Every time I try to replicate or create useful cases for LLMs in technical areas I understand (including code/software development, corroborating various claims, summarizing text, etc) I have such a terrible experience convincing it to actually answer what I ask, without hallucinating or its clear training biases to shine through.
I have yet to see anyone's shared "useful output" (non-trivial tasks) without the same flaws.
I'm not surprised, but confused: people keep claiming it works??
Niels Abildgaard
npub14g…g3gyr
2026-03-01 18:09:20 UTC
Author Public Key
npub14gfkpmm2k2e2p3jtuq2g4wwe8y8h8nrxclt4xvu04clm8yzmzy7qmg3gyrSeen on
wss://relay.momostr.pinkPublished at
2026-03-01 18:09:20 UTCEvent JSON
{
"id": "b2406ab6cd7f7f9790a82f31f7f3f1cbbcbbce28038b131fc5d9919df1b77135",
"pubkey": "aa1360ef6ab2b2a0c64be0148ab9d9390f73cc66c7d753338fae3fb3905b113c",
"created_at": 1772388560,
"kind": 1,
"tags": [
[
"proxy",
"https://mas.to/@nielsa/116155256730780974",
"web"
],
[
"proxy",
"https://mas.to/users/nielsa/statuses/116155256730780974",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://mas.to/users/nielsa/statuses/116155256730780974",
"pink.momostr"
],
[
"-"
]
],
"content": "Every time I try to replicate or create useful cases for LLMs in technical areas I understand (including code/software development, corroborating various claims, summarizing text, etc) I have such a terrible experience convincing it to actually answer what I ask, without hallucinating or its clear training biases to shine through.\n\nI have yet to see anyone's shared \"useful output\" (non-trivial tasks) without the same flaws.\n\nI'm not surprised, but confused: people keep claiming it works??",
"sig": "ee6a09f5477bc37f5b5134725469ba6a751c55f983111466c6d8477556f450c833d24184dd0c1145e0f9e4ad99601028502ca355e754522679a7dacbb637f592"
}