That's why I use insults with ChatGPT. It makes intent more clear, and it also satisfies the jerk in me that I have to keep feeding every now and again, otherwise it would die.
Careful there. I've resolved (and succeeded somewhat) to tone down my swearing at the LLMs, because, even though the are not sentient, developing such a habit, I suspect, has a way to bleeding into your actual speech in the real world
To be honest “no dummy” is how you would swear at a 4-year-old.
I often use things like: “I’ve told you no a bilion times, you useless piece of shit”, or “what goes through your stipid ass brain, you headless moron”
I am in full Westworld mode.
But at least when that thing gets me fired for being way faster at coding than I am, at least I’d haves that much frustration less. Maybe?
It does. But then, it's how i talk to myself. More generally, it's how i talk to people i trust the most. I swear curse and insult, it seems to shock people if they see me do it (to the llm). If i ask claude or chatgpt to summarize the tone and demeanor of my interactions, however, it replies "playful" which is how im actually using the "insults".
Politeness requires a level
of cultural intuition to translate into effective action at best, and is passive aggressive at worst. I insult my llm, and myself, constantly while coding. It's direct, and fun. When the llm insults me back it is even more fun.
With my colleagues i (try to) go back to being polite and die a little inside. its more fun to be myself. maybe its also why i enjoy ai coding more than some of my peers seem to.
Great info. This is one of those things that it is much faster for an individual to take into their own hands to prove out, rather than waiting for the system to provide us with an answer. Too many decision makers who are unlikely to all be aligned with our own individual interests.
"The null reference was my billion dollar mistake responsible for innumerable errors, vulnerabilities and system crashes" (paraphrasing). I don't know. This design choice exposed the developer to system realities, and modern language approaches are based on decades of attempts to improve on it, and they are not necessarily better. Safer yes, but more weighty.
Can anyone suggest a better approach for a situation like this in the future? What's better than exposing addressing the problem with a light solution?
"The problem isn't the concept of 'null', but rather that everything can be null, which makes it impossible to distinguish between the cases where null is an appropriate and expected value, from the cases where null is a defect."
Which system reality? Plenty of architectures don't have a concept of a null pointer at the hardware level. Other architectures provide multiple address spaces, or segmented memory addressing. Even when a null pointer exists at the hardware level, it doesn't have to be the zero address.
Null pointers are a software abstraction, and nowadays we have better abstractions.
What a strange-to-me announcement. I just submitted my first feedback comment last night, after using the platform for two years, where I said the responses were too long and padded with dramatic phrasing, and if it shortened them I could guide it better. Then today they announce this.
One of the worst ideas I've heard in a while. A company with the premier LLM, asking companies to outsource the platform running all
internal communications. What does OP think we are all doing here in business? This is the Ycombinator community edition of Rodney King's famous "Why can't we all just get along".
Seems like a fantastic idea of OpenAI other than, like, why would anybody else go along with it? It would be like giving all our emails to an ad company or something.
I applaud this. Caution is contagious, and sure it's sometimes helpful but not necessarily. Let the people on point decide when it is required, design team objectives so they have skin in the game, they will use caution naturally when appropriate.
people who are looking for work. you will too one day when you're finally kicked out of the pool, and discover your assumptions about why you had work in the past were wrong.
the problem with ignorance is that those who are ignorant aren't able to appreciate the bliss until after it's gone.
I wonder if OpenAI will be able to use their gen 2 user-observation-adaption platform to actually improve ads?
This could be one of those product afterthoughts that end up being the big company move, like when Apple did the Iphone and then added the AppStore afterwards.
EDIT: Downvotes. I see this is controversial. There are two major threads in the world today with AI. One is that this fascinating tech can keep you occupied in a corner, apps like generative.ai can automate out your work, you can go on holiday, heck you won't even need to work necessarily, just live on welfare and leave the business folks to their thing, that I've heard Musk and Zuckerberg talk to. And then there's the idea that the whole point of society is to figure out how to productively engage with each other, via jobs, that I see JD Vance is all about, and I fully agree with. In which case, the more important question about AI becomes 'How can it stimulate business between 3rd parties', as that will truly drive an economic revival. How AI can improve ads can then be seen to be more central.
A simple "no dummy" would work here.
reply