ioana ciucă
@errai34
Followers
2K
Following
11K
Media
960
Statuses
8K
anti-disciplinary researcher @Stanford 🗺️ · ai for science @universe_tbd · co-creating the future with starry humans · eu sou a mesma #colectiv
San Francisco, CA
Joined November 2014
🧵 We gave AI models the same biography to read. They all picked different "most important" life events. After analyzing hundreds of stories with LLMs, @Pranav_AL and I discovered AI models have different personalities🪄. Could this be AI's supernova moment? →
6
12
41
RT @denny_zhou: Slides for my lecture “LLM Reasoning” at Stanford CS 25: Key points: .1. Reasoning in LLMs simply….
0
213
0
was on a panel at an event i can’t talk about and i now realize why sv is so special. new friends from new worlds 💜.
0
0
4
RT @niloofar_mire: 🧵 Academic job market season is almost here! There's so much rarely discussed—nutrition, mental and physical health, unc….
0
21
0
RT @adrianicosma: Dr.Copilot is: .🧠 A multi-agent system .🔧 Prompt-optimized with DSPy .🏥 Deployed in real Romanian telemedicine .💬 Improve….
arxiv.org
Text-based telemedicine has become increasingly common, yet the quality of medical advice in doctor-patient interactions is often judged more on how advice is communicated rather than its clinical...
0
1
0
RT @adrianicosma: 🚨 New paper!.We present Dr.Copilot – a multi-agent LLM system deployed in the real world to improve doctor-patient commun….
0
18
0
This is so so great, congrats to the team!!!🚀.
🚨 New paper!.We present Dr.Copilot – a multi-agent LLM system deployed in the real world to improve doctor-patient communication in Romanian 🇷🇴. One of the first production deployments of LLMs in Romanian telemedicine. 👇.📄
0
0
1
RT @robertarail: I’m building a new team at @GoogleDeepMind to work on Open-Ended Discovery!. We’re looking for strong Research Scientists….
0
220
0
RT @richardcsuwandi: We’re training AI on everything that we know, but what about things that we don’t know? . At #ICML2025, the EXAIT Work….
0
18
0
Looking up ('99) -> math (2010) -> rockets (2013) → astro (2016) → entrepreneurship (2020) → ai for good → art ML (2021) → LLMs (2023) → funky ai for science lab (2023) → Stanford (2024). I need to chill. Or do I?.
1
0
6
RT @_jake_ward: Do reasoning models like DeepSeek R1 learn their behavior from scratch? No! In our new paper, we extract steering vectors f….
0
26
0
DeepHistory.
Our Aeneas AI model gives historians valuable new insights into ancient inscriptions & ancient history that may have taken years to uncover otherwise. Published in @Nature today:
0
0
3
music to write reviews on until you figure out what the title means haha.
0
0
2
RT @askalphaxiv: Google has shared the system prompt that got Gemini 2.5 Pro IMO 2025 Gold Medal 🏅. paper now #1 trending on alphaXiv 📈 htt….
0
259
0