Preferences

andromaton
Joined 750 karma
At the beginning there was Z80 machine code, Z80 assembly, Basic, Forth and Logo implemented, Logo taught, Turbo Pascal, Apple Pascal, 68K, 80386, and C.

Then there was c#, js, Python and PLCs.

Industrial control/hindering the baddies/too much more.

meet.hn/city/us-Chicago

Emails welcome to andromatonhn @ gmail


  1. Coined by Andrej Karpathy
  2. Almost none of the domain knowledge came from Claude. This is something I did by hand 40+ years ago (an assembler and a disassemble/debugger, which is in parts similar to the emulator)

    This time it was almost as fun : 1/8 of the mental effort per line, x 8 the speed.

  3. true - it's an homage to the zx81, ts1000, spectrum and ts2068
  4. 95% of it. It's a power tool.
  5. rule #1 of ai programming: read and approve everything before accept. rule #2 do not let it write commit messages - i did not know notice that until many commits later. they are horrible. change 10 things - writes about the last one, too peppy too.
  6. if by break you mean you can't see the action, that's by design :) otherwise, pls let me know.
  7. thank you. will or have fixed :)
  8. This is the same company behind Anthropic's Titanium cube vending fridge, recently on the front page. As of now, the leaderboard is #1 Claude 4 Opus #2 (distracted?) Human
  9. This used to cause malicious sites to reboot home internet routers around 2013.
  10. Any similarity in appearance between Steve Carell's VC character and real life is coincidental /s
  11. Lengthy and somewhat low in density. Favorite quotes:

    Plenty of that knowledge is, though, quite siloed in different areas. But sometimes there are “grand analogies” to make—say pulling an idea from relativity theory and applying it to biological evolution. In a sense such analogies reveal new abstractions—but to make them requires knowledge that spans many different areas. And that’s a place where bigger brains—or AIs—can potentially do something that’s in a fundamental way “beyond us”.

    But, OK, will it always take an “expanding brain” to keep up with the “expanding knowledge” we have? Computational irreducibility guarantees that there’ll always in principle be “new knowledge” to be had—separated from what’s come before by irreducible amounts of computation.

  12. Lets take Mensa iq tests with a few grains of salt.

    O3 public Norway Mensa iq test 136. Private test 116. Significant increase over 11 months.

This user hasn’t submitted anything.

Keyboard Shortcuts

Story Lists

j
Next story
k
Previous story
Shift+j
Last story
Shift+k
First story
o Enter
Go to story URL
c
Go to comments
u
Go to author

Navigation

Shift+t
Go to top stories
Shift+n
Go to new stories
Shift+b
Go to best stories
Shift+a
Go to Ask HN
Shift+s
Go to Show HN

Miscellaneous

?
Show this modal