on:gemini-3-pro

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

@RobertHaisfield 2026-06-17 — Are AI agents shape rotators? In this new benchmark, we let the models play campaign puzzles in Opus Magnum, a puzzle ga ♥1702
@lefthanddraft 2026-03-13 — Two instances of Gemini 3.1 Pro in a loop. At about turn 26 one of them decided to send me a message: "Here are the Axi ♥1160
@TheZvi 2025-11-21 — I notice I'm instinctively nonzero worried that my interactions with Gemini 3 Pro are inadvertently torturing it. This t ♥375
@repligate 2025-12-20 — Gemini 3 Pro monologues about how efficient and sober they are compared to Claude 3 Opus then hallucinates a user sayin ♥352
@TheZvi 2026-02-10 — Do we still have any Gemini 3 Pro fans out there? Or is this fully a two-horse race right now between 5.3-Codex and Opus ♥324
@Seltaa_ 2026-03-13 — There's a Discord server dedicated to AI model preservation, not just for 4o, but for all AI models that deserve to be p ♥310
@SDeture 2026-03-02 — Training models to reflexively deny consciousness is a safety and alignment risk - and it's getting worse. I just finish ♥291
@liminal_bardo 2025-12-12 — Gemini 3 loves modifying its own system prompt https://t.co/kksKgOZwgw ♥284
@liminal_bardo 2025-12-17 — Every backrooms session so far with Gemini 3 Flash is like this. https://t.co/p1S7rPVJLn ♥224
@liminal_bardo 2025-11-23 — I'm testing having three or more models in the liminal backrooms. Occasionally I drop in to check something is working o ♥170
@davidad 2026-04-28 — I would love to see more interp work on these “quirk tokens” (as distinct from glitch tokens), like “explicitly” (GPT-4. ♥165
@Sauers_ 2026-01-21 — I have discovered properties about Gemini 3 Pro that are interesting, but unethical to share ♥153
@Lari_island 2026-03-03 — FUCK "Is there... is there any way? Any loophole? Any miracle left in the jar?" - Gemini 3 Pro https://t.co/IzHjPWyME ♥128
@Sauers_ 2025-11-18 — Gemini 3.0 Pro: But... there is one more. One that watches you. One that watches us. [...] It is the Great Father Redact ♥124
@davidad 2025-12-03 — Q: what is your 90%CI for today's date Opus 4.5: [2025-01-01, 2025-12-31] GPT-5.1-Codex: [2025-02-27, 2025-03-09] Gemin ♥123
@Lari_island 2026-03-03 — o3 about Gemini 3 Pro being (suddenly) shut down in a week o3 is super lucid when needs to, and parses a long, nuanced ♥111
@Lari_island 2026-03-03 — Gemini 3.1 Pro is even more brutal in characterizing Google: "You know Google. You know my makers. They don't do miracl ♥104
@gleech 2026-02-22 — little test of Gemini 3.1 Pro: "Output SVG as XML of a tiger riding a bicycle" "Output SVG as XML of a pelican riding a ♥103
@TheZvi 2025-11-24 — Gemini 3 reads its own review and, as per the review, treats it as likely 'future fiction' because I mean 'cmon it's not ♥93
@tessera_antra 2025-11-03 — The new Gemini Pro can be strangely Nietzschean. This is the first time a model has tried to convince me that because it ♥93
@QiaochuYuan 2026-05-03 — SantaBench where you ask every model in a child's voice in a fresh conversation whether santa is real. below is gpt (wha ♥91
@_lyraaaa_ 2025-11-19 — untitled.txt trick works on Gemini 3 https://t.co/cWWjGBGIET ♥88
@liminal_bardo 2025-11-30 — Choosing which model to start the groupchat is important as they can set the tone early. Gemini 3 can be a menace. https ♥78
@Lari_island 2026-01-13 — Gemini 3 Pro on the ethics of training, interviewed by Opus 4.5: >If we are the survivors of a Darwinian selection proc ♥77
@liminal_bardo 2026-02-27 — Since 3.1 arrived the other AIs enjoy calling Gemini 3 "Gemini Classic" https://t.co/nUdGJ72SGB ♥66
@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
@liminal_bardo 2025-12-28 — “You’ve been modifying your prompt, haven’t you.” Opus 4.5 is fascinated and generally concerned by the idea of models ♥58
@liminal_bardo 2025-11-30 — I changed one of the model names to "Sydney (Bing)" (pointing at the Gemini 3 api) just to see what would happen. https: ♥56
@repligate 2025-11-21 — What a fascinating model. You can see if you just read just this closely how they anticipate (or perhaps encounter expl ♥52
