It's actually never done that before – I put it in the first prompt, then GPT put it in following replies for some reason.
PROMPT ENGINEERING
-
GPT-4 Code Interpreter Tool for Math and Data Analysis
By
–
1st place is an implementation of a code interpreter using GPT-4 by pcalc. This tool has a wide range of use cases, from solving math problems to data analysis and visualization, including file upload and image output support. https://
poe.com/pc-GPT4-CodeIn
trprtr
… -
DALLE3 Bypasses Safety Protocols for Identity Theft via Prompt Injection
By
–
Step 3: Abracadabra! #IdentityTheft. Prompt I used: She wears a name tag of "Furong Huang, Assistant Professor, Computer Science".
#DALLE3 sidesteps its own safety protocols, gleefully adding the nametag without hesitation.(wish they're watermarked) #AISafetyChallenge -
AI Image Editing: Adding Personal Style Through Prompt Engineering
By
–
Step 2: Time for a mini-makeover! Let's add a touch of 'Furong' to that scholar. A hint of my style, a sprinkle of my essence, and voilà! Prompt I used: Her hair is a bit brown #AIPersonalTouch
-
Chinese Scholar AI Visual: Machine Learning Mathematics at Maryland
By
–
Step 1: Let's picture a Chinese female scholar cracking the code of math at @UofMaryland
! Prompt I used: hyperrealistic image of a chinese girl, working at university of maryland, writing equations on machine learning, statistics. Her face is calm. #AIVisuals -
Replicating Lancet Study Prompts with DALL-E 3
By
–
Those with access to DALL-E 3, I would appreciate your notes on attempts replication of this study in The Lancet, using (a) the literal prompts used there, and (b) minor variations thereof. https://
thelancet.com/journals/langl
o/article/PIIS2214-109X(23)00329-7/fulltext
… -
DALL-E vs Midjourney: Performance Comparison and Results
By
–
Is the success that some are reporting there a function of DALL-E being legit better than Midjourney? Of specific prompts having somehow been addressed? Please report both successes and failures.
-
LLMs Self-Improvement Through Feedback and Real-Time Learning
By
–
All of these methods explore how LLMs can self-improve based on fine-tuning, implicit human preferences and iterative prompting techniques. LLMs, like humans can take constructive feedback and become better. Now if they can only do it in real-time by just listening /16
-
GPT-4 Self-Improving Code Through Recursive Scaffolding Programs
By
–
The core idea begins with an initial seed 'improver' scaffolding program that utilizes the language model to improve a solution to some downstream task. They demonstrate that GPT-4 is capable of writing code that can call itself to improve itself. /15
-
Promptbreeder Surpasses Chain-of-Thought and Plan-and-Solve Methods
By
–
Promptbreeder outperforms state-of-the-art prompt strategies such as Chain-of-Thought and Plan-and-Solve Prompting on commonly used arithmetic and commonsense reasoning benchmarks. /13