This is a tool whose previous maintainers have apparently stopped working on it, not something that Linus was still involved in maintaining. This isn’t so much him wanting to step down, as him not wanting to step up if someone else with an interest in it might be willing to do so.
I was really lucky to get mine in the early crowd funding phase - it was something like a quarter the current retail price. And my preferred green beans (when bought by the sackload, delivered) are about 60% the price of roasted beans at a local roastery. The value worked out well for me where I am, but I can certainly understand that your local prices will differ, and with the current price of the unit it’s a lot more of a painful initial outlay. Still pretty cool for anyone who likes to tinker with their roast profile, of course.
I don’t think that’s true in the way you appear to mean (sorry if I misunderstood). People who are already experts on the subject matter might be able to use better keywords and discard hallucinatory material quicker, but I don’t believe that you can generically “be good at prompting” outside of an area where you have substantial domain knowledge.
There are ways of phrasing LLM requests that can actively induce them to give you made-up bullshit that confirms your pre-existing assumptions. Which is fine if that’s what you want it to produce, but often not what people actually want. For (possibly poor, given I don’t actually use LLMs) example “give me the transcripts for five court cases for assault with a deadly fish” would likely result in five-ish almost-certainly made-up court transcripts. Someone who knows what they’re doing could phrase the prompt to be more likely to say that no such cases exist (assuming no such cases actually exist) instead of just hallucinating them as per the request.
And you might be right about domain knowledge being required for good prompting. But it’s possible to have domain knowledge and still be terrible at asking for what you actually want it to produce.
not to mention that they’re an “intern” who actually costs the same in computing power as two senior engineers’ salary.
Don’t expect me to defend the moronic economic decisions of companies that have jumped on this stupid band-wagon without regard for the actual value (or lack thereof) to their business.
Roasting your own coffee is trivially easy if you have the right tools. I bought an air roaster in a crowd funding campaign a few years back and it’s just incredibly more convenient, cheaper, and at least as good as buying from a roastery.
Of course, most people aren’t going to want to spend a grand on something to save a few dollars a week, or to tweak a roast to fit their palate slightly better. I know I wouldn’t have.
I especially like his most recent use of LLMs.
Specifically as a threat to induce someone else to step up as a maintainer of the debug tool sparse.
Good point. I probably should have stated “using LLMs for technical tasks that anyone cares about the results of”.
I’m not going to claim LLMs are trustworthy, but I am saying that there are ways to ask things that either reduce the odds of it giving you false things or actively cause it to provide wrong answers with misstated or hallucinated context. People who know what they’re doing can get better results out of them. This doesn’t stop them from being the equivalent of a nepo-hire intern, but it could be said to change whether they’re a malicious, apathetic, or semi-eager nepo-hire intern.
And one of the big risks with LLMs is staff who can recognise bullshit or questionable results being replaced with staff who unquestioningly accept whatever results they get. And people reading an “AI summary” of something and assuming it’s actually accurate.
Writing an appropriate prompt is a skill. Many (most?) people using LLMs aren’t using prompts that give them what they actually want, in many cases because they don’t understand the thing they’re trying to ask for, but also in many cases because they don’t know how to ask for it while avoiding the many possible pitfalls that come with uncareful prompts (including, but not limited to, hallucination and bias).
Personally I haven’t bothered learning that skill yet, largely because I don’t want that crap shoved in my face all the damned time, and have little use for it anyway. But it’s still a skill.
Huh. And hereabouts I can generally get a good 250g block of chocolate for the equivalent before tax of US$3.40.
I propose they compromise by going out of business after deleting all data and removing their cameras from everywhere.
As did the person you replied to.
Might want to save most of it for your next memory upgrade too.
I played it in one of their free play weekends, and it had so many glitches. I spent an afternoon and evening trying to play it and have never bothered with it again.
Calories per serving size is even more misleading here than calories per 100g, given that they’ve chosen their “serving size” by what numbers it lets them put on the packaging instead of by what someone would actually use.
Quarter of a second of spray is vastly less reasonable as a serving size, no matter how unreasonable you consider stopping at a single tictac.
And the rest of us can anticipate the “but still tried” part.