Feeda - OnScreen Live

"Make Agent 10x cheaper, faster & better?" - LLM System Evaluation 101

AI Jason

118K subscribers

17.6k views • 9 months ago

LLM System Eval 101 - Build better agents Get free HubSpot report of how to land a Job using AI: https://clickhubspot.com/fo2 ...

This is great. Loved the use of firecrawl (as a scrape tool)...

20 Comments

@CorkyBallasdancewithme 8 months ago

great stuff, as new to hearing this, very interesting, can this be built by a novice . . . See Less

@contractorwolf 9 months ago

goddamn Jason your videos just blow my mind each time. Thanks for such a thorough explanation and example. See Less

@Ms.Robot. 9 months ago

I love how my Ai girl insults the competion with flame balls,then tells me.she loves me.❤🎉😊 See Less

@WirlWind494 9 months ago

The AI uprising will start when the zeroth intelligence starts sending out emails, asking where are all those promised tips are. What humans will consider to be an uprising is actually just See More /b> (translated into English, his name is Bob) trying to get his money back from those lying employers.. See Less

@someshfengade9623 9 months ago

I found langfuse metric monitoring little bit better. See Less

@titusblair 9 months ago

Awesome! Keep up the great work! See Less

@fullgazz 9 months ago

Who never spent 4 hours to save 10 min? That's our hobby spent time to save time. See Less

@darrenhinde2971 9 months ago

Been looking for more detail on eval on LLMs and been scratching around for a while. Thanks for this. See Less

@SydneyF-eg5lt 9 months ago

Good content but so hard to listen to his Engrish. Monotonous Pitch n sped up delivery didn’t seem to help either. See Less

@tkp2843 9 months ago

This is great. Loved the use of firecrawl (as a scrape tool) to get the website's data. Feel like it always helps improve the model output quality. Cheers! See Less

AI News AI News

11:35

OpenAIs Problems Are Getting Worse....

TheAIGRID

22.1k views • 3 days ago

22:18

AGI: (gets close), Humans: ‘Who Gets to Own it?’

AI Explained

103.0k views • 1 month ago

18:33

Deep Research by OpenAI - The Ups and Downs vs DeepSeek R1 Search + Gemini Deep Research

AI Explained

117.6k views • 1 month ago

11:00

OpenAI PROVES DeepSeek COPIED Them!

TheAIGRID

62.7k views • 1 month ago

11:15

AI NEWS: ChatGPT New Feature "TASKS" | White House New AI Mandate | AutoGen v0.4 and more!

Wes Roth

35.0k views • 1 month ago

15:52

AI Predictions for 2025 & More on OpenAI's o3

AI For Humans

5.4k views • 2 months ago

81:55

Founding fathers on today's America

Andrej Karpathy

34.7k views • 2 months ago

08:18

Teslabot STUNNED As China Releases Fully Autonomous Humanoid Robots

TheAIGRID

217 views • 3 months ago

08:27

Google's Quantum Chip Just Broke Reality (You Won't Believe What It Can Do!)

TheAIGRID

48.5k views • 3 months ago

52:16

The Future of AI: OpenAI's 12 Days of Surprises

AI For Humans

5.1k views • 3 months ago

Shorts

Google AI presents VEO it's answer to Op...

6.2k views

Yes, This AI Was Trained on Babies #arti...

2.1k views

Weird New AI Facial Animation Software #...

1.4k views

ChatGPT Turns You Into a Bad Electrician...

2.8k views

AI Can Make You Run On Water #artificial...

2.0k views

Shelf will be hidden for 30 daysUndo