Remote work accomplishes all that as Covid days proved.

This is never going to happen. Is something can be done, it will be done.

>If something can be done, it will be done.

What does this mean? It's obviously false on its face.

There were historical worries about whether a ban would be feasible, but frontier AI research as we understand it today requires large amounts of specialized compute. Even if we couldn't or wouldn't destroy the chips, we could imprison anyone who tries to start a large training run, the same way we imprison anyone who tries to buy enriched uranium.

I think people really confuse their imagination and expectations with reality. There's so much talk about AGI and mass layoffs. Then there is my experience.

I was talking to Claude and ChatGPT, trying to fix an issue with a simple function in Rust, which is returning a boolean depending on day of week and time of day. The logic looked ok to me, but tests were failing. Notably, my real world data derived tests were succeeding, while brute-force/comprehensive tests written by Claude were failing. I wanted those "just to be sure". Both Claude and ChatGPT were spinning their wheels, introducing fixes, then undoing prior fixes, so on and so forth. They also updated tests. We were going from one failure to another, while they confidently reassured me that "this is the fix", they found the "crucial bug" etc. etc.

Turned out my logic was correct from the beginning. My tests were correct. Claude's tests were broken. I realized this by writing my own brute force test. Just a simple loop with asserts and printlns to see what is failing. I did what the machine was supposed to do for me. In less than 5 minutes I fine tuned the test to actually check what it was supposed to be checking and voila. The "fast" thinking machine episode took me 2 hours and only produced frustration. Sorry I should learn to speak the language - AI reduced my development velocity :)

The only poverty I see coming is from collapse of quality after these dumb machines are used to replace people, who actually know what they are doing.

And if the current models really are so great, why do we need to have a massive hype-train for each time the number goes up 0.1?

How are the "ulterior motives" of Chinese companies any worse than "ulterior motives" of US companies or European ones?

Why are you arguing when the internet expert already stated that is impossible.

My issue with borrowing books was the logistics of it. Showing up, borrowing, returning on time, remembering to return. I'd rather own. Plus, I really like Kindle. It eliminates the largest annoyance I had with books - keeping them open while reading. It introduced an annoyance of its own though; it has to be charged. Once a week or two. So not that bad.

I'm worried it will set the tone against all markets and trading, which would be very regrettable.

I just ran Unsloth's Q4_K_M quant on Macbook Pro M1 Max (2021), 32 GB RAM. Getting about 9 tok/s. Reported RAM usage 15.9 GB. It's okay, but a bit slow for my taste.

An example of a query and a response is below. It was done with 9.09 tok/s, 893 tokens, 7.56 seconds to first token, thought for 1 minute and 9 seconds.

Question: I gave the model this truth table and asked to tell me what boolean function would produce the output given A, B as inputs.

  | A | B | Output |
  | :--- | --- | ---: |
  | (T) | (F)  | (T) |
  | (T) | (T) | (F) |
  | (F) | (F) | (F) |
  | (F) | (T) | (F) |

Answer: (note this is part of a larger conversation, where I was getting it to help me with some boolean logic):

  The boolean condition for your table is simply:

  ```rust
  A && !B
  ```

  ### Why?
  Your table shows the output is `true` **only** when `A` is true and `B` is  false. That's exactly what `A && !B` expresses.

  | A | B | `A && !B` | Output |
  |---|---|-----------|--------|
  |  (T) |  (F) | `T && T = T` |   |
  |  (T) |  (T) | `T && F = F` |   |
  |  (F) |  (F) | `F && T = F` |   |
  |  (F) |  (T) | `F && F = F` |   |

  ### In Rust:
  ```rust
  if A && !B {
      // output is true
  } else {
      // output is false
  }
  ```

  This is the most direct and idiomatic way to express that logic. Let me know if you need it adapted back to your `live_ticks` / `on_disconnect` context!

I'm really struggling with terrible bloating today, but I deemed it too dangerous to release.

Thank you for your sacrifice. Could you speak to my dog please? You may wish to yell from a distance, actually.

Question for Musk hating people - I understand why you hate Musk, but why is doing business with Altman or Microslop any better?

Not much better but at least they're not speaking at far right rallys and lending support to fascist parties across Europe.

What really puzzles me is how years of woke insanity are forgotten / forgiven, but a nazi salute is not. Remember how Microslop employees used to start their presentations with a list of Native American tribes who owned the land their office was at? Maybe people don't read Orwell anymore... that stuff was straight out of 1984.

I see being downvoted on my question already - can people who hate Musk not see the difference between asking and supporting?

https://youtu.be/PraEcNDGSqY?t=310 privacy of their own meeting rooms? Let's not forget about her stating for the audience her race, sex, and skin color. Those are very important things in the context of a programming conference :) There is no baked in reverse racism here at all. Only those awful right wingers do racism.