In theory the /stats command tells you how many tokens you've used, which you could use to compute how much you are getting for your subscription, but in practice it doesn't contain any useful info, it may be counting what is printed to the terminal or something - my stats suggest my claude code usage is a tiny amount of tokens, but they must be an extremely underestimated token count, or they are charging much more for the subscription than the API per token (which is not supposed to be the case).

Last week's free extra usage quota shed some light on this. It seems like the reported tokens are probably are between 1/30th to 1/100th of the actual tokens billed, from looking at how they billed (/stats went up 10k tokens and I was billed $7.10). With the API it should be $25 for a million tokens.

It is clearly getting better globally, so I expect in 3 years or so things will be ready for me to try again.

I enjoyed the human->depth vs AI->breadth discussion and the waterline rising slowly to fill the 50 lowest hanging Erdos problems but struggling on the next few.

How amazing and ironic or a reminder it is that the comments below that seem the most reasonable and avoid generalizing an entire group of people or way of life are the ones that are the least likely to drive more comments because they are perfectly reasonable.

Comments URL: https://news.ycombinator.com/item?id=47178618

Points: 1

# Comments: 0

One thing I liked about HACF is despite using a decent amount of technobable, it plausibly captures the approach and spirit of hacking and coding, like reverse engineering a memoryless chip by rigging up a hex LED system to read out the values for each of the 65536 inputs to a ROM.

The expertise of the coders are demonstrated mainly by others admiring the structural complexity of their code as objects of beauty. This is something that feels extra nostalgic now.

https://michaelchinen.com/2023/12/31/halt-and-catch-fire-pos...

Comments URL: https://news.ycombinator.com/item?id=46936160

Points: 1

# Comments: 1

edit: It now says "Cloudflare Global Network experiencing issues" but it took a while.

Comments URL: https://news.ycombinator.com/item?id=45952568

Points: 2

# Comments: 0

I'm not even a youtuber and make these to keep myself accountable, so it's not that fun to watch, but it might be in the direction of your query:

https://www.youtube.com/watch?v=d9YCkWjD7WQ&list=PLEWSTtjNAw...

Anyway the experiments in Shannon's paper sound similar to what you describe but with less data and distance, so it should give some idea of how it would look: From the text:

* 5. First-order word approximation. Rather than continue with tetragram, : : : , n-gram structure it is easier and better to jump at this point to word units. Here words are chosen independently but with their appropriate frequencies.

REPRESENTING AND SPEEDILY IS AN GOOD APT OR COME CAN DIFFERENT NAT- URAL HERE HE THE A IN CAME THE TO OF TO EXPERT GRAY COME TO FURNISHES THE LINE MESSAGE HAD BE THESE.

6. Second-order word approximation. The word transition probabilities are correct but no further structure is included.

THE HEAD AND IN FRONTAL ATTACK ON AN ENGLISH WRITER THAT THE CHAR- ACTER OF THIS POINT IS THEREFORE ANOTHER METHOD FOR THE LETTERS THAT THE TIME OF WHO EVER TOLD THE PROBLEM FOR AN UNEXPECTED *

The mixed presentation of plug and play components interspersed with EE problems and solution really helped make it more accessible. It also got me excited about the possibilities and made me realize that we we might already approaching another open architecture DIY boom.

I got the sense that this is a side project, but I'm sure many have noticed that it could be a legit framework-level company. Someone already mentioned the recruiters, but also you're sure to have investors knocking. Whatever you do, please keep having fun and sharing it.

  >>> Give me 5 odd numbers that don't have the letter 'e' in them.

  
  Okay, so I need to come up with five odd numbers that don't have the letter 'e' in their name. Hmm, let's break this down step by step. First, what exactly is being asked here? The user wants numbers, specifically odd ones, and they can't contain the letter 'e'. So 
  I guess it's about the written form of the numbers, not their mathematical properties. For example, 13 is an odd number, and when you write it out, it's "thirteen," which does have an 'e' in it. So that wouldn't work.

  Alright, so I need to think of numbers where their names don't include 'e'. Let me start by listing some odd numbers and then check if each has an 'e' in their name. The first few odd numbers are 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, etc.

  Let's go one by one:

  1. "One": No 'e' here. So 1 is a candidate.
  2. "Three": Yes, that has an 'e'.
  3. "Five": Again, no 'e'. So 5 works.
  4. "Seven": Has an 'e' as well.
  5. "Nine": No 'e' in "nine". Good to go.

  Wait, so far I have 1, 5, and 9 as possible numbers. Let me keep going.
  
  Wait, let me make sure. The word "forty" is F-O-R-T-Y, no 'e', so adding "-one" which doesn't add an 'e' either. So yes, "forty-one" has no 'e's. So that's another number: 41.

  So now I have five numbers: 1, 5, 9, 19, and 41.

  Let me double-check each to ensure they don't contain the letter 'e':

  - One: No 'e'.
  - Five: No 'e'.
  - Nine: No 'e'.
  - Nineteen: No 'e'.
  - Forty-one: No 'e'.

  Yes, all of these are odd numbers and their names do not include the letter 'e'. I think that's a solid list.
  

  Here is a list of five odd numbers whose names do not contain the letter 'e':

  1. **One**  
  2. **Five**  
  3. **Nine**  
  4. **Nineteen**  
  5. **Forty-one**

  These numbers are all odd, and their written forms do not include the letter 'e'.

I haven't tried it but you may want to look into PAM, which is relatively new and doesn't require a reference (you don't need the original uncompressed audio), and is open source.

However, all approaches are quite far from perfect. Human evaluation is still the gold standard.