Comment by dlenski
7 hours ago
This article reads like a description of gambling-addiction behavior; the author appears to be addicted to using LLMs.
He's eagerly awaiting his next hit of dopamine from his favorite model. He's setting timers to be ready for when his next hit comes available. He's spinning up unnecessary queries just to start the timer ticking on new models.
You could basically write the same article about some guy who sits in a casino all day eagerly awaiting double-your-winnings bonuses or similar.
> He's spinning up unnecessary queries just to start the timer ticking on new models.
This one just makes sense though. If you have a body of work to do that you know will exceed your 5 hour limit, then sending a message 3 hours before you start so that the reset happens in the middle enables you to do a task in one sitting.
Gambling addition implies dopamine hits from irregular and uncertain outcomes: as I note in the post, I don't get a dopamine hit from running agents. I know people say "LLMs are just gambling because they're next-token-maximizers that can't write real code" but with GPT 5.6 Sol (and a few new tricks I discovered) the outputs are much less irregular and uncertain. It's just typical engineering.
"Not wanting to waste money" is the polar opposite of gambling.
> Gambling addition implies dopamine hits from irregular and uncertain outcomes
Your post literally describes your fascination with trying to figure out the pattern of a "random" reward that you get, and trying to maximize the value you get out of it.
I put "random" in scare quotes because I strongly believe that—just as slot machine payouts are carefully structured to keep you playing—these LLM resets are structured to keep heavy users like you coming back to max out their usage, and to progressively upgrade it.
Several other commenters have also stated this same suspicion about the pattern of resets you're describing.
> "Not wanting to waste money" is the polar opposite of gambling.
From everything I've read about gambling addiction, particularly Jay Caspian Kang, that seems wrong.
The desire to "not waste money" and "get back to even" seems like a huge part of what motivates gamblers to keep gambling.
>The desire to "not waste money" and "get back to even" seems like a huge part of what motivates gamblers to keep gambling.
As someone who had family members go through gambling addiction this is the primary mechanism behind it.
Addicts don't see it as "cool fun dopamine kicks" but instead find it the only way they can get back to normal/where they are supposed to be
1 reply →
> dopamine hits from irregular and uncertain outcomes
Like the LLM getting the solution right?
For the problems I work on with GPT 5.6 Sol and the checks and balances I have in place, I estimate:
- 80% of prompts get everything correct and are confirmed correct with manual validation
- 19% of prompts make a minor mistake based on an ambiguity of the original prompt (user error not LLM error), but then reliably fixed in a followup prompt
- 1% of prompts causes more problems than it solves and is more pragmatic to just revert
For 99% good output, there isn't much of a dopamine rush when there is good output. The dopamine rushes are for the <1% odds.
From the other replies on this post, I suspect no one believes me, but I am offering these numbers in good faith.
1 reply →
> and a few new tricks I discovered
This right here. Any gambler would recognize that statement.
Said tricks improve the output in an objective measurable manner, not theoretical, vibes, or gambler's fallacy. (blog post forthcoming on that)
I've been researching LLM prompt optimization for longer than ChatGPT has existed; I was successfully optimizing the output of GPT-2 back in 2019.
2 replies →
I think it is because the plans are crazy expensive. when you pay 200-300$/month for an online subscription, its normal to want to extract as much value as possible.
No it’s definitely addiction
Oh this is a good idea actually, that reset checker site allows for setting up a scheduled agent job, so that GPT alerts me when there's been a reset :)
> This article reads like a description of gambling-addiction behavior; the author appears to be addicted to using LLMs.
you're projecting, it's just insanely irritating to work with a tool that 1) limits its' own use 2) with a random interval.
keeping in mind that plenty of people are making money on token use..
this guy sets a timer to wake up for work; he appears to be addicted to work.
If you don’t want 1 or 2 then pay by the token. If that’s too expensive for you then now you know why 1 and 2 exist.
That's fine, but that doesn't mean that people taking steps to get the most out of what they have with 1 and 2 are now somehow gamblers.
I have a subscription. If I don't have anything to do at the moment I don't use it. I don't think I need to set a timer every five hours and come up with tasks to do just to use my subscription. Seems like odd behavior?
I also have a Netflix subscription. I watch a couple of things on it and stop. I don't think to myself I need to maximize my subscription so let me watch movies all the time and wake up at 2 AM to make sure the next movie starts.
I encourage you others to keep on minimizing so us others can keep in maximizing. Balance!
> it's just insanely irritating to work with a tool that 1) limits its' own use 2) with a random interval.
Do you understand how the psychological response to the "random" disappearance of an annoyance is pretty much exactly the same as the psychological response to the "random" appearance of a reward?
I put "random" in square quotes because neither are in fact totally random, but both are clearly quite carefully engineered to provoke the desired response.
> you're projecting
I am not projecting. My total lifetime gambling consists of maybe 10 or 15 cash poker games with high school friends, ten minutes at a casino in Montréal which I found a revolting experience, and receiving a few $1 scratch lottery tickets as party favors.
How does that mean you're not projecting? Yes if you oversimplify an LLM's responses to be random, and you squint real hard, it kinda resembles gambling, but an essay's worth of words is more meaningful to a human reading them than a human pulling a lever on a slot machine hoping for three sets of three cherries.