trust me it's paradise this is where the hungry comes to feed for mine is a generation that circles the globe in search of something we haven't tried before so never refuse an invitation never resist the unfamiliar never fail to be polite and never outstay your welcome just keep your mind open and suck in the experience and if it hurts you know what... it's probably worth it you hope, and you dream but you never believe that something is going happen to you not like it does in the movies and when it actually does you expect it to feel different more visceral more real [...] I still believe in paradise but now at least i know it's not some place you can look for because it's not where you go it's how you feel for a moment in your life and if you find that moment it will last forever [orbital : beached]

#postsToLinkedin ai productivity ai isn't magic, and there's many ways for it to be wrong. it might not have understood the question, might have not had appropriate context, might not have the necessary capabilities, or could have flat out lied / hallucinated. which is no different from people. and when you have people help you accomplish something, your job hasn't gone away: you've become a manager how you structure this trade is the best predictor of your opinion on ai. modeled as a simple cost-benefit ratio, you benefit from the work being done and it cost you the work to verify it. you want to have the ai do more work at a time, and you want it to be easier to verify. if you think about it, this is why everyone hated copilot years ago – it wasn't capable of doing very much, and you spent way too much time debugging the results. this hasn't gone away. many open source projects have changed their contribution policies to forbid anything that even smells like ai, because their established process for accepting changes has become overwhelmed my advice is to tame the "problem of ai" by using "even more ai". this sounds nonsensical, or at least hopelessly naive. as someone who has long railed against complexity, i fully agree. but from a certain angle, the definition of intelligence is the ability to simplify something. which implies that ai is software that is at least somewhat capable of simplifying things. so you should ask it to review its own work before you do. you can also have a new context review it without knowing anything about how the work was done. looking at something with fresh eyes is a classic way to find problems, and it's never been easier than it is today you can also have ai prove its own work. that can be arguing against it, having it write test suites, having it predict behavior in unlikely scenarios, even having it brainstorm what those unlikely scenarios might be. running that backwards, for important things it's good to ask the ai where mistakes might be made in this type of work, to predict how its solution would behave in them, and to write tests around those. maybe even write exhaustive tests, because why not? it's cheap, and even if it doesn't find everything, anything it does find reduces your work later so far everything has been about reducing the cost of using ai. but this is a long post for LinkedIn. i'll leave increasing the value for next time. but here's a teaser: it doesn't involve cursor

the highest leverage a maker can have is to properly define success and gtfo. claude's got you

#postsToLinkedin the biggest mistake when using ai is not providing context. if you called up John Carmack and asked him why your code was broken, could he fix it? of course not. it doesn't matter how capable someone is when they don't have enough information the same is true for almost everything. you should talk to the ai like a person, not because it is a person, but to shape the system's expectation of what you want from it. conversation is the user interface of artificial intelligence, and it's a powerful one

#postsToLinkedin stay buoyant 🌊 it sounds like a low bar, but today it's higher than anyone realizes. in competitive spaces we aim for optimization: a little less latency, a little more correct, one more feature – just a little better than the competition. it's hard but predictable, and there's comfort in predictability. we invest in education, understanding, execution, in the hope of finding a place at the front of the pack scooping up more rewards than the next guy last year the movie "F1" had an underdog achieving an inch of success, not by being faster, but by causing chaos and leveraging edge cases effectively. many might see this as underhanded and not sportsmanlike. it's certainly painful to watch if you're not the main character – constant interruptions and technicalities break pacing and flow, ruining overall emotional investment in the sport. the answer seems to be to remove the fly from the ointment. but this assumes that the fly is a mistake most racing, and incrementalism at large, presume that the world doesn't change – that we can go around the same track twice. even rally racing at least has a map and a somewhat controlled environment. there are always rules, and we don't expect those rules to change mid-race. there is continuity. there *must be* continuity which begs the question: what happens when there isn't. when the rules change because no one can stop them from changing. suddenly, "survive" isn't the low bar it used to be. observation and exploration trump education and expectation. how well you played the game could be largely irrelevant if you can't navigate the turn which is how i became obsessed with buoyancy. with trying to find a way to float on the wave rather than fight it. because if no one can control it, no one can stop it, the only way we can navigate it is by not drowning are we swimming then? that's exhausting are we surfing it? do we even know how? let's just float for a bit. at least then we'll have some time to understand it better

not even there and i need a "nakamoto stage" chaser

"last year i stood on this stage and promised you we'd get square bitcoin payments live by the end of the year, and to be honest we hadn't even started building it yet" that one hurt a little

haven't posted much status on claude reverse engineering this old mac game because this kind of work doesn't make for exciting demos until you're well into it

a million tokens to fix the line of code 99 million to find out which line to fix

we are all lee sedol

you don’t get soveng by calling someone’s api

claude's got shade for the code its decompiling: "NewObjectByName dispatch is hilariously loose"