Few Shot Prompting

topic on 2 shows · 6 statements across 4 episodes

Latent Space No Priors

6 statements about Few Shot Prompting, every show

Chase: Few-shot prompting works better than detailed instructions for agent trajectories
“I'm pretty bullish on it, to be honest, for a few reasons. Like, one, I think it can maybe help for more complex things, but then also, two, like, it's a form of prompting, and prompting is just Communicating with the model what you want it to do. And sometime…”
Harrison Chase Sep 27, 2024 ▶ 1:03:16 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
LATENT SPACE Assertion Supported
Schulhoff: Few-Shot Exemplar Order Can Shift Model Accuracy From 0% to 90%
“How you order your exemplars in the prompt is super important. And we've seen this move accuracy from like zero percent to 90%, like Zero to state of the art on some tasks, which is just ridiculous”
Sander Schulhoff Sep 20, 2024 ▶ 22:22 The Ultimate Guide to Prompting - with Sander Schulhoff from LearnPrompting.org
LATENT SPACE Assertion Supported
Schulhoff: LLMs Rely More on Prompt Structure Than Exemplar Labels
“There are a number of papers which have found that the label of the exemplar doesn't really matter, and the model reads the exemplars and cares more about structure than label.”
Sander Schulhoff Sep 20, 2024 ▶ 26:41 The Ultimate Guide to Prompting - with Sander Schulhoff from LearnPrompting.org
Swix: Few-Shot Prompting Is Not Always Superior to Zero-Shot Templates
“Few shot is not necessarily better than zero shot is, which is counterintuitive because you're working harder.”
Shawn Wang Sep 20, 2024 ▶ 28:19 The Ultimate Guide to Prompting - with Sander Schulhoff from LearnPrompting.org
LATENT SPACE Disclosure
Carlini never uses few-shot prompting for personal language model queries
“I don't because usually when I want the answer, I just, I want to get the answer.”
Nicholas Carlini Aug 28, 2024 ▶ 45:57 Personal benchmarks vs HumanEval - with Nicholas Carlini of DeepMind
NO PRIORS Insight
Chase: Few-shot prompting effectively builds procedural memory for AI agents
“So on the procedural side, I think the main thing that we see people doing and that we think is pretty effective is few-shot prompting and maybe fine-tuning for how to use for how to use tools, because that's basically what it comes down to. What's the right w…”
Harrison Chase Mar 28, 2024 ▶ 8:22 No Priors Ep. 57 | With LangChain CEO and Co-Founder Harrison Chase

← every entity, every show

Made with StarZero

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.