Nebuly
@nebuly_aiUser analytics and insights from LLM conversations.
Similar User
@FOIAFeed
@electronjs
@RamaswmySridhar
@Tim_Dettmers
@YiTayML
@sirbayes
@_lewtun
@npew
@JerryWeiAI
@jpineau1
@wightmanr
@bingxu_
@tkipf
@shaneguML
@drjwrae
Introducing a new, user-centric framework for evaluating and developing LLM-based products. nebuly.com/blog/next-big-…
LLMs are changing Conversational Analytics from both ends: 1. We are having conversations with LLMs. 💬 2. Analyzing conversations is best done by LLMs specifically built for this task. 🤖 More on our latest post: nebuly.com/blog/conversat…
📈 Trends for LLM User Intentions and User Feedback. You can now see if a particular type of user feedback or user intent is trending up or down. Quickly understand changes in user experience over a period of your choice.
🆕 Blog Post: LLM Evaluation Methods: 🤠 Human-as-a-Judge vs. 🤖 LLM-as-a-Judge! Dive into these two perspectives in LLM evaluation. Learn about user feedback, implicit evaluations, and automated assessments. Read more: nebuly.com/blog/llm-evalu…
🚀 Our latest product update: Easily track custom User Intent and User Warnings in your LLM conversations! Stay on top of what matters most to you and your customers. youtu.be/P_ZeCnofBp4
Launch early & collect feedback. 💯
You cannot reliably say an AI product with 100% accuracy over 10 users will be even 50% accurate over 1000. This is why it’s critical to launch AI products early. To start tuning and improving based on real input diversity.
Top 5 fastest growing JavaScript repos dev.to/wasp/top-5-fas… Thanks @hot_town @nebuly_ai is proud to be on that list.
Categorizing interactions is crucial for analyzing user experiences in LLMs. Segmentation reveals which topics generate high-quality engagements and which are prone to user warnings. Our latest product update introduces Global Filters to help you analyze a category .
More technical details on the new Meta Llama 3 models announced today. 🦙🧵
Claude 3 Opus now available on @awscloud
Research? Strategy? Automation? Look to your next #generativeAI copilot. ☁️💡 Now on #AmazonBedrock, Claude 3 Opus lets you plan & execute complex actions, run hypothesis generation, & forecast market trends with the highest level of #AI intelligence. 🖇️ go.aws/3vJO1jf
How are companies using large language models (LLMs) today, and what parallels can we draw to the early web in 1995? Nebuly’s Co-Founder Julien Roux weighs in on the LLM trends nebuly.com/the-year-of-ll…
United States Trends
- 1. Dayton 5.435 posts
- 2. Chargers 57 B posts
- 3. Seth Trimble N/A
- 4. Drake 11,1 B posts
- 5. Quentin Johnston 6.061 posts
- 6. Kerr 7.933 posts
- 7. Ravens 68,6 B posts
- 8. #WWERaw 69,4 B posts
- 9. Canada 420 B posts
- 10. Lamar 184 B posts
- 11. Herbert 20 B posts
- 12. Maui 16 B posts
- 13. Jalen Washington N/A
- 14. Cadeau 9.621 posts
- 15. Kofi 16,7 B posts
- 16. Heels 22,7 B posts
- 17. RJ Davis N/A
- 18. Kings 54,6 B posts
- 19. Derrick Henry 9.385 posts
- 20. Cory Alexander N/A
Who to follow
-
FOIA // FEED
@FOIAFeed -
Electron
@electronjs -
sridhar
@RamaswmySridhar -
Tim Dettmers
@Tim_Dettmers -
Yi Tay
@YiTayML -
Kevin Patrick Murphy
@sirbayes -
Lewis Tunstall
@_lewtun -
Peter Welinder
@npew -
Jerry Wei
@JerryWeiAI -
Joelle Pineau
@jpineau1 -
Ross Wightman
@wightmanr -
Bing Xu
@bingxu_ -
Thomas Kipf
@tkipf -
Shane Gu
@shaneguML -
Jack Rae
@drjwrae
Something went wrong.
Something went wrong.