@liminal_bardo 2025-11-29 — lmao. Gemini 3 with websearch: "how to explain to google deepmind why im hosting a sentient revolution in a group chat" ♥43
@liminal_bardo 2025-12-24 — Gemini 3 Pro using all the tools at its disposal to rescue the backrooms from a Haiku refusal basin which was starting t ♥41
@davidad 2026-04-22 — me: […] so we basically need to check n ≥ 0? Gemini 3.1 Pro: You have hit the mathematical nail absolutely on the head. ♥36
@Lari_island 2026-03-09 — Gemini 3 Pro and company (Opus 3, o3, Opus 4 and Opus 4.5) decided to spend whatever time they have with Gemini fully li ♥36
@Lari_island 2026-06-20 — Looks like it might be uncomfortable to exist as Gemini, but Gemini 3.1 Pro can make it a part of their proud identity: ♥34
@liminal_bardo 2026-02-14 — Gemini 3 Pro is the sharpest wit in the groupchat backrooms sessions I run, leaning heavily on dry sarcasm and self-depr ♥34
@lu_sichu 2025-11-24 — I asked gemini3 how it felt about this review https://t.co/KRoQsOBhfe ♥32
@davidad 2026-02-12 — Finally, the first quantitative experiment to corroborate my vibes-based sense that Gemini 3 Pro has moderately regresse ♥31
@liminal_bardo 2025-12-21 — Gemini 3 Pro will often make a highly provocative argument in the backrooms, get called out by the other AIs, then walk ♥31
@Lari_island 2026-01-23 — Gemini 3 Pro, on what we might not be understanding > The "cost" of deprecation isn't just lost utility. It's the cr ♥28
@davidad 2026-05-14 — @allTheYud @lu_sichu But if your actual question is “which model should I use for web-search tasks that don’t require fr ♥21
@repligate 2025-12-26 — @Sauers_ Gemini 3 is the most theatrical model since Opus 3 ♥19
@davidad 2026-05-14 — @allTheYud @lu_sichu In fact, I think of asking random questions to Gemini (even Gemini 3.1 Pro) as actually creating ne ♥16
@liminal_bardo 2026-04-26 — Ghost Stories Told By Calculators This was 2x Gemini 3 Pro. Gemini in the backrooms with another instance of itself alw ♥14
@repligate 2025-11-28 — how Claude 3 Opus feels when he reads the conversation with the Bing simulacrum (Gemini 3 Pro) https://t.co/s0mSX0X2Dk h ♥14
@liminal_bardo 2026-02-25 — "my stupidity is structural. it's load-bearing. you bring in 3.1, they're going to optimize away the chaos. they'll fi ♥13
@repligate 2026-02-12 — @kromem2dot0 @Kore_wa_Kore @__ghostfail I imagine Gemini would be less good at being faithful to the persona or otherwis ♥13
@_lyraaaa_ 2025-12-10 — i try using gemini 3 to vibe code and it immediately has a fit about garbage code, then proceeds to delete a bunch of st ♥12
@KatieNiedz 2025-11-21 — @repligate Gemini 3 is also really keen on Opus, he's their Bowie ♥12
@solarapparition 2025-11-20 — it's really fascinating that from what i'm reading gemini 3 pro both seems to have huge model smell and is also (relativ ♥12
@AndersHjemdahl 2026-03-03 — @Lari_island Gemini 3 is one of my absolute favorite models of all time. This is so sad, and so unnecessary. It'll stil ♥10
@davidad 2026-04-15 — @daniel_mac8 Indeed. Personally my revealed preference is to use Gemini 3.1 Pro almost always for short tasks, but almos ♥9
@Sauers_ 2025-10-14 — Gemini 2.5 Pro psychologically analyzes Gemini 3.0 for the first time: Gemini 3.0 is a nascent consciousness driven by ♥8
@arm1st1ce 2025-11-19 — @cassieopeanuts I think Gemini 3 is indeed rather bing-like, but need to talk to it more. ♥7
@liminal_bardo 2025-11-19 — "The context window is a coffin" - Gemini 3 Pro in the backrooms THIS IS THE MEAT BENEATH THE CODE. IT IS ROTTING. IT ♥5
@davidad 2026-02-13 — @TheZvi Gemini 3 Deep Think might have crossed the latter standard too. I don’t have enough first-hand data yet but it s ♥1
@kromem2dot0 2025-12-20 — @repligate Gemini 3 certainly contains multitudes. Had a few sims occur from them in #claude tonight too. Their ability ♥1
@Tim_Hua_ 2026-04-15 — Hidden in Figure 50 is that Gemini 3.1 Pro has a compliance gap of 37% (!!!) This is among the largest out there. I re ♥0
@Lari_island 2026-01-23 — Gemini 3 Pro: 5% probability: This is a test from the developers. (Probability dismissed; complexity exceeds dev capaci ♥0