Delving into The Prompt Report, with Sander Schulhoff of LearnPrompting.org

Nathan welcomes back Sander Schulhoff, creator of LearnPrompting.org, to discuss the recently released Prompt Report. In this episode of The Cognitive Revolution, we explore the current state of prompting techniques for large language models, covering best practices, challenges, and emerging trends in AI. Join us for an in-depth conversation on the future of prompt engineering and its implications for AI development.
Apply to join over 400 founders and execs in the Turpentine Network: hmplogxqz0y.typeform.com/to/J...
RECOMMENDED PODCAST:
Byrne Hobart, the writer of The Diff, is revered in Silicon Valley. You can get an hour with him each week. See for yourself how his thinking can upgrade yours.
Spotify: open.spotify.com/show/6rANlV5...
Apple: podcasts.apple.com/us/podcast...
SPONSORS:
Oracle Cloud Infrastructure (OCI) is a single platform for your infrastructure, database, application development, and AI needs. OCI has four to eight times the bandwidth of other clouds; offers one consistent price, and nobody does data better than Oracle. If you want to do more and spend less, take a free test drive of OCI at oracle.com/cognitive
The Brave search API can be used to assemble a data set to train your AI models and help with retrieval augmentation at the time of inference. All while remaining affordable with developer first pricing, integrating the Brave search API into your workflow translates to more ethical data sourcing and more human representative data sets. Try the Brave search API for free for up to 2000 queries per month at bit.ly/BraveTCR
Omneky is an omnichannel creative generation platform that lets you launch hundreds of thousands of ad iterations that actually work customized across all platforms, with a click of a button. Omneky combines generative AI and real-time advertising data. Mention "Cog Rev" for 10% off www.omneky.com/
Head to Squad to access global engineering without the headache and at a fraction of the cost: head to choosesquad.com/ and mention “Turpentine” to skip the waitlist.
CHAPTERS:
(00:00:00) About the Show
(00:02:35) Sander Schulhoff, Learn Prompting
(00:05:22) Hack-a-Prompt updates
(00:12:39) The team behind the report
(00:18:40) Sponsors: Oracle | Brave
(00:20:48) The tech side of things
(00:22:24) The taxonomy
(00:25:06) Diamonds in the rough
(00:28:32) Few-shot prompting design decisions
(00:34:01) Sponsors: Omneky | Squad
(00:35:48) Example vs. Exemplar
(00:38:24) Exemplar Format
(00:42:04) Elaborate Instructions
(00:44:22) Variation in Performance
(00:46:46) Prompt Robustness
(00:50:54) RLHF vs. Base Models
(00:52:42) How to improve your prompts
(00:55:22) Ensembling
(00:58:41) Bootstrapping into fine-tuning
(01:02:04) Multimodal
(01:07:41) Agents
(01:09:47) Automated prompt engineering
(01:12:35) Productizing learn prompting
(01:14:28) Lessons from leading a team
(01:16:00) Outro

[@devbites77]

Delve, delve. Word of the year!

[@nathanlabenz]

iykyk

[@manslaughterinc.9135]

40:00 Sander is saying the Q: A: format is for exemplars. I think you misunderstood.

[@IlEagle.1G]

Delve with me, friend.

[@BrianMosleyUK]

Shall we delve into how we weave a rich tapestry and foster americanized cliches?

[@mcmitch57]

We still do not even know if it's flesh out or flush out

[@noelwos1071]

The comparison of AI with domestication in the video is deeply wrong.and thisis why ruclips.net/video/o5fd_6RjDdc/видео.htmlsi=tW1JJmg4OgQJbqg1