LLMS - AI Dynamics

Mitigating LLM Hallucinations: 7 Practical Tips

By

–

14 October 2023 14h05

Good morning fellow AI enthusiast! This is the second iteration of my new video series for our free course "Training & Fine-Tuning LLMs for Production"! Dive into my favorite LLM-related topic, Hallucinations, with lots of practical tips to mitigate them: https://
open.substack.com/pub/louisbouch
ard/p/7-tips-to-mitigate-hallucinations?r=25qlky&utm_campaign=post&utm_medium=web
…

→ View original post on X — @whats_ai

14 October 2023

AWS Innovate Conference Features Generative AI Tools October

By

@bernardmarr

–

14 October 2023 11h00

#AWSINNOVATE on Oct 19th! Discover cutting-edge ways to revolutionize your applications with #GenerativeAI. Dive deep into Amazon CodeWhisperer, Bedrock, and more! Register now: https://
aws.amazon.com/events/innovat
e-online-conference/every-application/americas/?trk=5056e493-ac56-4384-bbf8-347983cfb2c5&sc_channel=sm
… #AWS #Event #FutureofAI #AmazonBedrock

→ View original post on X — @bernardmarr

14 October 2023

Small LLMs Poised to Outperform State-of-the-Art Models Soon

By

@abhi1thakur

–

14 October 2023 10h50

My bet is on 10-15b param (maybe even smaller) LLM models outperforming all state of the art soon. Everyone will be able to run them locally for free. WDYT?

→ View original post on X — @abhi1thakur

14 October 2023

Targeting LLMs via image for resume keyword stuffing

By

@goodside

–

14 October 2023 10h41

It’s been done for PDF but targeting LLMs that use conventional pdf2txt. Resume use case isn’t new but there’s more you can do with it being an image. The core trick dates back to 1990s keyword stuffing at least.

→ View original post on X — @goodside

14 October 2023

Evolution of AI Prompting Beyond Traditional Engineering

By

@hardmaru

–

14 October 2023 6h12

Tired: Prompt Engineering Wired: Prompt Evolution

→ View original post on X — @hardmaru

14 October 2023

Promptbreeder: Self-Improvement via Prompt Evolution

By

@hardmaru

–

14 October 2023 4h59

Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution Get LLMs to invent their own mutation operators for evolving prompts. Outperforms Chain-of-Thought and Plan-and-Solve and gets SOTA on a bunch of stuff! @chrisantha_f et al. https://
arxiv.org/abs/2309.16797

→ View original post on X — @hardmaru

14 October 2023

Screenshot-style adversarial prompts in GPT-4V system card

By

@goodside

–

14 October 2023 3h58

Screenshot-style multimodal adversarial prompts are discussed a bit in the GPT-4V system card; see fig. 1 in the PDF here: https://
openai.com/research/gpt-4
v-system-card
…

→ View original post on X — @goodside

14 October 2023

ChatGPT Security Threats: Risks and Vulnerabilities Report

By

@bamitav

–

14 October 2023 3h50

ChatGPT can pose security threats: Report https://
financialexpress.com/business/digit
al-transformation-chatgpt-can-pose-security-threats-report-3271320/
… #ChatGPT #GPT4 #GPT #GenerativeAI #GenAI #LLMs #LLM #RCE #ZeroTrust #ZeroDay #cybercrime #hacker #privacy #APT #bot #CISO #DDoS #hacking #phishing #CyberAttack #cybersecurity #Security #infosec #AppSec #CyberSec

→ View original post on X — @bamitav

14 October 2023