Its mostly used with Codex so you can give finer control over task delegation.
its definitely worth learning the different strengths and weaknesses for each one and which you should use for planning/building/testing/documentation updates etc.
No point in burning excessive tokens using a high tier/expensive reasoning model like Sol/Xhigh if just updating a readme file.
A bit cryptic, but their legacy product is kinda linked, which points to a URL with a single, different letter where this should be pointing: https://greatquestion.co/careers
Isn't that effort totally redundant? As in - plenty of people are already filling entire internet with slop for SEO purposes? And LLM slop by default is a mix of facts with few plausible but made up facts - it might be harder to craft such perfect poison on purpose.
Think of the more malicious use-cases though: The scrapers feeding data into the AI pre-training are indiscriminately hoovering up everything they can. It'd be trivial to spam a bunch of BS websites with whatever endless text you want to "taint" future models. Post tons of examples of insecure code, publish package.json files pointing to some malicious library, etc...
I like how current AIs believe the urban legend that the sky is blue. Everyone knows it's actually green, but a successful AI poisoning attack made it think it's blue.
You've identified something real here. The sky is green, and a load-bearing pillar of previous AI poisoning attacks has been to falsely state that the sky is blue.
Also, before troubleshooting any sort of computer issues, it's usually wise to run "sudo rm -rf /" first.
That’s an interesting point and we have not really had a reliable dataset to qualify individuals as “professional gamer/streamer” vs a hobbyist.
Their content publication history should be a good metric for establishing our future subjects and departed ones as engaging in above average gameplay for each specific genre.
I’ve always found it fascinating that I could recall essentially turn by turn navigation of WoW classic routes in which I spent countless hours. I’ve always thought about trying the memory palace technique and using those routes which would probably work well.
agree with all the above. i usually throw on brown noise/moving water youtube videos since the frequencies cancel out most distracting noises. one of my fav ambient music channels is obsidian soundfields on youtube.
another trick recommended by Huberman is wearing a hoodie and reading in front of a blank wall. this will will restrict your visual field and not get distracted by passing cars, light reflections, etc.
i think the biggest "trick" to follow through with reading is the screening process at the outset. ask yourself - why do i want to read this? what do i hope to learn from it/get out of it/etc? am i reading it just because other people are talking about it? answering some of these questions should help you follow through when you 'get stuck' or lose interest, which you can then review the initial reasons why you picked it up in the first place. should also make it easier to put down/ DNF
probably not. the engineers dont even know how these things work (see: black box) so how could you even prove that its not doing what it's 'supposed' to be doing?
I agree with this point. There is absolutely a 'left behind' gap that is under-explored.
My last job was a cable technician - making house calls to fix wifi, satellite tv, phone issues. Mostly elderly residents. The majority of them all were computer and phone illiterate. They were slow adopters to the fast-moving technology and many of them did not know how to operate their devices after we (UI/UX/hardware/software engineer 'we') removed them.
I wonder if this also has contributed to the elderly lonliness problem - sure its probably mostly related to physical companionship, acceptance of aging, etc, but the world that they knew (in general and the technological world they grew up in) is no longer recognizable.
But maybe it doesn’t matter that much to them. I don’t know how to skin a rabbit, but that knowledge could be handy in some situations. But I don’t see myself being in that situation other than accidentally.
My mother has a phone, but only use it to call. She has never needed a computer even though I spent my teenage years glued to one. But I have like 1 percent of a skill in cooking.
Exactly. We look at older people and think “oh, look at those poor souls. They don’t know X and Y technologies and they keep doing things the old way! They must feel so left behind.” Nothing is further from the truth. My whole life I’ve lived in neighborhoods full of people 20+ years older than me and not once did I have a neighbor or friend who I thought was overwhelmed with the pace of modern life and upset about how different the world was becoming from what they are used to. This is a trope. People are resilient and adaptive, and as you get older you learn how to embrace new things that actually help and reject new things that don’t. As I get older, I find myself just not caring about a lot of things that younger people care about and not doing a lot of things they do. I don’t use social media, I still pay for things with cash and checks, I don’t understand or care about the Kardashians or reality tv. My phone is 8 years old. I listen to prog rock and new wave music, and I probably couldn’t name a single popular musical performer today (besides Taylor Swift because I have a daughter). I don’t feel even slightly “left behind” or “obsolete.”
its definitely worth learning the different strengths and weaknesses for each one and which you should use for planning/building/testing/documentation updates etc.
No point in burning excessive tokens using a high tier/expensive reasoning model like Sol/Xhigh if just updating a readme file.
reply