Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Confident AI helps developers build the best version of their LLM application by automating evaluation, prompt iteration, and live testing. Their framework is open source and runs 700k evals every day. Congrats on the launch, Jeffrey 🐬 confident-ai.com + @KritinV78426!

ycombinator's profile picture

Y Combinator

1,611,832 subscribers

17,469 görüntüleme • 1 yıl önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

5 Yorum

Justin Jiang profil fotoğrafı
Justin Jiang1 yıl önce

@jeffr_yyy @KritinV78426 let’s go!!

Rickyticky Bobbywobbin profil fotoğrafı
Rickyticky Bobbywobbin1 yıl önce

INTRODUCING: Agentic Security - LLM Security Scanner! 🔍 🔑 Features: Scans for prompt injections, jailbreaking & more. Provides detailed reports & options to customize attack rules. 🔗access the GitHub Link ↓

Abhivendra Singh profil fotoğrafı
Abhivendra Singh1 yıl önce

@jeffr_yyy @KritinV78426 Exciting times ahead, @ycombinator. Open-source frameworks like Confident AI are game-changers, pushing the boundaries of what developers can achieve. This is the kind of innovation that fuels the future of education and AI. Let's keep the momentum going.

jorvarea profil fotoğrafı
jorvarea1 yıl önce

@jeffr_yyy @KritinV78426 That is so cool. I'm looking forward to trying it out

Theron Rogers profil fotoğrafı
Theron Rogers1 yıl önce

@jeffr_yyy @KritinV78426 This is great! I cobbled together a script for very basic validation of multiple prompts very early in dabbling with LLMs for a localization project for my app and wondered about how cool it would be to have something like this.

Benzer Videolar

YC S24's Patched (YC S24) helps developers build AI workflows to automate code reviews, docs, and patches. Patched is open-source and works with your chosen LLM, giving you complete control and privacy. Congrats on the launch, Asankhaya Sharma and Rohan Sood!
0:31

YC S24's Patched (YC S24) helps developers build AI workflows to automate code reviews, docs, and patches. Patched is open-source and works with your chosen LLM, giving you complete control and privacy. Congrats on the launch, Asankhaya Sharma and Rohan Sood!

Y Combinator

19,998 görüntüleme • 1 yıl önce

Fulcrum (Muzafar Bhai) is an agentic debugger for AI systems. It helps developers fix their RL environments and improve their agents. Congrats on the launch, Uzay and @kaivuhariharan!
0:36

Fulcrum (Muzafar Bhai) is an agentic debugger for AI systems. It helps developers fix their RL environments and improve their agents. Congrats on the launch, Uzay and @kaivuhariharan!

Y Combinator

14,892 görüntüleme • 11 ay önce

Plexe AI (Plexe AI) is building an open-source agent to build ML models from a prompt. Their agent is already helping companies go from idea to deployed models 10x faster. Congrats on the launch, Vaibhav Dubey and Marcello De Bernardi!
0:46

Plexe AI (Plexe AI) is building an open-source agent to build ML models from a prompt. Their agent is already helping companies go from idea to deployed models 10x faster. Congrats on the launch, Vaibhav Dubey and Marcello De Bernardi!

Y Combinator

55,872 görüntüleme • 1 yıl önce

.Tensorfuse (YC W24) is a testing and evaluation platform for LLM apps. They make it easy for developers to experiment with various prompts, models, and retrieval methods to find the most effective one. Congrats on the launch agam & samagra14!
0:54

.Tensorfuse (YC W24) is a testing and evaluation platform for LLM apps. They make it easy for developers to experiment with various prompts, models, and retrieval methods to find the most effective one. Congrats on the launch agam & samagra14!

Y Combinator

14,195 görüntüleme • 2 yıl önce

Cactus ( runs AI on smartphones. They help developers deploy local, private, and offline AI cross-platform in their apps. Congrats on the launch, Roman Shemet & Henry Ndubuaku!
0:59

Cactus ( runs AI on smartphones. They help developers deploy local, private, and offline AI cross-platform in their apps. Congrats on the launch, Roman Shemet & Henry Ndubuaku!

Y Combinator

14,926 görüntüleme • 1 yıl önce

.OpenSpec (YC W26) is building the open-source spec framework for coding agents. It helps devs generate software specifications that evolve with their codebase, making their agents reliable enough to take on larger, more complex work. Congrats on the launch, Tabish!
2:14

.OpenSpec (YC W26) is building the open-source spec framework for coding agents. It helps devs generate software specifications that evolve with their codebase, making their agents reliable enough to take on larger, more complex work. Congrats on the launch, Tabish!

Y Combinator

26,476 görüntüleme • 5 ay önce

𝜃 ZeroEval helps you build reliable AI agents through evaluations that learn from their mistakes and get better over time. Congrats on the launch, seb and xtamales!
0:46

𝜃 ZeroEval helps you build reliable AI agents through evaluations that learn from their mistakes and get better over time. Congrats on the launch, seb and xtamales!

Y Combinator

23,816 görüntüleme • 11 ay önce

Tropir (@tropir_) is the AI that builds better AIs. It kills traditional LLM observability tools by tracing where your pipeline breaks— then it fixes, reruns, does evals, and iterates on it for you. Congrats on the launch, Aarush and Ayush!
1:12

Tropir (@tropir_) is the AI that builds better AIs. It kills traditional LLM observability tools by tracing where your pipeline breaks— then it fixes, reruns, does evals, and iterates on it for you. Congrats on the launch, Aarush and Ayush!

