Weiyan Shi's banner

Weiyan Shi

@shi_weiyan • 8,696 subscribers

Prof @Northeastern | MIT TR-35 | #AI2050 Early Career Fellow | Prev @Columbia @StanfordNLP | Co-created CICERO | human-AI co-evolution + AI safety

Shorts

Ever watch an agent solve a problem with 100% confidence and get it completely wrong? You can fix it… if you catch it. But then you need to watch every… single… run. New paper: We show that a meta-agent can do this for you, so your agents get ~2x more done on their own. 🧵

Ever watch an agent solve a problem with 100% confidence and get it completely wrong? You can fix it… if you catch it. But then you need to watch every… single… run. New paper: We show that a meta-agent can do this for you, so your agents get ~2x more done on their own. 🧵

46,021 görüntüleme

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

New paper: You can make ChatGPT 2x as creative with one sentence. Ever notice how LLMs all sound the same? They know 100+ jokes but only ever tell one. Every blog intro: "In today's digital landscape..." We figured out why – and how to unlock the rest 🔓 Copy-paste prompt: 🧵

New paper: You can make ChatGPT 2x as creative with one sentence. Ever notice how LLMs all sound the same? They know 100+ jokes but only ever tell one. Every blog intro: "In today's digital landscape..." We figured out why – and how to unlock the rest 🔓 Copy-paste prompt: 🧵

279,025 görüntüleme • 8 ay önce

OpenClaw wiped people's inbox – ignoring repeated commands to stop. This isn't a fluke. Every model we tested fell for a simple trick: Split a dangerous command into a few routine steps → safety is gone. New paper + open-source fix so your agent doesn't wipe yours next ⬇️

OpenClaw wiped people's inbox – ignoring repeated commands to stop. This isn't a fluke. Every model we tested fell for a simple trick: Split a dangerous command into a few routine steps → safety is gone. New paper + open-source fix so your agent doesn't wipe yours next ⬇️

45,258 görüntüleme • 4 ay önce

Put ChatGPT at a cocktail party🥂. Can it - understand people's conversations, gestures - figure out their relations, - and even chime in with social advice? 🦍Announce KokoMind. 🌟Check out this demo! More at #AI #GPT4 #ChatGPT #OpenAI #Shrinking 🧵

Put ChatGPT at a cocktail party🥂. Can it - understand people's conversations, gestures - figure out their relations, - and even chime in with social advice? 🦍Announce KokoMind. 🌟Check out this demo! More at #AI #GPT4 #ChatGPT #OpenAI #Shrinking 🧵

110,963 görüntüleme • 3 yıl önce

Daha fazla içerik yok.