> I talked to GPT-3.5 and GPT-4 a decent amount while writing this article. While they lied to me a lot and most of the information was useless, they were sometimes very helpful for working through problems. LLM assistance can be net positive if you’re aware of their limitations and are extremely skeptical of everything they say. That said, they’re terrible at writing. Don’t let them write for you.
Good. Thank you for disclosing this.
Great to know that even teenagers like the author know the limits of LLMs and know where and when to use them and haven't fallen into the hype and mania in blindly trusting them, unlike the millions of so-called new wave of 'AI startups' out there.
> I talked to GPT-3.5 and GPT-4 a decent amount while writing this article. While they lied to me a lot and most of the information was useless, they were sometimes very helpful for working through problems. LLM assistance can be net positive if you’re aware of their limitations and are extremely skeptical of everything they say. That said, they’re terrible at writing. Don’t let them write for you.
Good. Thank you for disclosing this.
Great to know that even teenagers like the author know the limits of LLMs and know where and when to use them and haven't fallen into the hype and mania in blindly trusting them, unlike the millions of so-called new wave of 'AI startups' out there.
Once again, fantastic work and keep it up.