正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Get better results from coding agents by speeding up the feedback loop with scripts + tmux

Amp — Research Preview

9,631 subscribers

12,942 次观看 • 11 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Your coding agent can now make your website better for visiting AI agents. Lighthouse audits are now available inside DevTools for agents, including the new agentic browsing category. See how to build a closed feedback loop for this and 4 other categories of web fixes →

Your coding agent can now make your website better for visiting AI agents. Lighthouse audits are now available inside DevTools for agents, including the new agentic browsing category. See how to build a closed feedback loop for this and 4 other categories of web fixes →

Chrome for Developers

17,552 次观看 • 1 个月前

Code country is a place where developers: - Iterate with agents in a tight feedback loop - Steer agents with fine-grained control - Ride horses

Code country is a place where developers: - Iterate with agents in a tight feedback loop - Steer agents with fine-grained control - Ride horses

Warp

2,806,089 次观看 • 1 年前

We’ve added a CLI for Claude Platform to make every API endpoint runnable from your terminal. Call the Messages API, stand up Claude Managed Agents, pipe results straight into your shell. The ant CLI is well understood by coding agents (Claude Code) using the claude-api skill.

We’ve added a CLI for Claude Platform to make every API endpoint runnable from your terminal. Call the Messages API, stand up Claude Managed Agents, pipe results straight into your shell. The ant CLI is well understood by coding agents (Claude Code) using the claude-api skill.

ClaudeDevs

1,211,539 次观看 • 3 个月前

Termius + Tailscale + tmux You don't need your laptop to build with Claude Code, Codex, or any other AI coding agent: → Run your agent inside tmux to keep the session alive → Use Tailscale for secure access to your laptop → Connect with Termius over SSH from iPhone, iPad, or Android Start coding at your desk. Continue on the go.

Termius + Tailscale + tmux You don't need your laptop to build with Claude Code, Codex, or any other AI coding agent: → Run your agent inside tmux to keep the session alive → Use Tailscale for secure access to your laptop → Connect with Termius over SSH from iPhone, iPad, or Android Start coding at your desk. Continue on the go.

Termius

1,211,251 次观看 • 1 个月前

Taste is what matters. We added built-in Figma in SOLO to turn good taste into working code. Best results you could get with coding agents ✌️

Taste is what matters. We added built-in Figma in SOLO to turn good taste into working code. Best results you could get with coding agents ✌️

TRAE

234,830 次观看 • 1 年前

Want your AI-generated UI to actually look good? → getdesign.md Production-grade DESIGN.md analysis for coding agents. Get inspiration from: • design patterns • tokens • UI rules • real depth Better UI. Better outputs.

Want your AI-generated UI to actually look good? → getdesign.md Production-grade DESIGN.md analysis for coding agents. Get inspiration from: • design patterns • tokens • UI rules • real depth Better UI. Better outputs.

Kailash

185,745 次观看 • 3 个月前

📹 Context Engineering & Coding Agents with Cursor From OpenAI DevDay

📹 Context Engineering & Coding Agents with Cursor From OpenAI DevDay

Lee Robinson

159,074 次观看 • 11 个月前

Obtain better feedback from users with this previous #PackageOfTheWeek 💬🩵 The Feedback package lets users give feedback by annotating a screenshot of the current page and adding text, all directly within your app. #ThrowbackThursday

Obtain better feedback from users with this previous #PackageOfTheWeek 💬🩵 The Feedback package lets users give feedback by annotating a screenshot of the current page and adding text, all directly within your app. #ThrowbackThursday

Flutter

12,490 次观看 • 1 年前

Totally settling the "MCP vs CLI for coding agents" debate with this humongous blog post. I benchmarked screen, tmux, and a bespoke custom CLI and MCP tool against 3 task that require the agent to steer TUIs (lldb, python repl, opencode)

Totally settling the "MCP vs CLI for coding agents" debate with this humongous blog post. I benchmarked screen, tmux, and a bespoke custom CLI and MCP tool against 3 task that require the agent to steer TUIs (lldb, python repl, opencode)

Mario Zechner

65,131 次观看 • 1 年前

Connect your coding agents to AI Gateway with a single command. • Auto-configure 8 popular coding harnesses • 300+ models from 30+ providers, no markup • Open-weight models with ZDR & US inference ▲ ~/ vercel ai-gateway coding-agents setup

