Benedict Quartey
@Benedict_Q
Followers
994
Following
10K
Media
127
Statuses
4K
Son of the living God. Building instruction-following intelligence that improves with experience. PhD @Brownuniversity . Organizer @DeepIndaba . Prev @rai_inst
Joined July 2011
🚨 What is the best way to use foundation models in robotics?. Our new work shows that combining LLMs & VLMs with ideas from formal methods leads to robots that can verifiably follow complex, open-ended instructions in the real world. 🌍. We evaluate on over 150 tasks🚀. 🧵 (1/4)
3
49
277
Artificial intelligence isn’t THE THING … it is the thing that gets us to THE THING!.
0
0
2
I herald his beginning … i herald your end … I herald ….
NEWS🚨: An interstellar object has been spotted entering the solar system at high speed
0
1
1
RT @PapermapAI: Who are your BEST customers and how do you find more of them?. Alan reverse-engineers your top clients using your existing….
0
1
0
RT @PapermapAI: After weeks of building, we’re launching Papermap AI and with it, your first AI employee: Alan 🧠🚀. This isn’t another dashb….
0
14
0
Compelling product and great execution. Congratulations @im_roy_lee @neelyweely23 and the entire team @cluely.
introducing @cluely. today is the start of a world where you never have to think again. we just killed 9 industries (thread):
0
0
0
RT @Benedict_Q: Apt @karpathy ! Not enough credit is given to folks building functional reliable LLM based software. Requires a new set of….
0
6
0
Apt @karpathy ! Not enough credit is given to folks building functional reliable LLM based software. Requires a new set of skills not just traditional engineering. All of a sudden nothing is cleanly deterministic, and you have to manage a temperamental demigod living in your
+1 for "context engineering" over "prompt engineering". People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window.
4
6
10
Software 3.0 @karpathy . Why code yourself when you can negotiate with an overconfident alien intern until it does the right thing.
0
0
3
RT @YuXiang_IRVL: “As a PHD student, your job is not publishing a paper every quarter. Focus on a problem in deep understanding and solve i….
0
78
0
RT @ahmed__jaafar: Happy to announce that the paper has been accepted to #IROS2025! Thank you to my co-authors, including (but not limited….
0
1
0
RT @nnnnicholas: it’s going to take a long time for ai designers to fully internalize that most people don’t know what to ask for.
0
79
0
No one show this to my Phd Advisor 😂😂😂.
Felt insane energy last time I was in SF (thanks @byersblake). Chatting with folks like @karpathy, @ericjang11, @xf1280 got me feeling really unsatisfied with my ideas ending in published papers. I've been cooking with a cracked team of friends and i'm super excited to launch.
1
0
2
Felt insane energy last time I was in SF (thanks @byersblake). Chatting with folks like @karpathy, @ericjang11, @xf1280 got me feeling really unsatisfied with my ideas ending in published papers. I've been cooking with a cracked team of friends and i'm super excited to launch.
0
0
10
Very very impressive and cool work!.
💡Can we let an arm-mounted quadrupedal robot to perform task with both arms and legs? . Introducing ReLIC: Reinforcement Learning for Interlimb Coordination for versatile loco-manipulation in unstructured environments. [1/6].
0
0
4
RT @XYBRON: Built a shipping label generator in-house for a friend’s logistics company. No more manually writing order details on packages—….
0
4
0
Haven’t read this paper and have no opinions about it but everyday I’m reminded that many people who tweet about “Ai” on X don’t actually know anything about how research works or who actually writes papers.
0
1
8
APT! The great thing about AI forward dev is you stand the chance of getting surprising new additions you weren’t initially considering.
0
1
1