In this episode of The Lightcone, we talk with Mukund and Madhav Jha, the founders of Emergent - an AI platform that lets anyone build and ship production-ready software. In just eight months, users have created more than 7 million apps on Emergent, with the number doubling in just the last 45 days. We discuss how they built one of the most powerful AI coding agents, why they focused on non-technical users and what it's like building for a global audience from India. Apply to Y Combinator: https://www.ycomb ...

GitHub Copilot just closed a huge gap for the adoption of coding agents.The technology/tooling today is quite mature. But the adoption is still stuck, not because of capability, but because there's no easy and standardized way to govern these agents at scale.GitHub addresses this.The GitHub Copilot coding agent is embedded directly into GitHub's platform and works across VS Code, JetBrains, Eclipse, and Xcode.This means you can assign an issue to GitHub Copilot in the same way you'd assign it to an engineer ...

I feel like when I'm using quad code, it's like, oh, I feel like I'm flying through the code. >> When it's in your CLI, this thing can debug nested delayed jobs like five levels in and figure out what the bug was and then write a test for it and it never happens again. This is insane. I think everyone who's experimenting with this stuff on like a hobbyist level or at like a very small startup, they're just pushing the coding agents as far as they can go because it's like you don't really have time to figure ...

If you found it insightful, reshare it with your network.Find me → @_avichawlaEvery day, I share tutorials and insights on DS, ML, LLMs, and RAGs. https://t.co/z0r9ujOGF3Avi Chawla (@_avichawla):Finally, devs can vibe code all the way to production!There's a frustrating pattern that every developer using AI coding agents has experienced.The Agent builds a beautiful frontend in mins. It sets up working API routes and lays out the component architecture.But then it https://t.co/AbAaO4nibM ...

Zhipu AI just went public and its new coding tool is so popular they’re already limiting access. The most surprising part? The demand isn't just coming from China… its coming from American developers. Baseten’s Tuhin Srivastava joins us to discuss the infrastructure shift and whether American moats are evaporating. ...

People use traces from the start to just tell what's going on under the hood. And it's way more impactful in agents than in single LLM applications because in single LM applications, you get some bad response from the LLM. You know exactly what your prompt is. You know exactly what the context that goes in is because that's determined by code and then you get something out. In agents, they're running and and and repeating and so you don't actually know what the context at step 14 will be because there's 13 ...

Core Insights - A senior Google engineer revealed that Anthropic's Claude Code was able to replicate a system that her team had spent a year developing in just one hour, highlighting the rapid advancements in AI programming capabilities [1][3][6]. Group 1: AI Programming Capabilities - The engineer, Jaana Dogan, described how she used Claude Code to generate a system by simply providing a brief description, which closely resembled the work done by her team over the past year [3][4]. - Dogan emphasized that the industry is still in a phase of exploration regarding language models, which are expected to continue evolving and becoming more powerful [5][6]. - The rapid advancements in AI programming capabilities have led to a significant increase in quality and efficiency, surpassing previous expectations [6][7]. Group 2: Industry Reactions and Perspectives - There is a polarized reaction within the developer community regarding coding agents, with some viewing it as hype while others recognize its potential [4][9]. - Dogan's public acknowledgment of a competitor's product has sparked discussions about the implications of AI on the engineering profession, with some suggesting it could signal a technological turning point [10][11]. - Critics argue that while AI can generate code quickly, the real challenge lies in problem definition and alignment within teams, which AI does not address [12][13]. Group 3: Google and Anthropic Relationship - Google has invested approximately $3 billion in Anthropic and holds about 14% of its shares, indicating a strong partnership between the two companies [17][20]. - A significant agreement between Google and Anthropic involves Google providing up to 1 million TPU units, valued at hundreds of billions, to enhance AI capabilities [20]. - Dogan noted that the industry is not a zero-sum game, and recognizing the achievements of competitors can drive further innovation [21].

Coding agents are becoming one of the most active areas in applied AI, yet many teams keep rebuilding fragile infrastructure every time models or providers change. We believe there is a better way. By anchoring on a stable abstraction layer like Codex, we can stop worrying about harness rewrites and focus on the parts of the stack that create lasting value. We treat models as interchangeable sub-agents, plug into shared primitives, and let upstream improvements flow through without breaking products. This l ...

RT eric zakariasson (@ericzakariasson)turns out, senior engineers accept more agent output than juniors. this is because:- they write higher-signal prompts with tighter spec and minimal ambiguity- they decompose work into agent-compatible units- they have stronger priors for correctness, making review faster and more accurate- juniors generate plenty but lack the verification heuristics to confidently greenlight outputshows that coding agents amplify existing engineering skill, not replace it ...

Hi there, this is Christian from Lchain. If you build with coding agents like cursor, you probably recognize this. The first few turns with the agents are great.But then as you keep continuing talking to the agent in the same thread, the quality slides, the decision get more fuzzy and the overall code quality drops and then cursor drops this system line context summarized. That's the moment you know you've crossed the context boundary line. So why is summarization such a big deal for context engineering.Eve ...