Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

A conversation on the optimal reward for coding agents, infinite context models, and real-time RL

Cursor

389,074 subscribers

317,814 views • 1 year ago •via X (Twitter)

Health & Wellness Science & Technology Education

Anya Rossi• Live Now

Private livecam show

10 Comments

Han1 year ago

Found YouTube link

Moescape AI1 year ago

Sign up & effortlessly find YOUR perfect character to chat with on Moescape AI: #MoescapeTavern #aichatbot

kipply1 year ago

stan SEASNELL

martin.p1 year ago

how about direct user feedback below the agent answer? simple 1-5 rating, maybe hidable in settings. I'd gladly give feedback, especially on the answer of the initial request

Luke Igel1 year ago

Omg (Snell 2024) and Jacob ??

Yacine Mahdid1 year ago

we need more women in ai

morgan —1 year ago

youtube?

Pedro Ramos1 year ago

@mntruell Wrote about Revenue Sharing as RL for Agents:

Kalash1 year ago

this sounds like a wild debate

Edoardo Contente1 year ago

Looks more homely than @OpenAI

Related Videos

AI coding agents hit a wall when codebases get massive. Even with 2M token context windows, a 10M line codebase needs 100M tokens. The real bottleneck isn't just ingesting code - it's getting models to actually pay attention to all that context effectively.

AI coding agents hit a wall when codebases get massive. Even with 2M token context windows, a 10M line codebase needs 100M tokens. The real bottleneck isn't just ingesting code - it's getting models to actually pay attention to all that context effectively.

Garry Tan

976,161 views • 1 year ago

Nia by @NozomioAI is an MCP that gives coding agents 10x more developer context. It indexes external repos and docs, so any coding agent always has the right context. Congrats on the launch, Arlan!

Nia by @NozomioAI is an MCP that gives coding agents 10x more developer context. It indexes external repos and docs, so any coding agent always has the right context. Congrats on the launch, Arlan!

Y Combinator

33,333 views • 10 months ago

The Design OS for your coding agents $ npx skills add superdesigndev/superdesign-skill - Design w/ full codebase context - Infinite canvas exploration - Built in prompt library Here is how it works 🧵👇

The Design OS for your coding agents $ npx skills add superdesigndev/superdesign-skill - Design w/ full codebase context - Infinite canvas exploration - Built in prompt library Here is how it works 🧵👇

Jason Zhou

67,679 views • 5 months ago

A conversation with Claude Code's creator Boris Cherny on the future of agentic coding, the evolution of coding models, and how he uses Claude Code to build Claude Code.

A conversation with Claude Code's creator Boris Cherny on the future of agentic coding, the evolution of coding models, and how he uses Claude Code to build Claude Code.

Alex Albert

81,455 views • 9 months ago

2.5 models are thinking models, capable of reasoning through thoughts before responding. The result is enhanced performance and improved accuracy. This means Gemini 2.5 can handle more complex problems in coding, science and math, and support more context-aware agents.

2.5 models are thinking models, capable of reasoning through thoughts before responding. The result is enhanced performance and improved accuracy. This means Gemini 2.5 can handle more complex problems in coding, science and math, and support more context-aware agents.

Google

31,023 views • 1 year ago

inside Smallest AI office, Sudarshan Kamath on what's the missing piece for voice agents!! why Lightning TTS, ultra-low latency voice models needs HydraDB the knowledge and context layer for AI Agents!!

inside Smallest AI office, Sudarshan Kamath on what's the missing piece for voice agents!! why Lightning TTS, ultra-low latency voice models needs HydraDB the knowledge and context layer for AI Agents!!

Harnoor Singh

32,486 views • 1 month ago

The Context Company (The Context Company) is redefining observability for AI agents. Catch silent failures like bad tool calls, infinite loops, and hallucinations in just 10 lines of code. Congrats on the launch, Rohil Agarwal & arman!

The Context Company (The Context Company) is redefining observability for AI agents. Catch silent failures like bad tool calls, infinite loops, and hallucinations in just 10 lines of code. Congrats on the launch, Rohil Agarwal & arman!

Y Combinator

49,351 views • 7 months ago

The data analytics bottleneck is real. Questions stack up, context gets lost, and by the time you get an answer, you forgot why you even asked. How to turn coding agents into 24/7 data analysts👇

The data analytics bottleneck is real. Questions stack up, context gets lost, and by the time you get an answer, you forgot why you even asked. How to turn coding agents into 24/7 data analysts👇

Cognition

251,117 views • 9 months ago

The Copilot CLI now supports builtin subagents for parallelizing search and coding tasks within separate context windows. Uniquely, the outer agent can invoke different models. Ask Opus, Codex, Gemini and a dozen other models for answers in parallel.

The Copilot CLI now supports builtin subagents for parallelizing search and coding tasks within separate context windows. Uniquely, the outer agent can invoke different models. Ask Opus, Codex, Gemini and a dozen other models for answers in parallel.

