alt Hacker NewsModels are mediocre solo consumers: they skim, paraphrase and confidently miss the one subtle thing that actually matters. Humans are still better at deciding which three paragraphs in a 40‑page spec are load‑bearing. But as soon as you treat the model as a stochastic code monkey with a compiler, test suite, linter and some static tooling strapped to its back, it suddenly looks a lot more like “creation with a very fast feedback loop” than “consumption at scale”.
The interesting leverage isn’t that AI can read more stuff than you; it’s that you can cheaply instrument your system (tests, properties, contracts, little spec fragments) and then let the model grind through iterations until something passes all of that. That just shifts the hard work back where it’s always been: choosing what to assert about the world. The tokens and the code are the easy part now.
This might make it into this week's https://hackernewsai.com/ newsletter.
Replies
.. except you are completely wrong in a certain way.. AFAIK Google has been reading and indexing patent applications and maybe SEC filings since before word2vec. Certain niches absolutely are reading documents faster than your attorneys can...
Don't forget guardrails and other tweaks you don't know are being applied. I was exploring energy usage and when I reached solar energy somehow the AI decided it was political and switched to useless mode until I explicitly told it to look back at the conversation and it's context and that I wasn't trying to get it to say solar was good and it was OK if numbers made solar look good. I was really weird.