Latitude的封面图片
Latitude

Latitude

软件开发

San Francisco,CA 1,734 位关注者

Latitude is the open-source prompt engineering platform to build, evaluate, and refine your prompts with AI.

关于我们

Latitude is the open-source prompt engineering platform to build, evaluate, and refine your prompts with AI.

网站
https://latitude.so/
所属行业
软件开发
规模
2-10 人
总部
San Francisco,CA
类型
私人持股
创立
2022

地点

Latitude员工

动态

  • Latitude转发了

    查看Cesar Miguelanez的档案

    CEO at Latitude.so — The prompt engineering platform for teams

    Lovely video by Santiago Valdarrama showcasing Latitude ??

    查看Santiago Valdarrama的档案

    Computer scientist and writer. I teach hard-core Machine Learning at ml.school.

    This is next-level smart: An open-source platform that evaluates your prompts and automatically refines them based on the results. Of course, it feels obvious after you see it: ? You write a prompt ? The system evaluates it across different scenarios ? Based on the results, it refines it to improve results I recorded a quick video to show you how it works. It's pretty cool stuff! Here are some of the problems and best practices for teams building AI applications: 1. Testing your prompts manually doesn't scale 2. Prompts should not be spread throughout the codebase 3. Non-technical people need easy access to your prompts 4. Prompts can always use a version history to track changes 5. Monitoring the performance of prompts overtime is critical Evaluating the prompts is what keeps me up at night from this list. Of all the conversations I've had with companies and people building AI applications, this is the area that's causing the most pain. Testing a prompt is difficult. Think about how you'd test the response of a model subjectively. What do you account for, "tone," "objectivity," "completeness," "creativity," "readability," etc.? Last week, I met the developers behind Latitude, an open-source prompt engineering platform trying to solve all of these issues. You can try the platform in two ways: ? You can self-host the platform. Free and open-source. ? If you want to try their online product, their free tier is huge. Here is the link:?https://lnkd.in/eDwKk7AE Thanks to the Latitude team for collaborating with me on this post, and congratulations on going live with their product!

  • Latitude转发了

    ?? Really excited to finally launch Latitude and share what we've been working on! If you’re curious to learn more or want to support us, check it out on Product Hunt and give us an upvote if it resonates with you. https://lnkd.in/eNwsqYmr

    查看Cesar Miguelanez的档案

    CEO at Latitude.so — The prompt engineering platform for teams

    We’re excited to announce that Latitude is live on Product Hunt! ?? Latitude is the open-source prompt engineering platform to build, evaluate, and refine your prompts with AI. Proud to be building this alongside Gerard Clos and the amazing team. We’d greatly appreciate your support! ???https://lnkd.in/egitH3-4

  • 查看Latitude的组织主页

    1,734 位关注者

    We're so back! ??

    查看Cesar Miguelanez的档案

    CEO at Latitude.so — The prompt engineering platform for teams

    We’re excited to announce that Latitude is live on Product Hunt! ?? Latitude is the open-source prompt engineering platform to build, evaluate, and refine your prompts with AI. Proud to be building this alongside Gerard Clos and the amazing team. We’d greatly appreciate your support! ???https://lnkd.in/egitH3-4

  • Latitude转发了

    Just tested a new feature I've been working on, and honestly... it’s wild. ?? Latitude is already familiar with your prompts and the metrics that interest you. It even knows how it’s performing. This means prompts can now actually improve by themselves without any manual intervention! It’s like it learns on the fly and improves in ways that really matter. I didn’t expect it to be this smooth, but here we are. It’s crazy to see how far we’ve come with AI.

  • Latitude转发了

    查看Cesar Miguelanez的档案

    CEO at Latitude.so — The prompt engineering platform for teams

    So excited to share this. We're working on automatic prompt refinement. This is how it works: 1. Create your prompt in Latitude 2. Evaluate it with a dataset (synthetic or not) 3. Click Refine 4. Our AI will suggest improvements to your prompt based on your evaluation results 5. Evaluate again and see the improved results Feels like magic. Launching next week! ??

  • Latitude转发了

    查看Cesar Miguelanez的档案

    CEO at Latitude.so — The prompt engineering platform for teams

    My advice to people building with AI: You only need prompts. I've met a lot of people making AI pipelines unnecessarily complicated with very little return. Fine-tuning, RAG, self-hosting models… You're not going to fix your product by throwing technology at it. Don't fine-tune. Don't build complex RAG systems. Don't host your own models. You're so worried about the technology that you forgot about your users.

  • Latitude转发了

    查看Cesar Miguelanez的档案

    CEO at Latitude.so — The prompt engineering platform for teams

    If you have LLM features running in production but don’t have an evaluation system in place, you’re not serious about AI. Just now, I was testing a simple prompt manually and thought it was working fine. Then, I ran a batch evaluation through Latitude and discovered it was failing in 18% of cases. Without the evaluation system, I would've never caught that.

  • Latitude转发了

    查看Cesar Miguelanez的档案

    CEO at Latitude.so — The prompt engineering platform for teams

    PSA: After months of hard work, we’re officially granting access to the first people on our waitlist! The opening will be progressive to make sure we deliver the best experience possible: - If you’re in, I’m curious about your first steps with Latitude — ping me if you have any questions! - If you haven’t received any email yet, don’t worry, you’ll get it in the upcoming days. - If you’re not on the waitlist yet, you can join right now ?? https://ai.latitude.so/ - Or if you can’t wait and you need access immediately, let me know in the comments and I’ll take care of you!

相似主页

查看职位