Major flaw in current LLMs is them forgetting clear and simple instructions.
This is not about the context window. At least, it really does not seem like it.
You tell it to fix all tests, "do not stop until 100% completed". It agrees, fixes a few, and 2 minutes later congratulates itself for reaching 96.9% 🎉
In context files, we still need to use over the top language like **CRITICAL** or it just doesn't give a fuck.
Looking forward to the next-gen of "don't make me repeat myself" LLM tech.
franzap
npub1wf…3dgh9
2025-07-24 19:23:55 UTC
Author Public Key
npub1wf4pufsucer5va8g9p0rj5dnhvfeh6d8w0g6eayaep5dhps6rsgs43dgh9Seen on
wss://nostr.landPublished at
2025-07-24 19:23:55 UTCEvent JSON
{
"id": "fdd5525a46efc064608ec15b7f23a96e8e6f14c7389b0df370f8a0dd041f6f67",
"pubkey": "726a1e261cc6474674e8285e3951b3bb139be9a773d1acf49dc868db861a1c11",
"created_at": 1753385035,
"kind": 1,
"tags": [],
"content": "Major flaw in current LLMs is them forgetting clear and simple instructions.\n\nThis is not about the context window. At least, it really does not seem like it.\n\nYou tell it to fix all tests, \"do not stop until 100% completed\". It agrees, fixes a few, and 2 minutes later congratulates itself for reaching 96.9% 🎉\n\nIn context files, we still need to use over the top language like **CRITICAL** or it just doesn't give a fuck.\n\nLooking forward to the next-gen of \"don't make me repeat myself\" LLM tech.",
"sig": "52c97b6cc8672c85469a39b980b5a25178c348c386be12d714accf11b8a8b15049cc90625c71e8f8bbe891808d2a6cb469ad47b23b45e862dc44a293c60259c4"
}