Riley Goodside: The Art and Craft of Prompt Engineering

4 snips

Jun 1, 2023

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

Three Eras Of Language Models

Riley describes three eras: pre-trained LMs, instruction tuning, and RLHF, each improving how models follow user intent.
Instruction tuning made models follow commands and RLHF further reduced harmful hallucinations by learning human preferences.

INSIGHT

Why RLHF Changed Model Behavior

RLHF trains a preference model from human rankings and fine-tunes the LM to prefer human-approved outputs.
This process made models more truthful and less prone to confidently fabricating facts compared with earlier instruction-tuned models.

INSIGHT

Instruction Tuning Isn’t Just Safety

Instruction tuning was framed as safety work but primarily taught models to follow instructions and assume tasks should be completed.
That capability enhancement made models more useful, not just more socially constrained.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

In episode 75 of The Gradient Podcast, Daniel Bashir speaks to Riley Goodside.

Riley is a Staff Prompt Engineer at Scale AI. Riley began posting GPT-3 prompt examples and screenshot demonstrations in 2022. He previously worked as a data scientist at OkCupid, Grindr, and CopyAI.

Have suggestions for future podcast guests (or other feedback)? Let us know here or reach us at editor@thegradient.pub

Subscribe to The Gradient Podcast: Apple Podcasts | Spotify | Pocket Casts | RSSFollow The Gradient on Twitter

Outline:

* (00:00) Intro

* (01:37) Riley’s journey to becoming the first Staff Prompt Enginer

* (02:00) data science background in online dating industry

* (02:15) Sabbatical + catching up on LLM progress

* (04:00) AI Dungeon and first taste of GPT-3

* (05:10) Developing on codex, ideas about integrating codex with Jupyter Notebooks, start of posting on Twitter

* (08:30) “LLM ethnography”

* (09:12) The history of prompt engineering: in-context learning, Reinforcement Learning from Human Feedback (RLHF)

* (10:20) Models used to be harder to talk to

* (10:45) The three eras

* (10:45) 1 - Pre-trained LM era—simple next-word predictors

* (12:54) 2 - Instruction tuning

* (16:13) 3 - RLHF and overcoming instruction tuning’s limitations

* (19:24) Prompting as subtractive sculpting, prompting and AI safety

* (21:17) Riley on RLHF and safety

* (24:55) Riley’s most interesting experiments and observations

* (25:50) Mode collapse in RLHF models

* (29:24) Prompting models with very long instructions

* (33:13) Explorations with regular expressions, chain-of-thought prompting styles

* (36:32) Theories of in-context learning and prompting, why certain prompts work well

* (42:20) Riley’s advice for writing better prompts

* (49:02) Debates over prompt engineering as a career, relevance of prompt engineers

* (58:55) Outro

Links:

* Riley’s Twitter and LinkedIn

* Talk: LLM Prompt Engineering and RLHF: History and Techniques

Get full access to The Gradient at thegradientpub.substack.com/subscribe