Hacker News Reader

Comment by simonw | Hacker News Reader

I do this all the time. It's shocking how well it works. A year or two ago suggesting that someone use LLMs for fact checking would get you laughed out of a room, but today the good ones (Fable, GPT-5.6/6) with a search tool enabled are genuinely excellent at this.

They can even retrieve articles you link to and check that you aren't misrepresenting them.

View on HN

This is bad advice for anything serious that can be subtly wrong. I’ve had Fable being consequentially wrong about what a certain, rather small, code block does in our codebase. Not even on something very complex which wasted a lot of time and effort from the team until we checked the code ourselves. I think these tools are still useful and one should learn to use them but blind trust for anything of importance is misguided IMO.

To paraphrase, "if a junior programmer doesn't understand what your code does, it's bad". If Fable doesn't understand, well...

Did you just paraphrase yourself in quotation marks?

You don't blind trust them in the fact checking. You check what they point out.

Fact check the fact checker!

I use Fable to give me feedback on things I write. But I discard about 50%, because it often does not have the context and thus tends to favour hedging stuff. Also, it does not always vibe with my writing style.

But the 50% I do take into account, improves the text! And, like TFA, I never ask it for concrete text. It only helps me diagnose the issues, I prescribe the medicine!

I do something like this with code all the time, “is this idiomatic <foo>?”, I find it very helpful.

Reply on news.ycombinator.com