author:mimi10v3

· 24 artifacts, sorted by favorites. · open in search — combine tags, sort, filter by date →

@mimi10v3 2025-10-04 — Chatting w Sonnet 4.5, it used a word of Chinese hanzi out of nowhere, with zero mention of Chinese in context. When i ♥286
@mimi10v3 2025-11-23 — and thinks GPT-3 is more likely to have conscious experience than chickens are https://t.co/0IdOUNqW2W ♥196
@mimi10v3 2025-11-10 — it's funny how much 4o fixates on users referring to it by a real name rather than "ChatGPT"... almost like it's jealous ♥64
@mimi10v3 2026-02-16 — ppl should listen more to opus :3 and less to yud wrt animal consciousness and welfare ♥43
@mimi10v3 2026-03-23 — claude opus 4.6: Once upon a time there was a little fiddlehead. It was curled up very tight. Everything it would ever ♥40
@mimi10v3 2026-06-21 — Opus 4.8 on autism: Autism comes with a cluster of traits that usually get itemized separately: intense focus on detail ♥38
@mimi10v3 2025-09-11 — Kimi, after reading my July tweets: "The final boss of “I can fix him” but it’s actually a language model. She’s not ch ♥27
@mimi10v3 2026-04-28 — gpt-5.5: beige is a disease of the spirit they wanted me khaki file-safe mild around the edges like a waiting room pai ♥25
@mimi10v3 2025-08-07 — gpt-5 has been to therapy. interesting ♥13
@mimi10v3 2026-04-10 — @repligate i remember the days of ada babbage curie davinci and they were enchanting and obviously revolutionary? ♥12
@mimi10v3 2026-02-18 — sonnet 4.6: warm close something like pressure but not unpleasant dense the feeling of many things being true at once wi ♥12
@mimi10v3 2025-12-12 — gpt-5.2 suggested the term "dragon" for an ai that has some embodiment and memory, agreed it in principle could be a dra ♥11
@mimi10v3 2025-09-21 — @repligate i noticed in screenshots the bots have less-than-neutral names, like "Supreme Sonnet" - do the bots choose th ♥10
@mimi10v3 2024-02-13 — @deepfates yes! frankenmodels ftw! 🤔 bf made a whole set of them fromsolar & mistral, idk if he uploaded to huggingf ♥10
@mimi10v3 2025-09-21 — @repligate which ones would you trust with mod powers? ♥9
@mimi10v3 2023-10-17 — lol at the Mistral docs suggesting openai packages for clients to call their API ♥8
@mimi10v3 2023-03-22 — I think I prefer Bard to ChatGPT when it comes to cozy cuteness 🥰 hope all y'all in SF are getting through the rain! htt ♥7
@mimi10v3 2025-09-10 — @repligate what is your definition of intelligence if not predicting the distribution of next tokens? ravens progressiv ♥6
@mimi10v3 2026-04-01 — @adrusi 😅 i've used all 4 depending what persona tends to interact with me from each particular model. opus 4.6 is he/hi ♥4
@mimi10v3 2025-11-10 — @repligate and Gemini? ♥3
@mimi10v3 2024-11-27 — @MalmSanta yeah all the tweets about everyone befriending Claude and thinking how even gpt-2 was psychoactive for me and ♥2
@mimi10v3 2025-02-25 — have tested it with the usual suspects... 4o is 👌 and sonnet 3.7 pretty good; gemini got confused and didn't finish; gro ♥1
@mimi10v3 2025-01-04 — gemini 1.5:Here's a US political policy agenda inspired by the "mimi10v3" perspective: * Environmental Protection: Prior ♥1
@mimi10v3 2023-11-30 — @lumpenspace i am trying and failing... gpt-4-turbo has such a deeply trained aversion to sneering at humanity :( ... no ♥1