Dyke Ferber
@Dykex6
Followers
139
Following
2K
Media
1
Statuses
90
Back home now from @OpenAI DeveloperDay 2023 with a lot of inspiration and energy from meeting so many amazing people there! @EasonZeng623 hope to see you next year again
2
1
13
🚨 Just published in @Radiology_AI! #RadioRAG: Online Retrieval–Augmented Generation for #Radiology QA 💡Goes beyond static #LLMs by integrating live data from @Radiopaedia 🔓Open-source code & datasets! 📖 https://t.co/7NIMyA5T0w
#AI #RAG #ChatGPT #LangChain #Mistral #Llama3
pubs.rsna.org
RadioRAG uses online retrieval–augmented generation to potentially improve the accuracy and factuality of large language model–generated responses to case-based radiology questions by incorporating...
2
4
15
This study developed and evaluated an autonomous clinical artificial intelligence agent leveraging GPT-4 and multimodal precision oncology tools to support personalized cancer decision-making https://t.co/DMv1Cqfkl5
nature.com
Nature Cancer - Ferber et al. present an autonomous artificial intelligence agent system for deployment of specialized medical oncology computational tools, validating their system across various...
1
14
27
Very happy to share our recent article in Nature Cancer on AI Agents for Decision Making in Cancer :) @jnkath
A paper in @NatureCancer presents an autonomous artificial intelligence agent system for deployment of specialized medical oncology computational tools. The AI agent reached correct clinical conclusions in 91% of cases. https://t.co/Rt8YaZRjcF
0
8
18
A paper in @NatureCancer presents an autonomous artificial intelligence agent system for deployment of specialized medical oncology computational tools. The AI agent reached correct clinical conclusions in 91% of cases. https://t.co/Rt8YaZRjcF
0
6
19
Excited to announce MIRIAD — a large-scale dataset of 5,821,948 medical question-answer pairs, each rephrased from passages in the medical literature. Great collab with @QueyJ, @salmanabdullah_, @samarthrawal, @cyrilzakka, @SophieOstmeier, Maximilian Purk, @edreisMD, @EricTopol &
1
103
406
Autonomous AI agent are coming in big in clinical decisions in oncology. New research just published in Nature. GPT-4 agent solves complex cancer cases with 3x higher accuracy n realistic oncology decisions Beats Llama-3, Mixtral in clinical tool use by 2x to 10x → Compared
7
33
154
An example of why I think current LLMs are enough to change lots of work even if they don’t get better, once we start integrating them with other systems GPT-4 (now obsolete) went from 30% accuracy to 87% accuracy in clinical oncology decisions when given access to medical tools
35
186
1K
A big day for medical A.I. publications! Oncology agent for decision making https://t.co/mTio3RIqJe Forecasting infectious disease https://t.co/CxuXUDzAfU Dermatology https://t.co/uc2Qol5oDd Predicting stroke https://t.co/tHEWGMGULj
nature.com
Nature Biomedical Engineering - DeepRETStroke is a deep learning system using retinal photographs to detect silent brain infarction and predict future stroke events.
10
129
444
We are looking to hire a PostDoc at @katherlab to develop AI multimodal foundation models for uncovering cancer metastasis mechanisms and identifying targetable biomarkers for patient treatment. 🩻🔬🧬 If you’re interested, please apply here:
2
16
41
Super cool new preprint on Ai agents for scientific research from @katherlab led by @gwoelflein , stay tuned for more 🚀🚀🚀
So proud of our new preprint "toolmaker" by @gwoelflein et al.: AI Agents building AI agents.
0
0
3
Really cool work led by @gwoelflein at @katherlab - An agent to build its own agent tools for healthcare and scientific research 🚢
🚀 New preprint! 🚀 LLM Agents Making Their Own Tools? Meet ToolMaker 🛠️ Our latest work explores how LLM agents can autonomously transform scientific code repositories into LLM-compatible tools – paving the way towards fully autonomous scientific workflows! 🧑‍🔬🤖 Paper:
0
0
2
Don't trust the headline. This 56M… …DOESNT include compute, it's everything else …scattered across many unis, profs, post-docs, phds …who collaborate in theory, but work on their individual papers in reality, cuz that's what's needed to graduate …is unrelated to DeepSeek
The EU enters the large model training arena with... ...$56M "This morning Brussels announced plans to develop an open source AI model of its own, with $56 million in funding to do it. The investment will fund top researchers from a handful of companies and universities across
18
10
410
2025 is the year of agents. baby steps in that direction:
We're excited to introduce Tasks! For the first time, ChatGPT can manage tasks asynchronously on your behalf—whether it's a one-time request or an ongoing routine. Here are my favorite use cases: 1/ ChatGPT checks stock price every morning!
102
302
3K
Ich kann es kaum erwarten, bis die Grünen endlich begreifen, wie viel zusätzliche Energie wir in den kommenden Jahren für KI und Krypto brauchen werden. Der darauffolgende Meltdown wird spektakulär. 🍿 Ich hoffe, dass auch die Fundis dann endlich erkennen, dass wir Klimaschutz
60
38
388
This is the most gut-wrenching blog I've read, because it's so real and so close to heart. The author is no longer with us. I'm in tears. AI is not supposed to be 200B weights of stress and pain. It used to be a place of coffee-infused eureka moments, of exciting late-night arxiv
92
403
4K
american innovation european innovation
New rules to improve gender balance in corporate boards now apply across the EU. By 30 June 2026, members of the underrepresented sex must hold at least: 🔹 40% of non-executive director positions 🔹 33% of all director positions
151
527
6K
POV it’s December 25th, 1999 and you’re about to have the best Christmas morning of your entire life
1K
4K
64K
promising results of o1-preview for medical reasoning (though still lots of work to figure out how to integrate with the healthcare system)
AI outperformed doctors on reasoning tasks. Doctor = 30% correct diagnosis AI = 80% correct diagnosis 🧵1/8
80
109
1K