thomas

Just spent the weekend deep-researching and writing about a relatively arcane topic using ChatGPT, Claude, and Perplexity side by side.

Using multiple LLMs and contrasting responses to weed out the occasional hallucination is a massive accelerator of knowledge.

The LLMs even helped me spot a misleading error in one of the authoritative textbooks on the same topic, which was until then my source of truth.

Game changer in how I’ll be engaging going forward with topics I want to discover more seriously.

Aviator, diver, Etherean, nexialist, PhD in aviation ∩ climate science | Host of /diving /ethfinance /eth-staker /geopolitics /science /singapore /thomas

Are there specific cases where you prefer ChatGPT to Claude or vice versa?

Pragmatism (Security) at OP Labs.
Prev: ConsenSys & Coinbase.

Attribs: Friendly, curious, introverted, mid-witted.
Chans: /eth-security /maurelian /stoicism




Thanks. I had been using Claude exclusively for about 6 months, but came back to ChatGPT for the ghiblis and was surprised how fast it had come in terms of just the app itself. It’s definitely the richest and multi-modalest, and the deep research is excellent.

Might actually cancel my Claude sub (can use it via cursor or API if I really need it).

I’ve found ChatGPT’s conversational style to be more natural, as if I was exchanging with a knowledgeable human. Claude was more terse and the LaTex formatting broke down completely there, but not on ChatGPT, making it difficult to parse the replies. I did encounter one misleading hallucination on ChatGPT though.