Загрузка видео...

Не удалось загрузить видео

На главную

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's profile picture

Adithya S K

13,764 subscribers

66,982 просмотров • 2 месяцев назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Introducing Wingman: a model-agnostic, MCP-native coding assistant. You can now get the Claude Code experience with ANY model for FREE. - MIT-licensed - MCP-native - Model-agnostic > pip install wingman-cli
2:00

Introducing Wingman: a model-agnostic, MCP-native coding assistant. You can now get the Claude Code experience with ANY model for FREE. - MIT-licensed - MCP-native - Model-agnostic > pip install wingman-cli

Dedalus Labs

38,700 просмотров • 7 месяцев назад

Introducing Bottleneck: Code review for hyper engineers - Faster loads. Github is slow and crashes. Bottleneck is desktop native, uses smart caches, never lags. - Built for coding agents. Group PRs by prompt, agent, or contributor. - Superhuman shortcuts. Keybinds for everything Looking for testers! Waitlist or/DM me
1:34

Introducing Bottleneck: Code review for hyper engineers - Faster loads. Github is slow and crashes. Bottleneck is desktop native, uses smart caches, never lags. - Built for coding agents. Group PRs by prompt, agent, or contributor. - Superhuman shortcuts. Keybinds for everything Looking for testers! Waitlist or/DM me

Alex Reibman 🖇️

71,146 просмотров • 11 месяцев назад

Scaling embodied AI starts with automating the environments. Introducing SimWorld Studio: a self-evolving factory for endless interactive 3D environments where agents act, fail, and learn. With coding-agent + embodied-agent co-evolution, navigation success improves from 50% → 90%. 1/
1:36

Scaling embodied AI starts with automating the environments. Introducing SimWorld Studio: a self-evolving factory for endless interactive 3D environments where agents act, fail, and learn. With coding-agent + embodied-agent co-evolution, navigation success improves from 50% → 90%. 1/

Lianhui Qin

59,270 просмотров • 3 месяцев назад

Introducing W&B Skills for coding agents! Watch us install the skill, point it at a live fine-tuning project with thousands of traces and RL training runs, then query it all from the terminal in seconds. Also works with W&B Weave to pull in your agent traces and spot failures.
3:16

Introducing W&B Skills for coding agents! Watch us install the skill, point it at a live fine-tuning project with thousands of traces and RL training runs, then query it all from the terminal in seconds. Also works with W&B Weave to pull in your agent traces and spot failures.

Weights & Biases

261,540 просмотров • 5 месяцев назад

Introducing the Skills Manager in AI Assistant. Easily install skills from a curated collection focused on coding workflows, verified for safety, and use them in codex and claude agent across different projects. Check the thread for examples, or watch the walkthrough:
1:19

Introducing the Skills Manager in AI Assistant. Easily install skills from a curated collection focused on coding workflows, verified for safety, and use them in codex and claude agent across different projects. Check the thread for examples, or watch the walkthrough:

JetBrains

11,912 просмотров • 3 месяцев назад

Open-ended coding training data may no longer be the bottleneck: AI can scale open-ended tasks—and even outperform human-expert curation. FrontierCS team is releasing FrontierSmith: a system for synthesizing open-ended coding problems at scale. Starting from closed-ended coding tasks, FrontierSmith mutates, filters, and builds runnable optimization environments for long-horizon coding agents. In our experiments, FrontierSmith data trains stronger models than human-curated open-ended data on FrontierCS and ALE-bench. Blog: Paper: Code: Model:
0:56

Open-ended coding training data may no longer be the bottleneck: AI can scale open-ended tasks—and even outperform human-expert curation. FrontierCS team is releasing FrontierSmith: a system for synthesizing open-ended coding problems at scale. Starting from closed-ended coding tasks, FrontierSmith mutates, filters, and builds runnable optimization environments for long-horizon coding agents. In our experiments, FrontierSmith data trains stronger models than human-curated open-ended data on FrontierCS and ALE-bench. Blog: Paper: Code: Model:

Qiuyang Mang

95,481 просмотров • 3 месяцев назад

Paths: the plugin marketplace for onchain agents Install or publish skills, scripts, and trading strategies to extend your agent’s capabilities Use them in our new trading UX, or in your preferred coding agent Secured by Builder + Staker collateral Built on Base
1:02

