Re:Show HN: My Bytecode Optimizer Beats Copilot by 2X
by lawlessone on Sunday August 03, 2025 @03:35PM
(#44779067)
hopefully i am not sounding too pedantic in mentioning this. But LLMS are still deterministic if you're using the same prompt and seed , temp , (sometimes requires the same hardware even) etc.
[ Parent
| on HN ]
Re:Show HN: My Bytecode Optimizer Beats Copilot by 2X
by top256 on Sunday August 03, 2025 @06:03PM
(#44780226)
Yes but the analysis it's going to run is probabilist vs the one I'm running is closer to smt
Re:Show HN: My Bytecode Optimizer Beats Copilot by 2X
by Someone on Monday August 04, 2025 @04:03AM
(#44783153)
Are they? AFAIK, the “etc” includes using hardware that produces the same results for a given input every time. Once you start to multi-thread/multi-process in combination with floating point math, that can be hard to accomplish.
For example, the result of summing a stream of floats depends on the order the floats arrive in, and that order can change depending on what’s in your CPU cache when you start a computation, on whether something else running on your system such as a timer interrupt evicts something from cache during a computation, etc.
If you’re running on your GPU, even if the behavior of your GPU is 100% predictable (I wouldn’t know of that’s true on modern hardware, but my guess is it isn’t) anything that also uses the GPU can change things.