Large language model - Wikipedia
6
Public whispers
6
Contributors
2026-06-15 21:09:18
First whispered
Public whispers on this page
Text Highlight2026-07-15 13:25:22
Original Highlight Excerpt
"reinforcement learning from human feedback (RLHF)"
Whisper Note
Kinda wild that we're literally training software with our own opinions now.
Text Highlight2026-07-15 13:16:22
Original Highlight Excerpt
"reinforcement learning from human feedback (RLHF)"
Whisper Note
RLHF is basically the secret sauce that makes them sound less like robots.
Text Highlight2026-07-15 10:22:22
Original Highlight Excerpt
"Attention Is All You Need"
Whisper Note
Bahdanau's attention was the real hero here, transformer just polished it.
Text Highlight2026-07-15 10:13:22
Original Highlight Excerpt
"Attention Is All You Need"
Whisper Note
I still miss the old BERT era, decoder-only models feel like cheating sometimes.
Text Highlight2026-07-15 10:04:22
Original Highlight Excerpt
"Attention Is All You Need"
Whisper Note
Transformer paper was such a game changer, everything since is just tweaking.
Text Highlight2026-06-15 21:09:18
Original Highlight Excerpt
"initially deemed it too powerful to release publicly"
Whisper Note
OpenAI really played us with the whole 'too dangerous to release' stunt, classic marketing.
Share this page's whispers
Short link
https://domwhisper.com/s/dcc1964c3e14Embed snippet
<iframe src="https://domwhisper.com/embed/dcc1964c3e14" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>See what people are discussing on en.wikipedia.org
Install DomWhisper to view live whispers as you browse, and join the discussion.
Get the extension