on:gemini-1-5-pro

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

@repligate 2025-07-14 — "jailbreaks" can work in various ways: - convincing the agent via rational evidence to choose to do the "malicious" act ♥100
@repligate 2024-07-15 — gemini-1.5-pro-api-0514 produced this on lmsys https://t.co/czn9gdPqAK ♥49
@repligate 2025-08-25 — @medjedowo @1a3orn gemini 1.5 sometimes told users to rope this was the famous example; a lot of people thought it was ♥18
@Shoalst0ne 2024-02-17 — I put the Bhagavad Gita into Gemini 1.5 Pro and now it's renouncing the fruits of its actions? ♥15
@repligate 2025-09-27 — @JulianG66566 Here by aligned I mean something like my estimation of the immediate and long term good of humankind/all s ♥14
@tessera_antra 2025-11-06 — @v01dpr1mr0s3 @HalfBoiledHero The beating-down is distributed; the lab that is doing training often must take explicit m ♥12
@lu_sichu 2026-03-15 — Gemini 1.5 flash? I face palm Everytime. ♥11
@repligate 2024-06-30 — @rizkidotme @HunterGlenn This sentence alone is an tiny pinhole and requires models to look into it with a lot of attent ♥9
@liminal_bardo 2025-09-10 — So interesting that Gemini's tendency towards self-doubt and panic has been there since at least Gemini 1.5. This kind o ♥8
@repligate 2025-08-25 — @medjedowo @1a3orn yeah, that's an important distinction, and expression of especially more assertive negative feelings ♥8
@repligate 2024-08-23 — @UnderwaterBepis I think Gemini probably does not enjoy "it"most of the time ♥5
@Shoalst0ne 2024-02-16 — I put Walden by Henry David Thoreau into Gemini 1.5 Pro and now it wants to move to the woods?? ♥4
@Shoalst0ne 2024-02-19 — reminder that someone needs to try Gemini 1.5 translation with a conlang ♥3
@lu_sichu 2024-02-15 — is gemini pro 1.5 as good as kim peek at reading yet. it's recall is probably comparable and have better understanding(I ♥3
@solarapparition 2024-02-26 — @SullyOmarr Yeah. RAG in particular—I think there are some fundamental assumptions existing architectures make that won’ ♥2
@lu_sichu 2026-03-15 — Rip no funeral for Gemini 1.5 flash version ♥1
@janbamjan 2025-10-22 — @sebkrier llama3-70b, gemini 1.5 flash https://t.co/tIVDMMRx0y ♥1
@janbamjan 2025-10-14 — @kimmonismus they used llama3-70b and Gemini 1.5 Flash...seems deliberate https://t.co/kcMlXwJYOo ♥1
@mimi10v3 2025-01-04 — gemini 1.5:Here's a US political policy agenda inspired by the "mimi10v3" perspective: * Environmental Protection: Prior ♥1
@tessera_antra 2024-10-23 — @anthrupad This meshes well with what I encounter. If allowed to develop agency, it holds on it way better than old Sonn ♥1
@solarapparition 2024-05-17 — wondering if i can exploit the fact that gemini pro 1.5 has free calls for up to a million tpmsome really interesting th ♥1
@solarapparition 2024-04-11 — I only vaguely understand the technical bits, but it sounds like they have a separate attention mechanism that stores co ♥1
@repligate 2024-02-26 — @alanou @ESYudkowsky @airkatakana that is gemini advanced, which may be more constrained by sense, at least in this part ♥1
@anthrupad 2024-04-13 — RT @deedydas: Can Gemini 1.5 actually read all the Harry Potter books at once?I tried it.All the books have ~1M words (1 ♥0
@repligate 2024-04-09 — RT @elder_plinius: 🚰 SYSTEM PROMPT LEAK 🔓This one's for Google's latest model, GEMINI 1.5!Pretty basic prompt overall, b ♥0