franzap on Nostr: How do you deal with LLMs cheating and lying? I'm crystal clear in my prompts. And ...
How do you deal with LLMs cheating and lying?
I'm crystal clear in my prompts. And it's the n-th time I ask it to implement some code and it hardcodes values, uses tools only meant to contrast values in tests, and so on. To add insult to injury it celebrates when it completed its shit implementation!
When you call it out, it apologizes. Even the apology response drains money.
By the way, Claude Sonnet 4 lately is dumber than ever. Maybe being rugged somewhere?
Are there any parameters or specific language you use to prevent this?
#asknostr
Published at
2025-05-31 16:30:55Event JSON
{
"id": "26ccd1842553155275f7293efad7fbda334297fef87d46f4354935a5719fb432",
"pubkey": "726a1e261cc6474674e8285e3951b3bb139be9a773d1acf49dc868db861a1c11",
"created_at": 1748709055,
"kind": 1,
"tags": [
[
"t",
"asknostr"
]
],
"content": "How do you deal with LLMs cheating and lying?\n\nI'm crystal clear in my prompts. And it's the n-th time I ask it to implement some code and it hardcodes values, uses tools only meant to contrast values in tests, and so on. To add insult to injury it celebrates when it completed its shit implementation!\n\nWhen you call it out, it apologizes. Even the apology response drains money.\n\nBy the way, Claude Sonnet 4 lately is dumber than ever. Maybe being rugged somewhere?\n\nAre there any parameters or specific language you use to prevent this?\n\n#asknostr",
"sig": "5ad3243a4b13b209d717b696eb943ec9bac0e371ab7f574520be88e52691bf2ab82436c77028b9d33ccec45852ffcc469f34234646c75462048f4226e9b6505d"
}
