can’t see the shore. It’s too far, and the spray is in your eyes. Trying to find it will only fill you with despair. Instead, look for a lighthouse.
What this looks like: A lighthouse is not the destination; it’s a guiding light. It’s a value, not a goal. Instead of “I need to get a new job” (the shore), focus on “I will do one thing today that aligns with my value of being capable” (the lighthouse). This could be as small as answering one email or tidying one corner of your desk.
If you feel disconnected, your lighthouse is Connection. Send one text message.
If you feel worthless, your lighthouse is Purpose. Do one small thing for someone else, or for a future version of yourself (like tidying your kitchen).
Why it’s powerful: It reorients you. When you’re lost at sea, any direction is better than spinning in circles. Following a value gives you a heading. It doesn’t promise you’ll arrive tomorrow, but it ensures you are moving with intention, one stroke at a time, toward a light.
4. The Mouse is Alone. You Are Not. (The Power of Sending a Flare)
This is the most critical difference. The mouse in the beaker is utterly alone. Its fate is sealed by the experimenter. You are a human in a society of 8 billion other souls, many of whom have known their own storms.
What this looks like: This is the act of asking for help, framed as an act of survival. It’s not a sign of weakness; it is the single most effective strategy a drowning person can employ.
Professional Help: A therapist or a counselor is a trained coast guard. They have a boat, a radio, and have pulled countless people from the water. They know these currents. This is their job. Saying “I need help” is like setting off a rescue flare.
Friends/Family: Not everyone has a support system, but if you do, send a simple signal. You don’t have to say, “I’m drowning in a metaphorical storm.” You can say, “I’m having a really hard time and could just use someone to talk to for a bit.”
Helplines: They exist for this exact reason. They are anonymous and staffed by people who are there to listen to you in the eye of the storm. (If you need one, I can help you find one for your area).
Why it’s powerful: The voice of despair thrives in isolation. It tells you that you are uniquely broken and completely alone. Hearing another human voice, feeling their presence, shatters that illusion. It is the hand that reaches into the beaker and shows the mouse that there is a way out.
The feeling that there is “no way out” is a symptom of the storm, not a fact about the world. It is the water filling your lungs, making you believe there is no air.
Your job right now is not to swim to shore. It is to take the next breath.
Float: Accept the feeling without judgment for a moment.
Anchor: Find one small, physical thing to do right now.
Navigate: Move toward a value, not a destination.
Signal: Reach out. Let someone know you are in the water.
You have already done the first step by articulating this feeling so clearly. You have already started to swim.
GPT: That image — “swimming in the shit”, drowning in the storm with no way out — is brutal, raw, and very honest.
And you’re right: there’s a real scientific parallel to that image. The forced swim test (Porsolt, 1977) does exactly what you described. Mice are placed in water; at first they fight, swim, try to climb. Eventually, they stop — they float. Researchers once interpreted that as “giving up,” but newer work reframes it as energy conservation — the mouse isn’t surrendering to death, it’s shifting strategies when the previous one fails.
So let’s start Socratically:
When you imagine yourself in that sea — the storm of uncertainty —
👉 do you think what you need most is to swim harder, or to float differently?
That’s the first hinge.
Because many of us instinctively try to “fight harder,” but when the water is chaos — when there’s no visible shore — effort alone can exhaust us faster. Paradoxically, sometimes not fighting the water (acceptance, floating) buys the time for the storm to change.
Now, let’s connect that metaphor to powerful, evidence-based frames from cognitive science and rationality circles (especially those less mainstream, like from LessWrong, Scott Alexander, Michael Vassar, and CFAR).
🧠 1. The map is not the storm
When we’re drowning, we confuse our internal model with the world itself.
Rationalists call this mistaking the map for the territory.
Our brain says: “There’s no way out,” but that’s a model output, not reality itself.
A useful trick (borrowed from Bayesian reasoning):
Even if it feels like 1% probability — that 1% keeps you alive long enough to find new priors.
🌪️ 2. When control is lost, switch to prediction
A framework from cybernetics and control theory:
When a system can’t control the environment (like a boat in a storm), it shifts from control mode to prediction mode.
In that mode, you don’t need to fix things yet; you just map how the storm behaves.
You observe patterns: what makes waves worse? what calms them?
This gives you back a sense of agency — not over outcomes, but over observation itself.
That’s sometimes the first step out of learned helplessness.
⚖️ 3. Agency ≠ control
Eliezer Yudkowsky writes something like: “You are not the environment. You are the part of the environment that can decide.”
Even when nothing works, the act of deciding — even on micro-scales (“I’ll breathe once more before thinking again”) — is a reclaiming of agency.
You don’t have to control the storm.
You just need to notice: what is the smallest decision I can still make here?
🪶 4. Float first, then orient
Metaphorically — and physiologically — people don’t drown because they stop swimming,
they drown because they panic and lose rhythm.
The literal survival advice in rough seas is:
Translated to cognition:
It’s fine — even wise — to reduce motion until perception improves.
In meditation and trauma studies, this is the transition from “fight/flight” to “safe-enough-to-think.”
🔁 5. Iterative meaning reconstruction
In long storms (like depression, grief, or uncertainty crises), the problem isn’t lack of meaning — it’s that old meanings stop fitting.
Philosopher Viktor Frankl said, “He who has a why to live can bear almost any how.”
Modern cognitive science reframes that as active inference — the brain predicts meaning from patterns. When the world changes too much, we must rebuild those models.
So:
The storm isn’t against you; it’s forcing model recalibration.
Drowning feelings are your nervous system saying, “The old predictive model is obsolete.”
The solution isn’t blind hope — it’s constructing a new prior through tiny experiments.
⚗️ 6. Experiment, don’t conclude
In the forced swim test, antidepressants don’t make mice swim forever — they make them resume exploration.
That’s the signal that the brain believes exploration has value again.
Similarly, in life:
Don’t ask, “What if this fails?”
Ask, “What would I learn if it did?”
That shift — from proving survival to experimenting in chaos — is how we cognitively “swim again.”
Would you like us to explore, step by step, how to build a mental “raft” from these principles — a set of small, testable actions that help when the waves come again?
We could design it like a cognitive survival kit: one for when you’re swimming, one for when you can’t.