PROMPT ENGINEERING

–

03 November 2022 21h12

@dust4ai takes some work to wrap your head around, but it's very powerful — gives a collapsible tree UI for representing k-shot example datasets, prompt templates, and prompt chaining with intermediate JS code. Replaces a lot of code around prompt APIs. http://
dust.tt

Langchain Python Package Implements Advanced LLM Prompting Techniques

By

–

03 November 2022 20h12

@hwchase17
's Python package Langchain implements and lets you easily compose many published LLM prompting techniques. Implements self-asking, web search, REPL math, and several of my own prompts.

EveryPrompt Extends Playground for Prompt Variables and API Integration

By

–

03 November 2022 20h12

@everyprompt extends Playground in a similar way: Putting variables in prompts and giving you a single button to go from prompt to API. Has nice developer-oriented touches in the UI too — e.g. displaying invisible chars as ghosts. https://
everyprompt.com

Humanloop Playground enhances prompts and API endpoint creation for AI

By

–

03 November 2022 20h12

First up, @humanloop has a Playground that brings variable interpolation to prompts and lets you turn them into API endpoints. Once you're deployed, it also lets you collect past generations along with user behavioral feedback for fine-tunes. https://
humanloop.com

→ View original post on X — @karpathy

Using StableBoost to refine image generation through visual selection

By

@karpathy

–

02 November 2022 22h44

e.g. I used stableboost for this earlier tweet 🙂 – the prompt by itself gives bad, too diverse, not amazing results, but once I generated ~1000 I could visually narrow in on the composition I liked. Not sure how I'd get that by tuning the prompt alone

2 November 2022

Visual Iteration Over Text Prompts for AI Image Generation

By

@karpathy

–

02 November 2022 22h35

Sometimes it's difficult to put the look&feel of what you're after into text. You end up re-rolling results over and over again, looking for the needle in a haystack. stableboost flips it around – you create a large haystack of variations, then narrow in on the needle visually.

→ View original post on X — @karpathy

2 November 2022

GPT-3 Requires Chain-of-Thought for Problem Solving, Paper Analysis

By

–

02 November 2022 19h37

Regardless how a human would do it, GPT-3 needs chain-of-thought to perform on these problems. Only skimmed the paper, but I don't see a specific deficit in ToM vs. known inability to do multi-hop inference without CoT.