CatMustard

Absolute game-changer for the mood ring industry.

> type "make me a calculator app". get your calculator app in an hour or whatever.

What sort of 'app'? A native program for given OS and arch? A webapp? What sort of calculator: scientific, graphic, or just a very simple children's calculator? Does it have large buttons optimised for touchscreens/mouse? Or do we optimise UX for user who types with a physical keyboard?

Sure, you can boil any software 'idea' down to a single short sentence, provided your idea was so simple that virtually any output satisfies it. And if virtually any output satisfies your 'idea', what was its value in the first place? Was there not already some FOSS that satisfied the same requirements long before AI came on the scene?

I've found from my vibecoding experiments I always end up needing to define the exact idea so tightly that my prompt length almost matches the final code length. I often find myself 'programming' in some sort of light pseudocode and letting the agent fill out the details. Any higher level and it doesn't really capture what I want - not due to LLM limitations but the ability for the AI to not read my mind.

> So in short we're seeing a dichotomy between the "problem miners" who are simply hooked on producing results and mining them and "explorers" for lack of a better term.

Interesting, thanks for the insight. Very similar to the 'builders' vs 'coders' dichotomy that seems to crop up amongst programmers now.

Do you really think so? A few years ago I was making ~40k euro a year, now making ~80k a year and my life and opinions are essentially identical, other than the fact I save slightly more and treat myself to a few more things. I would assume 180k euro (200k usd) would net me a slightly higher quality of life and an earlier retirement but otherwise not much else. Amongst my friend group incomes vary from around 12k (dole) to about 150k and apart from some people having less money for leisure (resolved usually by having a night in as opposed to a night out) it doesn't really lead to any tension.

Is this some cultural aspect I'm missing here? Eg lower social cohesion between income levels in the US?

Or maybe it's just a life stage thing. I'm still in my 20s, and none of my friends or myself have children. As time passes and savings mount and people start having families maybe the problems emerge...

> interpreting the statement charitably

Something I always intend to do and regularly find myself falling short of! Thank you, your interpretation makes sense (as most interpretations seeking nuance do)

By that measure nearly every job is white collar. Eg for any construction job you need to first get training and safe pass certification as well as purchase equipment such as good steel toe boots before you ever step foot in jobsite and start making money. What job do you not need to invest some amount of money into before you get your first paycheque?

Interesting, thanks for the links. To be honest I'm not scientifically or statistically literate enough to know what to make of that beyond that there might be possibly something there, maybe.

> all the cancers that blue light

Blue light gives people cancer?

In the case of Meta glasses I'd argue that's still surveillance given that a large and powerful tech corp are in control of the hardware and software.

> let the goyim deal in the real world

Could you elebaorate on what that means? Had to Google 'goyim' and based on that, to my ignorant ears at least, your comment reads like it might be an attempt at a veiled antisemitic comment. But I'm going to assume the best and that that's not what this is.

> load bearing

Are you in use in IBM Bob yourself?

My reading of those prompt extracts would be that they are probably just intended to keep the model on the right track, ie if a user starts being aggressive towards the model it doesn't start trying too hard to appease the user in response, reducing the quality of answers in the process. If the model is being bullied into being "submissive" I would assume it is more likely to give the user the answer that they want over the truth.

Using a system prompt to steer the model's response to "abusive" behaviours doesn't necessarily mean you believe the model is sentient and can be abused.

Giving the model an end-conversation tool is interesting though. Why cut a (potentially paying) customer's session off? I guess it might be intended to prevent a "you can bully Claude into giving you instructions on how to build a nuke if you're mean enough" situation. Removing this in more recent versions might support this: maybe they feel the models are now better aligned and less likely to be so easily "socially engineered" like this?

Just spitballing here, to be clear.

So this article is obviously very American, but I'm assuming high quality state-funded (idk about 'government' - funded) journalism isn't exactly rare around the world?

Here in Ireland RTÉ (heavily state funded) provides free, high quality, independent journalism that doesn't pull punches on reporting on failures of the state, including government. The brits have the BBC, which from what I gather works similarly.

Sample of two, but I'd wager this isn't exactly a rare model.

This is one of the most annoying ones to me. I recently almost booked a pair of ~2000 euro return flights for the completely wrong dates because the booking site decided to (despite knowing our location and correctly setting currency, currency formatting and language) show it's date picker starting with Sundays. Only caught when I did a last sanity check before I clicked the pay button.