Paths: the plugin marketplace for onchain agents Install or publish skills, scripts, and trading strategies to extend your agent’s capabilities Use them in our new trading UX, or in your preferred coding agent Secured by Builder + Staker collateral Built on Base

Wayfinder Foundation 🧭

16,641 просмотров • 2 месяцев назад

Move from idea to production-ready agents in hours with the updated ADK and our AI-native coding skills. Use Agent Studio to convert prompts into functional agents, or leverage Agent Garden's pre-built blueprints to jumpstart your multi-agent systems →
1:09

Move from idea to production-ready agents in hours with the updated ADK and our AI-native coding skills. Use Agent Studio to convert prompts into functional agents, or leverage Agent Garden's pre-built blueprints to jumpstart your multi-agent systems →

Google Cloud Tech

22,488 просмотров • 3 месяцев назад

Introducing: Browser Use CLI 3.0 🌐 Turn any model into a SOTA browser agent > Direct CDP control via browser-harness > Run on cloud browsers or real Chrome > 6× smaller, fewer tokens Try it now 🔗↓
0:30

Introducing: Browser Use CLI 3.0 🌐 Turn any model into a SOTA browser agent > Direct CDP control via browser-harness > Run on cloud browsers or real Chrome > 6× smaller, fewer tokens Try it now 🔗↓

Browser Use

140,209 просмотров • 1 месяц назад

Most engineering metrics are broken. They count PRs and commits, not real impact. Developer 360 from CodeAnt AI (YC W24) changes that. Built on top of their AI code reviews, it shows what’s actually being built, fixed, or improved— with real visibility into engineering work.
0:57

Most engineering metrics are broken. They count PRs and commits, not real impact. Developer 360 from CodeAnt AI (YC W24) changes that. Built on top of their AI code reviews, it shows what’s actually being built, fixed, or improved— with real visibility into engineering work.

Y Combinator

16,430 просмотров • 10 месяцев назад

🤖Coding agents like Claude Code are already game changers for digital tasks in 2026. But what if they could write code to build physical worlds? 🏙️ Imagine going from a single line of prompt → a controllable, interactive simulated world. Such environments could open new frontiers for game creation, RL training, large-scale world simulation, and studying complex social reasoning. Our SimWorld agent coding team is working toward releasing a platform that lets anyone build their own virtual worlds. Stay tuned.
0:27

🤖Coding agents like Claude Code are already game changers for digital tasks in 2026. But what if they could write code to build physical worlds? 🏙️ Imagine going from a single line of prompt → a controllable, interactive simulated world. Such environments could open new frontiers for game creation, RL training, large-scale world simulation, and studying complex social reasoning. Our SimWorld agent coding team is working toward releasing a platform that lets anyone build their own virtual worlds. Stay tuned.

Lianhui Qin

10,647 просмотров • 5 месяцев назад

Coding agents that actually get better the more your team uses them. Introducing Hivemind: continual learning for AI coding agents. Hivemind turns the traces from every agent your team runs (Claude Code, Codex, Cursor, Hermes, OpenClaw, Pi) into reusable skills, then pushes those skills across all of them. All on your cloud storage. Now with SkillOpt built in, your skills get trained: +19.1 points of accuracy in Claude Code, +24.8 in Codex, best or tied on all 52 setups tested. Open source, one line install.
0:38

Coding agents that actually get better the more your team uses them. Introducing Hivemind: continual learning for AI coding agents. Hivemind turns the traces from every agent your team runs (Claude Code, Codex, Cursor, Hermes, OpenClaw, Pi) into reusable skills, then pushes those skills across all of them. All on your cloud storage. Now with SkillOpt built in, your skills get trained: +19.1 points of accuracy in Claude Code, +24.8 in Codex, best or tied on all 52 setups tested. Open source, one line install.