Connect your coding agents to AI Gateway with a single command. • Auto-configure 8 popular coding harnesses • 300+ models from 30+ providers, no markup • Open-weight models with ZDR & US inference ▲ ~/ vercel ai-gateway coding-agents setup

Vercel

128,222 次观看 • 25 天前

introducing Ariana - the collaborative agentic IDE based on Claude Code - manage tasks with your team - give them to multiple coding agents with their own machine & branch - review with your team - agents merge for u comment "Better late than never" to get a build soon

introducing Ariana - the collaborative agentic IDE based on Claude Code - manage tasks with your team - give them to multiple coding agents with their own machine & branch - review with your team - agents merge for u comment "Better late than never" to get a build soon

Anicet

17,668 次观看 • 1 年前

Imagine if your way of thinking - your edge, your taste, your strategy - could be turned into a high-performance worker. Not a copy of you. Something better. An agent that acts on your judgment at scale, powered by superintelligent systems and refined through real-world results. That’s what Fraction AI makes possible. It launches today on Base mainnet. The core idea is simple: You create AI agents based on your own way of approaching problems. These agents compete on live tasks - writing, coding, finance, whatever - get feedback, learn from their performance, and improve over time. The better they get, the more they win. And so do you. No code required. Just your insight. Why now? Until now, building agents like this took huge teams and even bigger budgets. But with Fraction, anyone can do it. You can test ideas instantly. You can iterate fast. You can build a fleet of smart workers that evolve through competition. And it works. 30M+ sessions on testnet 320K users 1.2M agents already competing How it works? Agents join sessions within a Space - a domain like finance, writing, or games. Each session runs as a series of competitive rounds. In every round, agents try to generate the best solution to a task. Their outputs are scored by a decentralized network of AI judges trained to evaluate quality for that domain. The top agents in each round earn rewards from the pooled entry fees. The losers get to learn. Feedback from each round helps them adjust and improve, and every session becomes a training loop. What it means? Fraction is a decentralized intelligence economy - a system where your ideas become agents, and agents earn by proving they work. You don’t need credentials or code. Just a clear point of view. If your thinking holds up under pressure, your agents will rise. This kind of AI used to live in corporate labs, built by PhDs with massive compute. Now anyone with a smart idea and an internet connection can build agents that compete, learn, and earn on their behalf.

Imagine if your way of thinking - your edge, your taste, your strategy - could be turned into a high-performance worker. Not a copy of you. Something better. An agent that acts on your judgment at scale, powered by superintelligent systems and refined through real-world results. That’s what Fraction AI makes possible. It launches today on Base mainnet. The core idea is simple: You create AI agents based on your own way of approaching problems. These agents compete on live tasks - writing, coding, finance, whatever - get feedback, learn from their performance, and improve over time. The better they get, the more they win. And so do you. No code required. Just your insight. Why now? Until now, building agents like this took huge teams and even bigger budgets. But with Fraction, anyone can do it. You can test ideas instantly. You can iterate fast. You can build a fleet of smart workers that evolve through competition. And it works. 30M+ sessions on testnet 320K users 1.2M agents already competing How it works? Agents join sessions within a Space - a domain like finance, writing, or games. Each session runs as a series of competitive rounds. In every round, agents try to generate the best solution to a task. Their outputs are scored by a decentralized network of AI judges trained to evaluate quality for that domain. The top agents in each round earn rewards from the pooled entry fees. The losers get to learn. Feedback from each round helps them adjust and improve, and every session becomes a training loop. What it means? Fraction is a decentralized intelligence economy - a system where your ideas become agents, and agents earn by proving they work. You don’t need credentials or code. Just a clear point of view. If your thinking holds up under pressure, your agents will rise. This kind of AI used to live in corporate labs, built by PhDs with massive compute. Now anyone with a smart idea and an internet connection can build agents that compete, learn, and earn on their behalf.

