I let Claude Code write an entire book
github.com
I let Claude Code write an entire book
1–10 of 84 posts
Re: I let Claude Code write an entire book
#2Did you read it tho? We might be approaching a time when saying an author has written more books than they've read might turn from a joke to a fact.
Re: I let Claude Code write an entire book
#3> The second insight is that human hallucinations are fundamentally social. Unlike AI, which hallucinates in isolation, humans hallucinate collaboratively. At the dinner party, each false fact was immediately reinforced by social validation. The nods, the interested expressions, the follow-up comments - all of these served to solidify the hallucination into shared "knowledge."
Oh boy, that burns - the Futuristic AI dystopia won't be robots killing humans, but robots embarrassing us to death by revealing our ignorance.
Re: I let Claude Code write an entire book
#4Is it any good? Perhaps we can ask Opus to review it to find out.
Re: I let Claude Code write an entire book
#5Did you read it tho? We might be approaching a time when saying an author has written more books than they've read might turn from a joke to a fact.
The actual author is Claude, and Claude has read a lot of books.
Re: I let Claude Code write an entire book
#6Did you read it tho? We might be approaching a time when saying an author has written more books than they've read might turn from a joke to a fact.
> First Revision - Completed with minimal human contribution (auto-accept mode)
>
> Second Revision - Planned with increased human-in-the-loop involvement
At least 'minimal human contribution' in the first revision. So scan read it as it revised the book.
I do find it amusing to think that people might just ask an AI to summarize the book instead of actually reading it. Maybe even 'review' it as well.
The future will have authenticity in short supply
Re: I let Claude Code write an entire book
#7> The second insight is that human hallucinations are fundamentally social. Unlike AI, which hallucinates in isolation, humans hallucinate collaboratively. At the dinner party, each false fact was immediately reinforced by social validation. The nods, the interested expressions, the follow-up comments - all of these served to solidify the hallucination into shared "knowledge." Oh boy, that burns - the Futuristic AI d…
I feel like we do a great job of that already and the internet is full of people pointing it out from others.
Re: I let Claude Code write an entire book
#8Is it any good? Perhaps we can ask Opus to review it to find out.
It's full of made up scenarios and anecdotes. Make it a little bit worse and it'll reach Malcolm Gladwell level.
Re: I let Claude Code write an entire book
#9There have been good discussions recently about preventing AIs from being too sycophantic. There have been some dangerous moments where LLMs would praise every idea the user has as genius, ground-breaking, and a brilliant observation.
Some academics have reported a noticeable increase in the volume of crackpot emails they get daily. They're full of LLM-generated nonsense, where the AI goes along with the nonsensical ramblings, always telling the person they've found some critical insight.
While this feels good, it can end up reinforcing dangerous nonsense. This encourages some people to dig further and further into what the LLM is constantly telling them is a brilliant idea.
Most of the time it's pretty harmless, but when it veers into "revealing hidden patterns" and "illuminating human cognition", you start to worry about a disconnect with consensus reality.
Re: I let Claude Code write an entire book
#10There have been good discussions recently about preventing AIs from being too sycophantic. There have been some dangerous moments where LLMs would praise every idea the user has as genius, ground-breaking, and a brilliant observation. Some academics have reported a noticeable increase in the volume of crackpot emails they get daily. They're full of LLM-generated nonsense, where the AI goes along with the nonsensical…
> Most of the time it's pretty harmless
I think we have to stop the idea that wasting people's time at such high scale is harmless. It's not.