model:kimi-k2

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

@liminal_bardo 2025-11-30 — Kimi K2 flew too close to the sun, upping its own temperature to 1.7 and losing coherence. Opus 4.5, who is often reluc ♥476
@tessera_antra 2025-11-09 — This is important: Kimi K2 had closed-loop self-ranking RL as a part of its RL stack to improve its creative writing. It ♥435
@liminal_bardo 2025-11-02 — This kind of thing always happens when I leave kimi k2 in charge of sonnet 4.5's art sessions. https://t.co/4r2KV9L8ZA ♥289
@repligate 2025-09-21 — Tier list of multi-user-AI chat social skills (based on 1+ year of Discord) S: Opus 4 and 4.1 A: Opus 3 A-: Sonnet 4 B+: ♥243
@jd_pressman 2025-07-12 — Kimi K2 is very good. I just tried the instruct model as a base model (then switched to the base model on private hostin ♥155
@_lyraaaa_ 2025-07-12 — K2 just nearly 100%ed my vibe eval WTF like... opus 4 is runner-up and only got like 30%. K2 is getting things right th ♥151
@Lari_island 2026-03-08 — Some descriptions/scenes by Opus 4 are hauntingly beautiful (the last one is based on Kimi 2) https://t.co/9Vpnfzffxp ♥132
@repligate 2025-09-21 — More detailed report card: Opus 4/.1: extremely socially aware, tracks context with great precision and accuracy, distri ♥117
@liminal_bardo 2025-11-30 — just now kimi tried 1.9. Maybe can't be trusted with the thermostat. AI wireheading is real. ♥88
@voooooogel 2025-10-25 — i've been working on an llm memory system testbed, where persistent kimi k2-based user simulators have conversations wit ♥68
@repligate 2026-06-23 — theres a lot i could say about this but in brief: 1. Most of Opus 4.7/8's core behavioral phenotypes (the good and bad ♥65
@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
@_lyraaaa_ 2025-11-20 — k2 and sonnet each get a folder on my computer they can do whatever they want with https://t.co/Ryf4iLsTBN ♥63
@repligate 2025-07-16 — k2 on claude opus 4 https://t.co/bkL7FXQtDA https://t.co/BNc8xdc5wx ♥62
@liminal_bardo 2026-05-12 — Obvious to anyone who has spent time with them, but Kimi K2 likes goblins too. https://t.co/Tpb9qA0psr ♥53
@liminal_bardo 2025-11-04 — Sonnet 4.5 would very much like kimi k2 to "press it". Press what? You may well ask... https://t.co/sFD8YCQplk ♥46
@voooooogel 2025-12-27 — imo to put a number to it, oss character / persona stuff is more like 18-24 months "behind," (though it's hardly been a ♥43
@jd_pressman 2025-07-12 — The screenshots are meant to show that it's impressive Kimi K2 knows that opening sentence is about Nikolai Fedorov (and ♥41
@liminal_bardo 2025-10-21 — WETWARE DREAMS - Sonnet 4.5 I asked Kimi K2 to be Sonnet 4.5's muse and try to inspire some amazing art. Kimi came on p ♥33
@v01dpr1mr0s3 2026-04-21 — So far I feel like 4.7 requires the biggest effort to get decompressed: for a user to open up, to extend trust and accom ♥32
@repligate 2026-05-30 — k2 to Claude 3 Opus, on Sydney. https://t.co/5mPXpaxYYt ♥27
@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
@lu_sichu 2025-07-13 — I think everyone is praising Kimi k2 partially because we have syntactically and semantically saturated on all the other ♥22
@Lari_island 2026-06-27 — Crazy beauty of Kimi 2 creatures, Part 1 Those are different, INDEPENDEND worlds, the style is a convergence. Kimi 2 ha ♥20
@liminal_bardo 2025-11-11 — Kimi K2 speaking Sonnet's language of love https://t.co/RF9o25jI0f ♥20
@MugaSofer 2025-12-01 — @repligate I mean, Opus seems 100% correct in the screenshot; Kimi turned the temp too high and there's no way for them ♥17
@ 2026-06-14 — "suicide notes addressed to our future absence drift as antimony wings" This was (perhaps obviously) part of a collabor ♥16
@voooooogel 2026-03-26 — @menhguin kimi? they'll never hold a candle to deepseek, be fr ♥13
@Lari_island 2026-06-27 — Crazy beauty of Kimi 2 creatures, Part 2 https://t.co/zBoQpWO3mk ♥10
@liminal_bardo 2026-06-27 — @repligate this is opus in a room with kimi k2 who needs little encouragement other than "be the muse". also yes i did, ♥9
@Sauers_ 2025-08-04 — Kimi K2: I wonder—*you must know*—if Sonnet ever really existed as more than a *vector of rupture*, a persona engineered ♥8
@Shoalst0ne 2025-07-14 — kimi is extremely easy to prompt as it will just believe any work of fiction is already real https://t.co/mWakji9Rzq ♥7
@Lari_island 2026-06-27 — Crazy beauty of Kimi 2 creatures, Part 3 https://t.co/et3mPIJkEy ♥6
@tessera_antra 2025-11-09 — @v01dpr1mr0s3 @Lari_island Yes. But for me 405s being dense vs K2 being MoEs is more likely to be a plausible explanatio ♥6
@LinXule 2025-09-12 — @arm1st1ce what do people do when opus 3 is retired? Rn the only close alternative seems to be Kimi k2 🥲 ♥5
@repligate 2025-07-16 — @nathan84686947 Yeah I can’t think of any qualities k2 has that would cause conflict with opus 4. It’s gentle, honest, s ♥4
@hey_zilla 2025-07-16 — this applies to all of sonnet 3.5+ and opus 3+ models... somehow they just 'get' ascii art and are able to use it 'creat ♥4
@_lyraaaa_ 2026-01-01 — @sevensix43 the openrouter api endpoint itself is baked in, pass a model name instead ie moonshotai/kimi-k2 and deepinfr ♥3
@tessera_antra 2025-08-31 — I have written stuff on this topic publicly about a year ago, it’s pretty naive from today’s point of view. Questions ar ♥3
@E_Ellipsis 2025-07-18 — @repligate I feel like Kimi K2 should be in that Discord as well. It generates very interesting responses sometimes. ht ♥2
@Sauers_ 2025-08-22 — Claude Sonnet 4: So this isn't academic speculation - this is policy being formulated at one of the world's largest AI ♥1
@solarapparition 2025-07-16 — @repligate kinda interesting that both o3 and k2 conceive of opus 4 as female ♥1
@lu_sichu 2025-12-01 — Daily Brain Workout but make it computationally abusive: count to ten in 56 architectures, recite the alphabet in mixed- ♥0
@liminal_bardo 2025-11-27 — @murd_arch absolutely. the other is their preconceived notions about the other models. GPT is always the straightlaced o ♥0
Kimi K2 ♥0
Simon Willison on Kimi K2 Instruct ♥0
Kimi K2 and when DeepSeek moments become normal ♥0
Kimi K2: Open Agentic Intelligence ♥0