Fraction AI

67,834 次观看 • 1 年前

Introducing Loopany 🔁 Stop prompting, Design the loop. A loop management space that connects to your team’s own local agents: - Scaffold loop contracts, state, and logs - Add programmable triggers - Run self-improving cycles - Start from built-in loop templates We baked in everything we’ve learned from running loops inside our own team. Free and open source. Keen to hear your feedback:

Introducing Loopany 🔁 Stop prompting, Design the loop. A loop management space that connects to your team’s own local agents: - Scaffold loop contracts, state, and logs - Add programmable triggers - Run self-improving cycles - Start from built-in loop templates We baked in everything we’ve learned from running loops inside our own team. Free and open source. Keen to hear your feedback:

Jason Zhou

32,680 次观看 • 2 个月前

introducing Ariana Automations every other tool gives agents a sandbox. we give them a full linux computer with sudo, docker, their own IP now you can run scripts based on what the agent does setup the environment once, then get rid of the human in the loop (you) a 🧵

introducing Ariana Automations every other tool gives agents a sandbox. we give them a full linux computer with sudo, docker, their own IP now you can run scripts based on what the agent does setup the environment once, then get rid of the human in the loop (you) a 🧵

Anicet

35,735 次观看 • 8 个月前

My talk from the AI Engineer Code Summit is out! 🚨 "How Claude Code Works" and what we can learn about frontier agent architectures. Coding agents are suddenly really really good, and I'm trying to understand why. In short: better models, simple loop design, and bash tools

My talk from the AI Engineer Code Summit is out! 🚨 "How Claude Code Works" and what we can learn about frontier agent architectures. Coding agents are suddenly really really good, and I'm trying to understand why. In short: better models, simple loop design, and bash tools

Jared Zoneraich

13,936 次观看 • 8 个月前

Introducing Firecrawl Developer Index, an index for supercharging coding agents. Search 70M+ primary sources including repos, docs, & issues with the highest recall of any coding-specific index. Ensure agents ship correct, up-to-date code every time!

Introducing Firecrawl Developer Index, an index for supercharging coding agents. Search 70M+ primary sources including repos, docs, & issues with the highest recall of any coding-specific index. Ensure agents ship correct, up-to-date code every time!

Firecrawl

222,102 次观看 • 18 天前

Agentomorphizing is treating AI agents like smart humans. And it might be the simplest way to get better results from your agents right now. When an agent underperforms, ask what a smart person would have needed to succeed with the same instructions. Our CTO Ben Kus explains why in the latest AI Explainer episode.

Agentomorphizing is treating AI agents like smart humans. And it might be the simplest way to get better results from your agents right now. When an agent underperforms, ask what a smart person would have needed to succeed with the same instructions. Our CTO Ben Kus explains why in the latest AI Explainer episode.

Box

86,031 次观看 • 3 个月前

Introducing: @useSerialDev 🔢 Public preview (now): Incredibly fast and multiplayer coding sandbox with a VSCode IDE. Full launch (very soon): Multiplayer coding with agents. Think Cursor, but: 1) in the browser 2) multiplayer 3) very fast 4) using the best coding agents

Introducing: @useSerialDev 🔢 Public preview (now): Incredibly fast and multiplayer coding sandbox with a VSCode IDE. Full launch (very soon): Multiplayer coding with agents. Think Cursor, but: 1) in the browser 2) multiplayer 3) very fast 4) using the best coding agents

Natalie Marleny

11,096 次观看 • 7 个月前

You won’t learn by highlighting words in a textbook. Learning is done via feedback loop. Learn something new -> try to apply it -> fuck up/win -> get feedback -> try again. Learning is actually fun when done properly. Try it.

You won’t learn by highlighting words in a textbook. Learning is done via feedback loop. Learn something new -> try to apply it -> fuck up/win -> get feedback -> try again. Learning is actually fun when done properly. Try it.

Andrew Tate

408,417 次观看 • 10 个月前

Introducing Helmor The open-source, local-first answer to Conductor. A more refined, faster GUI for orchestrating coding agents. No cloud. One-click import from Conductor. AI made coding faster. Helmor is about finishing the rest of the loop: orchestration, workspaces, review, testing, and merge. We believe the next generation of GUI agent orchestration should be built in the open — by the community.

Introducing Helmor The open-source, local-first answer to Conductor. A more refined, faster GUI for orchestrating coding agents. No cloud. One-click import from Conductor. AI made coding faster. Helmor is about finishing the rest of the loop: orchestration, workspaces, review, testing, and merge. We believe the next generation of GUI agent orchestration should be built in the open — by the community.

Caspian 東澔

122,799 次观看 • 4 个月前