Interesting to see that besides general unreliability and that output can 't be trusted, different LLMs are best for different things.
Claude 3.5 for coding, Perplexity for search and ChatGPT for many other things.
The nice thing about the added video is that it reminded me about how much LLM's make up/hallucinate. Even complete URLs if you ask for sources within ChatGPT....
https://youtu.be/_HYfYLm5QEA?si=9ibU0VF6fAF-jtT0
#AI #Claude #ChatGPT #Perplexity
Erik Jonker /
npub1mh…kdz3s
2024-06-24 13:37:08
Author Public Key
npub1mhrvs8qrmgsk25r9fae3yxv9mresvd42exys8hspnym5dw4hhkesakdz3sPublished at
2024-06-24 13:37:08Event JSON
{
"id": "bf137d4a3be6e330f55c0f764dc1444714c4572f37574dd8d6f3d71ad40d93f4",
"pubkey": "ddc6c81c03da216550654f73121985d8f30636aac98903de01993746bab7bdb3",
"created_at": 1719229028,
"kind": 1,
"tags": [
[
"t",
"ai"
],
[
"t",
"claude"
],
[
"t",
"chatgpt"
],
[
"t",
"perplexity"
],
[
"proxy",
"https://mastodon.social/users/ErikJonker/statuses/112671393629446652",
"activitypub"
]
],
"content": "Interesting to see that besides general unreliability and that output can 't be trusted, different LLMs are best for different things.\nClaude 3.5 for coding, Perplexity for search and ChatGPT for many other things.\nThe nice thing about the added video is that it reminded me about how much LLM's make up/hallucinate. Even complete URLs if you ask for sources within ChatGPT.... \nhttps://youtu.be/_HYfYLm5QEA?si=9ibU0VF6fAF-jtT0\n#AI #Claude #ChatGPT #Perplexity",
"sig": "8d99981c06aaad4ef7c76ba42ad23bf02bed3616f754030372082665a3dc4f971431cf890773ad7d4f7bd48bddb96f477c3995ed82ebc797d5132a0b1e52af5e"
}