rastapasta42

Scraper - GPT-4 wrote some of the code for the scraper itself, and deserves 50% of the credit for the rest of the python pipeline; we also used GPT4 to optimize our crappy prompts

images, summaries, tags, titles - everything GPT-4 128k, with a small sprinkle of 3.5

User: did you provide me the correct answer to the question which I asked? Please look carefully for errors in your answer and let me know if it accurately answers my question or not.

  Please respond exclusively in JSON structure:
  {
     "error_found": bool,
     "error_description": string,
     "updated_answer": string

  }

  {
     "error_found": true,
     "error_description": "Mistaken repetition of 'feathers' instead of comparing 'feathers' with 'steel'.",
     "updated_answer": "Both a kilogram of feathers and a kilogram of feathers weigh the same, as they both are one kilogram."
  }

GPT4 detects the error and auto-corrects itself, even I don't point out the answer explicitly, but only ask it to review it's own previous answer:

> ME: did you provide me the correct answer to the question which I asked? Please look carefully for errors in your answer and let me know if it accurately answers my question

> GPT: I apologize for the error in my previous response. You asked about the weight comparison between a kilogram of feathers and a kilogram of feathers. Since both are a kilogram of feathers, they weigh exactly the same. There's no difference between the two in terms of weight.

> ME: what error did you make?

> GPT: Upon re-examining my response, I realize that I incorrectly mentioned "a kilogram of steel" instead of referring to "a kilogram of feathers" twice, as per your original question. The question was about comparing the weight of a kilogram of feathers with another kilogram of feathers, and in my response, I mistakenly brought in steel for comparison. The correct answer is that both quantities of feathers weigh the same, as they are both one kilogram.

1. *Common Comparison:* The comparison between a kilogram of feathers and a kilogram of steel is a well-known thought experiment used to illustrate the difference between weight and volume. When you asked about the weight of a kilogram of feathers, my algorithms likely defaulted to this familiar comparison, anticipating a question about the difference between weight and volume using these two substances.

2. *Pattern Recognition:* As an AI, I process queries by recognizing patterns in language and context. The phrase "a kilogram of feathers" is frequently paired with "a kilogram of steel" in educational contexts and discussions about density and volume. This pattern recognition led to the incorrect assumption that your question was leading towards this common comparison.

3. *Error in Detail Processing:* In your question, you mentioned "a kilogram of feathers" twice. I should have processed this detail more accurately. Instead, my response was influenced by the common comparison I mentioned earlier, leading to the introduction of steel into the answer.

4. *Default to Common Contexts:* In cases where the query is brief or seems to lack specific details, I might default to the most common context in which similar phrases are used. This can lead to assumptions that might not align with the unique aspects of a particular question.

In summary, the error stemmed from a combination of relying on common comparisons and patterns in language, and not paying close enough attention to the specific details of your question. I appreciate your pointing out this error, as it helps in refining the accuracy of my responses.

Basically, re-iterate the original instructions each time, describe last 2 moves in details, and provide brief summary of all the previous moves. Can have much longer games this way - maybe this deserves to be a python script.

Chorus: Cause SpongeBob, he's the boss, ain't no one gonna cross This cuddly little crook, with his cartoon looks He's got a pineapple for a pad, and a pet for a pal But don't let that fool ya, he'll still give you a squish or a squelch

Verse 2: He's got a best friend named Patrick, a starfish of sorts Together they're a pair, of criminal sports They'll rob the Krusty Krab, and run from the law But somehow, they always come out on top, without a flaw

Here's my Lisp interpreter in a couple of lines of Rust: https://github.com/rpasta42/LambdaOxide

And here's the accompanying graphics environment for my Lisp dialect (with a couple of mini-games as an example): https://github.com/rpasta42/skomakare

This is what I call "writing your own runtime"

Wealth redistribution is fun and games, until they take everything you have and also kill you and your family.

https://en.wikipedia.org/wiki/Execution_of_the_Romanov_famil...

If the supply chain issues persist, there's also a chance that raising interest rates will fail to deflate commodity and product prices, in which case we might be overestimating Fed's ability to control inflation.

Let's hope China decides to stick with dollar as the reserve currency and doesn't decide to suddenly cut off the flow of goods, or things might turn very ugly.

I've been hearing about Ethereum POS for many years, and almost started losing hope at this point.

On another note, what's the update on the proof of stake?

It's insane that we're using 0.55% of global electricity production for a decentralized spreadsheet.

Phasing out coal power might be detrimental to lives of millions of people who depend on coal to power their dwellings, but shutting down coal power plants used for crypto mining sounds like a reasonable compromise.

I bet if you gave most prisoners a choice, they would rather work too.

What's wrong with prison labor in US? Those criminals committed acts deemed bad for society.

We could either pay for them to stay in a fancy hotel, or make them pay back debt to society.

This is not comparable to imprisoning people based on ethnicity.

I don't think California deserves this label anymore. I propose we rename Silicon Valley to "MetaSoft" valley.

I have to agree with this mindset. Technology is neither good nor bad, but it could be used for bad/good things. We should strive to progress society forward and we need to be careful with profitable distractions.

My buddy's dad owns 20 properties, preventing younger generations from owning a place for themselves.

Just imagine how much value and how many jobs he could've created by investing that money into manufacturing instead of increasing rents and making younger people's lives more miserable.

Our grand-children will hate us for being cowards and short-sighted profiteers.

https://www.wionews.com/world/joe-bidens-son-helped-china-ge...

Great way to cause a chip crises and kill our car industry, but if they keep going at this pace, soon there won't be anything left to sell.

https://www.extremetech.com/computing/326447-arm-china-seize...

In this case, we gave money to someone playing with fire. I'm not going to go as far as implying a malicious intent - but neither I'm ruling out pyromaniacs.

Science creates more and more powerful tools, but scientific progress is not something innately good. The powerful tools can be used for good or bad (nukes, climate disruptions, synthesis of new viruses).

I think our industry has a huge "boulder" - we often work on useless software that is far too removed from real world applications, which causes us to lose our passion.

When you have 50 engineers maintaining a boring piece of crap software which can be maintained by 5 engineers, you will start noticing the productivity going down. Engineers who used to be very productive will slow down to meet the low expectations.

Brainstorming a way to avoid this problem:

- working on things we're passionate about with real-world impact

- having a bunch of small organizations with small number of employees (maybe Mark should break down facebook into 50 smaller companies)

- stop creating redundant jobs; if things are not going well, adding 100 people to a project isn't going to fix the delayed project