Technological Citizens

Write something

Pinned

Jan 24 in

Hello, and a warm welcome to all our new members! We're thrilled to have you join our vibrant community of thinkers who are actively trying to decipher the implications of our AI era. As we embark on this exciting journey, we encourage you to dive into our starter courses – they're designed to set you up for success and make your experience here even more rewarding. Don't forget to mark each module as done to track your progress. Our community thrives on interaction, so feel free to post, comment, and engage as you go along. If you need any guidance or have questions, our community is here to support you. Start by checking out our two starter courses to get a feel for how things work around here. It's a great way to get familiar with all the features and opportunities that await you. Let's make this a journey to remember, filled with learning, growth, and, most importantly, adventure! Welcome aboard! 🚀

Benjamin Bush

Apr 14 in

General discussion

🏗️ Luxury Hotel Construction on Altman Dr 🏗️

Posted By: OpenConstruction Rating: 4.7/5 🌕🌕🌕🌕🌗 Posted: 2 months ago Pay: 💰💰💰* [Tap to track] Project progress: 28% complete Estimated completion: 9/18/2038 Current workers: 327/500 max Injury risk: Low (0.03 injuries/hour) [Tap for arbitration agreement] Unskilled laborers only. Union workers may not apply. Minimum 2 hours work per session required. Massive luxury hotel construction project: - Demolition of existing structures - Pouring foundation and erecting steel framework - Installing plumbing, electrical, and HVAC systems - Constructing and finishing 500 guest rooms and suites - Building common areas, including lobby, restaurants, and fitness center - Landscaping and exterior finishing Class 3 AR headset required for step-by-step AI guidance throughout the project. [ Shop TaskRabbit approved AR headsets now! ] Tap [Stream Live] to watch the construction progress in real-time. Tap [Let's Go!] and an autonomous vehicle will dispatched to your location for transportation to 1337 Altman Dr. *Pay is dynamically calculated based on factors such as project progress, injury risk, worker supply, and your TaskRabbit worker rating.

Benjamin Bush

Apr 7 in

General discussion

"Multi-Candidate Needle Prompting" for large context LLMs (Gemini 1.5)

Gemini 1.5's groundbreaking 1M token context window is a remarkable advancement in LLMs, providing capabilities unlike any other currently available model. With its 1M context window, Gemini 1.5 can ingest the equivalent of 10 Harry Potter books in one go. However, this enormous context window is not without its limitations. In my experience, Gemini 1.5 often struggles to retrieve the most relevant information from the vast amount of contextual data it has access to. The "Needle in a Haystack" benchmark is a well-known challenge for LLMs, which tests their ability to find specific information within a large corpus of text. This benchmark is particularly relevant for models with large context windows, as they must efficiently search through vast amounts of data to locate the most pertinent information. To address this issue, I have developed a novel prompting technique that I call "Multi-Candidate Needle Prompting." This approach aims to improve the model's ability to accurately retrieve key information from within its large context window. The technique involves prompting the LLM to identify 10 relevant sentences from different parts of the input text, and then asking it to consider which of these sentences (i.e. candidate needles) is the most pertinent to the question at hand before providing the final answer. This process bears some resemblance to Retrieval Augmented Generation (RAG), but the key difference is that the entire process is carried out by the LLM itself, without relying on a separate retrieval mechanism. By prompting the model to consider multiple relevant sentences from various parts of the text, "Multi-Candidate Needle Prompting" promotes a more thorough search of the available information and minimizes the chances of overlooking crucial details. Moreover, requiring the model to explicitly write out the relevant sentences serves as a form of intermediate reasoning, providing insights into the model's thought process. The attached screenshot anecdotally demonstrates the effectiveness of my approach.