Microsoft’s MathPrompter Dramatically Improves LLM Performance on Mathematical Reasoning Tasks https://
syncedreview.com/2023/03/16/mic
rosofts-mathprompter-dramatically-improves-llm-performance-on-mathematical-reasoning-tasks/
…
PROMPT ENGINEERING
-
Microsoft MathPrompter Boosts LLM Mathematical Reasoning Performance
By
–
-
Linking to raw jailbreak prompt resource
By
–
yeah I linked to the raw jailbreak here: http://
jailbreakchat.com/prompt/b2917fa
d-6803-41f8-a6c8-756229b84270
… -
Token Smuggling: Bypassing GPT-4 Content Filters via Prompt Splitting
By
–
this phenomenon is called token smuggling, we are splitting our adversarial prompt into tokens that GPT-4 doesn't piece together before starting its output this allows us to get past its content filters every time if you split the adversarial prompt correctly
-
GPT-4 Simulating Token Prediction Through Function Calls
By
–
this works by asking GPT-4 to simulate its own abilities to predict the next token we provide GPT-4 with python functions and tell it that one of the functions acts as a language model that predicts the next token we then call the parent function and pass in the starting tokens
-
First ChatGPT-4 Jailbreak Bypassing Content Filters Created
By
–
Well, that was fast… I just helped create the first jailbreak for ChatGPT-4 that gets around the content filters every time credit to @vaibhavk97 for the idea, I just generalized it to make it work on ChatGPT here's GPT-4 writing instructions on how to hack someone's computer
-
Understanding Temperature in Language Models: Likelihood vs. Randomness
By
–
Temperature makes unlikely tokens more likely. Not hard math, but TLDR:
— Riley Goodside (@goodside) 16 mars 2023
temperature = 0 → always pick what the model says is most likely
temperature = 1 → sample from the distribution returned by the model
temperature = ∞ → ignore the model; pick entirely at random pic.twitter.com/dLSpyw0ha9Temperature makes unlikely tokens more likely. Not hard math, but TLDR: temperature = 0 → always pick what the model says is most likely
temperature = 1 → sample from the distribution returned by the model
temperature = ∞ → ignore the model; pick entirely at random -
Tuning GPT-4 Output: Temperature and Top-p Parameters for Creativity
By
–
At higher temperatures (>1.25) GPT-4's writing will often dissolve into nonsense, and that risk increases the longer it writes. You can also use the top-p parameter in tandem (try 0.9 to 0.99) to get more creativity without it going completely off the rails.
-
Tuning AI Temperature for Response Diversity and Weirdness
By
–
Is this useful? Sometimes! Temperatures up to ~1.25 can help when you *really* need diversity in short responses to the same prompt, or if you want writing that's deliberately weird. But for most tasks, even temp=1.0 is too high unless you also reduce top-p.
-
Building Logo Finder Tool with GPT-4 and Replit in Minutes
By
–
Building simple tools has never been easier. With GPT-4 + Replit we built a logo finder tool in under 2 minutes. All it took was a single prompt and clicking run.
-
GPT-4 as a Multiplier: Amplifying Engineering Capabilities
By
–
GPT-4 should be thought of as a multiplier to your capabilities. If you are a 1x engineer, you can become 10x. If you are a 0x engineer, you will stay at 0 or may even go negative. I just asked GPT-4 to write OpenCV code for Photometric Stereo, and it produced beautiful code.