This is right but missing that the goal of these corporate cultural proclamations is optimizing for people who are true believers in the mission. Whether that leads to better business outcomes than optimizing for really smart people who believe in work-life balance… I personally doubt.
Readit Newsadamiscool8 commented on Fundamental Flaw of Hustle Culture brodzinski.com/2025/08/ai... · Posted by u/flail
adamiscool8 commented on NautilusTrader: Open-source algorithmic trading platform nautilustrader.io/... · Posted by u/Lwrless
I can try a dynamic intermediate stop-loss point, with the intended goal that is not too early where it triggers often, and not too late where the loss mounts geometrically. This is intended to greatly limit the max loss per trade, which is good, but it still has significant risk of being triggered unnecessarily. I am highly skeptical that this will work, because I even see in the chart that it doesn't, but it's worth an actual test.
Yes, optimizations of this form can work to manage tail risk on an edge and can reproducibly lift expectancy for a strategy. GP is essentially claiming no positive edge can exist, which is false - though these edges may be short-lived and dependent on particular market regimes.
adamiscool8 commented on NautilusTrader: Open-source algorithmic trading platform nautilustrader.io/... · Posted by u/Lwrless
The market is adaptive, particularly with options, and will adapt to bust your approach in a heartbeat. It will in general adapt to bust a lot more sophisticated approaches. This is not physics. The underlying assumptions change.
In general, yes - no edge is forever. But that doesn't mean trading is a coin flip where no edge can exist. The market is adaptive because humans are adaptive - but, for example, their machine offspring are often slightly less adaptive and create opportunities for persistent returns. Even more so for most retail where your position size isn't creating slippage.
adamiscool8 commented on NautilusTrader: Open-source algorithmic trading platform nautilustrader.io/... · Posted by u/Lwrless
OutOfHere gets it. Think about it in terms of probability. The closer to the current price your stop loss is the higher the odds of it being triggered by random market fluctuations.
The same applies to your profit target. This means that if your profit mark is $10, and your stop loss is $5 you will lose roughly twice as often as you win, all other things being equal.
What you actually CAN do is use smart money management, (something like the Kelly Criterion) to ensure that you properly capitalize on any slight edge you do manage to find without going broke in the long term.
That of course requires you to find a bet you can win 51% of the time, and that you be made of iron when it comes to sticking to the plan. Most folks can't.
All of these points are irrelevant. If you have the data that shows 99.5% win rate, you would have the data on your expected win size, and could compute a fixed loss stop that would keep you on-side. In the example, which I'm assuming must be hyperbolic, your average win would only need to stay >1/199th of your average loss. I would agree that if a person cannot manage their positions to this, that person should stick to investing.
adamiscool8 commented on NautilusTrader: Open-source algorithmic trading platform nautilustrader.io/... · Posted by u/Lwrless
I used to trade options and had about 99.5% success on all my trades
The problem is the 0.5% of the time, it erases all the gains made on the successful ones.
I'm convinced without information edge or some capital sunk cost edge (for HFT) you are literally just flipping coins when it comes to trading.
What's dangerous is fixation on strategies that form after a period of success.
All in all, I think just buying stock and holding is the best and most successful approach to making money.
Maybe when AI becomes sentient it will know on which days it make sense to buy and sell iron condors with huge ass wings....
This doesn't make sense. If you had a 99.5% success rate, you could simply use a fixed $ stop and clean up. I agree you need an information edge, but the difficulty of finding one inversely correlates with your scale. Buying and holding is the best strategy for almost everybody - but that is orthogonal to whether trading is a "coin flip" vs mining an edge.
"I think it's pretty likely the entire surface of the earth will be covered with solar panels and data centers." - Open AI Chief Scientist Ilya Sutskever
I'm surprised the future of technology is in the hands of a few people who have absolutely no clue what's happening outside their computers.
Building a large data center near a town can strain the power grid, drain local water supplies, generate constant noise, release excess heat, harm the environment, disrupt traffic during construction, raise security concerns, and offer very little long-term benefit to the local community.
So, yeah, the solution is to cover the earth with data centers, right?
You could say that about building almost any infrastructure anywhere populated.
adamiscool8 commented on Incapacitating Google Tag Manager (2022) backlit.neocities.org/inc... · Posted by u/fsflover
I don't think this article makes a good case for why you should.
>The more of us who incapacitate Google's analytics products and their support mechanism, the better. Not just for the good of each individual person implementing the blocks - but in a wider sense, because if enough people block Google Analytics 4, it will go the same way as Universal Google Analytics. These products rely on gaining access to the majority of Web users. If too many people block them, they become useless and have to be withdrawn.
OK - but then also in the wider sense, if site owners can't easily assess the performance of their site relative to user behavior to make improvements, now the overall UX of the web declines. Should we go back to static pages and mining Urchin extracts, and guessing what people care about?
adamiscool8 commented on Show HN: Reverse Pac-Man reverse-pacman.staticrun.... · Posted by u/Eagle64
I like the concept but shouldn't the score be counting down? Or am I trying to shepherd Pac-Man into eating as many as possible to get a high score?
adamiscool8 commented on Recent AI model progress feels mostly like bullshit lesswrong.com/posts/4mvph... · Posted by u/paulpauper
My mom told me yesterday that Paul Newman had massive problems with alcohol. I was somewhat skeptical, so this morning I asked ChatGPT a very simple question:
"Is Paul Newman known for having had problems with alcohol?"
All of the models up to o3-mini-high told me he had no known problems. Here's o3-mini-high's response:
"Paul Newman is not widely known for having had problems with alcohol. While he portrayed characters who sometimes dealt with personal struggles on screen, his personal life and public image were more focused on his celebrated acting career, philanthropic work, and passion for auto racing rather than any issues with alcohol. There is no substantial or widely reported evidence in reputable biographies or interviews that indicates he struggled with alcohol abuse."
There is plenty of evidence online that he struggled a lot with alcohol, including testimony from his long-time wife Joanne Woodward.
I sent my mom the ChatGPT reply and in five minutes she found an authoritative source to back her argument [1].
I use ChatGPT for many tasks every day, but I couldn't fathom that it would get so wrong something so simple.
Lesson(s) learned... Including not doubting my mother's movie trivia knowledge.
[1] https://www.newyorker.com/magazine/2022/10/24/who-paul-newma...
I don't think this reflects a flaw in LLM's at all. It is true that Paul Newman is not "known for" having alcohol problems. Paul Newman is known for acting, and salad dressing. Paul Newman has been "known to" have had alcohol problems, which formed as a question correctly one-shots accurate results for me across a few common LLMs. Someone like Betty Ford could be "known for" having alcohol problems. Paul Newman's alcohol problems are relatively specialized knowledge.
Citation needed or this is just more vibe-xecutive decree.