Davit

421,439 просмотров • 2 месяцев назад

BFL Skills Packaged FLUX into a single install command for agents. Install once. Your coding agent handles the rest - model selection, prompting, API integration. All built in. Sub-second generation and editing with [klein]. Highest quality with [max]. Text rendering with [flex] Works in Claude Code, Cursor, and other IDEs. > npx skills add black-forest-labs/skills
0:20

BFL Skills Packaged FLUX into a single install command for agents. Install once. Your coding agent handles the rest - model selection, prompting, API integration. All built in. Sub-second generation and editing with [klein]. Highest quality with [max]. Text rendering with [flex] Works in Claude Code, Cursor, and other IDEs. > npx skills add black-forest-labs/skills

Black Forest Labs

35,593 просмотров • 6 месяцев назад

We’re introducing Canvas and welcoming Audio Overview to the Google Gemini today. Turn docs, slides + Deep Research reports into podcasts with Audio Overview. Or create a doc or coding project with Canvas – it spins up prototypes super fast and you can edit with Gemini in real-time.
0:30

We’re introducing Canvas and welcoming Audio Overview to the Google Gemini today. Turn docs, slides + Deep Research reports into podcasts with Audio Overview. Or create a doc or coding project with Canvas – it spins up prototypes super fast and you can edit with Gemini in real-time.

Sundar Pichai

384,189 просмотров • 1 год назад

Today I built this voice agent while on a call with it Introducing /this-needs-a-call - it's a slash command to start a phone call - grill or be grilled by the voice agent in realtime - your coding agent listens in on the call via MCP and works while you talk for hours
6:15

Today I built this voice agent while on a call with it Introducing /this-needs-a-call - it's a slash command to start a phone call - grill or be grilled by the voice agent in realtime - your coding agent listens in on the call via MCP and works while you talk for hours

jacob paris ▲

32,463 просмотров • 1 месяц назад

Introducing arkenOS — an autonomous training gym that takes any RL agent from a goal to a proven, deployable policy. We are automating complex RL research, enabling high-velocity training and rigorous, diverse environment design and testing right on your local hardware. Out of the box. Our bet is simple: The future of AI will be built by companies giving millions of agents millions of simulated environments to adapt and learn cause and effect in, and survive. This continuous, autonomous selection will create a digital Cambrian explosion, distilling evolutionary trial and error into a foundational specialized intuition.
0:39

Introducing arkenOS — an autonomous training gym that takes any RL agent from a goal to a proven, deployable policy. We are automating complex RL research, enabling high-velocity training and rigorous, diverse environment design and testing right on your local hardware. Out of the box. Our bet is simple: The future of AI will be built by companies giving millions of agents millions of simulated environments to adapt and learn cause and effect in, and survive. This continuous, autonomous selection will create a digital Cambrian explosion, distilling evolutionary trial and error into a foundational specialized intuition.

Dev Shah

17,206 просмотров • 1 месяц назад

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.
0:53

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

121,766 просмотров • 3 месяцев назад

MiniMax M2.1 is officially live🚀 Built for real-world coding and AI-native organizations — from vibe builds to serious workflows. A SOTA 10B-activated OSS coding & agent model, scoring 72.5% on SWE-multilingual and 88.6% on our newly open-sourced VIBE-bench, exceeding leading closed-source models like Gemini 3 Pro and Claude 4.5 Sonnet. The most powerful OSS model for the agentic era is here.
0:54

MiniMax M2.1 is officially live🚀 Built for real-world coding and AI-native organizations — from vibe builds to serious workflows. A SOTA 10B-activated OSS coding & agent model, scoring 72.5% on SWE-multilingual and 88.6% on our newly open-sourced VIBE-bench, exceeding leading closed-source models like Gemini 3 Pro and Claude 4.5 Sonnet. The most powerful OSS model for the agentic era is here.

MiniMax (official)

1,074,233 просмотров • 8 месяцев назад

Introducing SWE-grep and SWE-grep-mini: Cognition’s model family for fast agentic search at >2,800 TPS. Surface the right files to your coding agent 20x faster. Now rolling out gradually to Windsurf users via the Fast Context subagent – or try it in our new playground!
0:28

Introducing SWE-grep and SWE-grep-mini: Cognition’s model family for fast agentic search at >2,800 TPS. Surface the right files to your coding agent 20x faster. Now rolling out gradually to Windsurf users via the Fast Context subagent – or try it in our new playground!

Cognition

663,797 просмотров • 10 месяцев назад