
Shengran Hu
@shengranhu
Followers
1K
Following
2K
Media
6
Statuses
174
PhD student @UBC_CS w/ @jeffclune. RS Intern @SakanaAILabs. I am building open-ended agentic AI systems that can accumulate complexity in language.
Vancouver, British Columbia
Joined February 2019
Can AI systems improve themselves recursively—agents that enhance their performance while advancing further self-improvement? Today, we take a step toward realizing this vision. Introducing Darwin Gödel Machine: AI that improves itself by rewriting its own code. We build on the.
Introducing The Darwin Gödel Machine: AI that improves itself by rewriting its own code. The Darwin Gödel Machine (DGM) is a self-improving agent that can modify its own code. Inspired by evolution, we maintain an expanding lineage of agent variants,
14
17
96
RT @iwiwi: Go wider, deeper—or together? 🤔 Introducing AB-MCTS (Adaptive Branching Monte Carlo Tree Search), a new inference-time framework….
0
63
0
RT @hardmaru: AI Improves at Improving Itself Using an Evolutionary Trick: Researchers use evolutionary algorithms to enhance AI coding ski….
0
46
0
RT @hardmaru: The future of AI is open-ended: Embracing open-endedness in the pursuit of creative AI. Essay by @richardcsuwandi . https://t….
0
36
0
RT @jeffclune: Great writing about the Darwin Gödel Machine by @SilverJacket, who is one of the best science writers in the business. Thank….
0
1
0
RT @richardcsuwandi: Most AI systems today follow the same predictable pattern: they're built for specific tasks and optimized for objectiv….
0
21
0
RT @jeffclune: We are thrilled to welcome Ryan to our lab at UBC! We very much look forward to working with you and seeing the amazing work….
0
3
0
RT @jennyzhangzt: @SilverJacket thinks very deeply about the science and tech he covers and writes really well, I highly recommend his arti….
0
1
0
RT @SilverJacket: AI Improves at Improving Itself Using an Evolutionary Trick. My latest for @IEEESpectrum, on research by @jennyzhangzt e….
0
10
0
RT @jeffclune: How it felt to know AGI is coming soon long before the world was paying attention.
0
20
0
ADAS:
Can AI agents design better AI agents?. We describe a newly forming research area "Automated Design of Agentic Systems" (ADAS) that aims to automatically design powerful agents & a new method where a meta agent invents new agents by programming them in code. Led by @shengranhu 🧵
1
0
0
Very excited to share our latest work on Automated Design of Agentic Systems (ADAS) and Darwin Gödel Machine (DGM) with @Synced_Global! Watch the interview: (in Chinese)
2
7
21
RT @jeffclune: Very nice summary of the Darwin Gödel Machine in Fortune, and an interesting tie-in to @sama's excellent recent blog post.….
0
7
0
RT @hardmaru: It feels like the agent layer is almost as important as the foundation model layer for hard tasks.
0
30
0
RT @tianyu_hua: 🚨 New benchmark alert! 🚨. Can today’s LLMs implement tomorrow’s research ideas?. We put them to the test. Introducing #Rese….
0
26
0
RT @tan51616: Very excited to share this work. Here's an example of how to interact with T2L through a webui provided in the repo https://t….
0
21
0
RT @RobertTLange: Introducing Stein Variational Evolution Strategies. Exciting new work on leveraging Stein Variational methods for discove….
0
9
0