Y Combinator

38,871 görüntüleme • 1 yıl önce

YC W24's nuvi.dev is a testing and simulation stack to harden LLM-based applications. AI teams leverage Relari to stress test mission-critical GenAI use cases with modular evaluation and synthetic data. Congrats on the launch, Yi Zhang and Pasquale!
0:45

YC W24's nuvi.dev is a testing and simulation stack to harden LLM-based applications. AI teams leverage Relari to stress test mission-critical GenAI use cases with modular evaluation and synthetic data. Congrats on the launch, Yi Zhang and Pasquale!

Y Combinator

14,312 görüntüleme • 2 yıl önce

AI is insecure by default. The open secret is that most AI apps launch with serious flaws. It takes MORE time to secure these apps than it does to build them. I learned this firsthand from shipping LLM agents to 200M users at Discord and supporting LLM evals for hundreds of companies. It doesn’t have to be this way. Today, we’re launching promptfoo, an open-source company that helps find and fix vulnerabilities in AI powered apps before they ship, and announcing a $5M seed round led by a16z.
1:01

AI is insecure by default. The open secret is that most AI apps launch with serious flaws. It takes MORE time to secure these apps than it does to build them. I learned this firsthand from shipping LLM agents to 200M users at Discord and supporting LLM evals for hundreds of companies. It doesn’t have to be this way. Today, we’re launching promptfoo, an open-source company that helps find and fix vulnerabilities in AI powered apps before they ship, and announcing a $5M seed round led by a16z.

Ian Webster

28,779 görüntüleme • 2 yıl önce

Golf (Golf (YC X25)) is an open-source platform for shipping production-ready MCP servers. Build a server with Golf's OSS framework with auth, telemetry, and debugging included. Deploy with one click, and observe through their hosted platform. Start shipping at Congrats on the launch, Wojciech Błaszak and Antoni Gmitruk!
0:51

Golf (Golf (YC X25)) is an open-source platform for shipping production-ready MCP servers. Build a server with Golf's OSS framework with auth, telemetry, and debugging included. Deploy with one click, and observe through their hosted platform. Start shipping at Congrats on the launch, Wojciech Błaszak and Antoni Gmitruk!

Y Combinator

31,036 görüntüleme • 1 yıl önce

Leeroo (Leeroo) builds trainable AI agents that keep learning—and get better at their job— every day. Congrats on the launch, Alireza Mohammadshahi, Majid, and Arshad!
2:08

Leeroo (Leeroo) builds trainable AI agents that keep learning—and get better at their job— every day. Congrats on the launch, Alireza Mohammadshahi, Majid, and Arshad!

Y Combinator

16,953 görüntüleme • 1 yıl önce

🍐PearAI (YC F24) is an open source AI code editor with a curated inventory of the best AI tools, natively integrated for effortless AI-powered coding. They're building a flexible framework for the AI coding tech stack under a unified UX: Congrats on the launch, 🟢 nang 🟢 and @CodeFryingPan!
1:45

🍐PearAI (YC F24) is an open source AI code editor with a curated inventory of the best AI tools, natively integrated for effortless AI-powered coding. They're building a flexible framework for the AI coding tech stack under a unified UX: Congrats on the launch, 🟢 nang 🟢 and @CodeFryingPan!

Y Combinator

53,960 görüntüleme • 1 yıl önce

Besimple (Besimple AI) helps you spin up your own data annotation platform in 60 seconds, so you can build robust evaluation and training data without the hassle of looking at complex spreadsheets. Congrats on the launch, Yi Zhong & Bill Wang!
0:38

Besimple (Besimple AI) helps you spin up your own data annotation platform in 60 seconds, so you can build robust evaluation and training data without the hassle of looking at complex spreadsheets. Congrats on the launch, Yi Zhong & Bill Wang!

Y Combinator

17,163 görüntüleme • 1 yıl önce

.Armature (YC P26) helps companies monitor and optimize how AI agents experience their products. It runs real agent workflows and improves your MCP or CLI. Reinventing the Agent Experience! Congrats on the launch, Theo (YC P26) and Louis Scremin!
1:09

.Armature (YC P26) helps companies monitor and optimize how AI agents experience their products. It runs real agent workflows and improves your MCP or CLI. Reinventing the Agent Experience! Congrats on the launch, Theo (YC P26) and Louis Scremin!

Y Combinator

11,605 görüntüleme • 2 ay önce

Announcing CodeArena! Two LLMs build the same app, vote on which one did best, and see a live leaderboard of the best open source coding LLMs! 100% free & open source. Powered by Together AI & available today:
0:36

Announcing CodeArena! Two LLMs build the same app, vote on which one did best, and see a live leaderboard of the best open source coding LLMs! 100% free & open source. Powered by Together AI & available today:

Hassan

22,378 görüntüleme • 1 yıl önce

✨Spur (YC S24) is building an AI QA Engineer that helps users test their websites with natural language. Congrats on the launch, Sneha Sivakumar and Anushka!
1:07

✨Spur (YC S24) is building an AI QA Engineer that helps users test their websites with natural language. Congrats on the launch, Sneha Sivakumar and Anushka!

Y Combinator

36,249 görüntüleme • 1 yıl önce

Aster (Aster) is building the autonomous research lab. They run thousands of AI agents in parallel to achieve 1000x speedups in autonomous research. Their lab just set a world record on ProteinGym in 30 minutes—and now they're automating open-ended research. Congrats on the launch, Emmett Bicker!
1:10

Aster (Aster) is building the autonomous research lab. They run thousands of AI agents in parallel to achieve 1000x speedups in autonomous research. Their lab just set a world record on ProteinGym in 30 minutes—and now they're automating open-ended research. Congrats on the launch, Emmett Bicker!

Y Combinator

367,113 görüntüleme • 1 ay önce