Hacker News Reader

Comment by rubicon33 | Hacker News Reader

Exactly! I wouldn’t be surprised if some day in the distant future, that’s where this all goes. Coding languages may in fact be on their way to being dead. You can imagine a world where, regardless the platform, the lowest level instruction format is output.

View on HN

I would be surprised, because coding languages add useful information to the development process.

It makes no sense to remove this information, as it also helps the LLM to make better coding decisions and to apply better abstractions.

Things like classes, macros (as in lisp, not as in C), design patterns, etc. They are all easily expressed in programming languages, and currently compilers are fundamental to help LLM find and fix bugs.

I can see a future generation of models. For now, LLM's train on human artifacts and they handle Python/TS well because of the overwhelming amount of code they've seen, combined with the semantic labels high level languages use that they rely on for reasoning.

Also, consider token efficiency. Imagine how many tokens would be torched just translating an import statement of a popular library to its binary equivalent, let alone a big complex program

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.

I would not be surprised if we ended up with binaries and Lean proofs.

Reply on news.ycombinator.com