Comment by stvltvs
4 hours ago
How would we train those LLMs? Feed them binary executables along with their business requirement docs? Is the corpus of training data large enough to be effective? What happens when a new CPU architecture is developed? Where would the training data come from for the new machine code?
Exactly! That's why the "pelican riding a bicycle SVG" test is unfair. It's a token predictor, not an intelligence. What corpus of SVG data has the LLM been trained on? Only in the last 10 years has "drawing using data" been in existence. Midjourney can generate you a pelican riding a bicycle artwork easily. But instead, if the test is intentionally based on a task with no corpus, then you get garbage.