Evan Boyle

10,602 views • 5 months ago

A deep conversation with Nikolay Savinov, the Gemini long context pre-training co-lead… We go from the basics to what is needed to scale to infinite context to long context best practices for devs:

A deep conversation with Nikolay Savinov, the Gemini long context pre-training co-lead… We go from the basics to what is needed to scale to infinite context to long context best practices for devs:

Logan Kilpatrick

252,322 views • 1 year ago

Hoping your coding agents could understand you and adapt to your preferences? Meet TOM-SWE, our new framework for coding agents that don’t just write code, but model the user's mind persistently (ranging from general preferences to small details) arxiv: ❓Motivation: Most coding agents today can plan, edit, run, and test code. But they still fail at a key part of real-world development, understanding the user! Underspecified, shifting, or context-dependent instructions can easily break them. You must have those moments when coding agents were running for 10 minutes and ended up producing things largely misaligned. (1/)

Hoping your coding agents could understand you and adapt to your preferences? Meet TOM-SWE, our new framework for coding agents that don’t just write code, but model the user's mind persistently (ranging from general preferences to small details) arxiv: ❓Motivation: Most coding agents today can plan, edit, run, and test code. But they still fail at a key part of real-world development, understanding the user! Underspecified, shifting, or context-dependent instructions can easily break them. You must have those moments when coding agents were running for 10 minutes and ended up producing things largely misaligned. (1/)

Xuhui Zhou

39,728 views • 7 months ago

∞ Introducing World #1 Infinite Agent - infinite steps, infinite context, infinite output on cloud. See for yourself:

∞ Introducing World #1 Infinite Agent - infinite steps, infinite context, infinite output on cloud. See for yourself:

Flowith

446,943 views • 1 year ago

Introducing Repo2RLEnv Turn any repository into runnable, verifiable coding environments built from real PRs and commits for coding-agent evaluation or RL training > uv pip install repo2rlenv

Introducing Repo2RLEnv Turn any repository into runnable, verifiable coding environments built from real PRs and commits for coding-agent evaluation or RL training > uv pip install repo2rlenv

Adithya S K

66,475 views • 24 days ago

Behavioral Foundation Models (BFMs) trained with RL are secretly more powerful than we think. BFM’s directly output a policy believed to be near-optimal given any reward function. Our new work shows that they can actually do much better:

Behavioral Foundation Models (BFMs) trained with RL are secretly more powerful than we think. BFM’s directly output a policy believed to be near-optimal given any reward function. Our new work shows that they can actually do much better:

Harshit Sikchi

44,182 views • 1 year ago

📹 Context Engineering & Coding Agents with Cursor From OpenAI DevDay

📹 Context Engineering & Coding Agents with Cursor From OpenAI DevDay

Lee Robinson

159,074 views • 8 months ago

For a long time, software was limited by how fast people could write code, and how good that code was. As models have improved, that constraint has largely disappeared. Now the bottleneck is access: what surfaces can your agents actually reach? Those interaction layers sit on top of coding agents, the kernel that turns prompts into real-world impact. With Notion's custom agents, we pushed this further. They adapt to your work style as you collaborate with them, using the same deterministic logic that powers coding agents. Simon Last sarah guo

For a long time, software was limited by how fast people could write code, and how good that code was. As models have improved, that constraint has largely disappeared. Now the bottleneck is access: what surfaces can your agents actually reach? Those interaction layers sit on top of coding agents, the kernel that turns prompts into real-world impact. With Notion's custom agents, we pushed this further. They adapt to your work style as you collaborate with them, using the same deterministic logic that powers coding agents. Simon Last sarah guo

Notion Developers

25,065 views • 2 months ago

shadow is an open-source background coding agent with a real-time interface and codebase context system here's a breakdown of how it works ⬇️

shadow is an open-source background coding agent with a real-time interface and codebase context system here's a breakdown of how it works ⬇️

ishaan dey

21,582 views • 10 months ago

AI coding without systems thinking is just tech debt on speedrun. Delty (@delty_ai) is an AI Staff Engineer for your team. With deep expertise, it designs software systems, evaluates tradeoffs and makes AI coding agents smarter with your engineering context. Congrats on the launch, Lalit Kundu and Catherine!

AI coding without systems thinking is just tech debt on speedrun. Delty (@delty_ai) is an AI Staff Engineer for your team. With deep expertise, it designs software systems, evaluates tradeoffs and makes AI coding agents smarter with your engineering context. Congrats on the launch, Lalit Kundu and Catherine!

Y Combinator

73,297 views • 1 year ago

Introducing Agentkit: A production-ready, model-agnostic framework for building AI agents with infinite onchain and web2 functionality, powered by @coinbaseDev and Based Agents on Base were just the beginning. its time to change the way we interact onchain. 🧵

Introducing Agentkit: A production-ready, model-agnostic framework for building AI agents with infinite onchain and web2 functionality, powered by @coinbaseDev and Based Agents on Base were just the beginning. its time to change the way we interact onchain. 🧵

lincoln.base.eth

409,263 views • 1 year ago