Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Doomscroll Detector
This talk demonstrates a low-code AI tool that detects doomscrolling and generates concise discussion points summarizing overlooked content using Groq and llama 3.1 70B models.
Catches you in the act of doomscrolling. When it does, summarizes all the things you glossed over into a series of discussion points for you to actually spend time to think about.
Chrome extension employs scroll tracking and content summarization for digital well-being.
- GroqGroq delivers ultra-fast AI inference using its custom-built Language Processing Unit (LPU) to accelerate Large Language Models (LLMs) at scale.Groq specializes in high-speed AI inference, leveraging its proprietary Language Processing Unit (LPU) Inference Engine: a chip specifically architected for generative AI and LLMs. The LPU's unique dataflow architecture bypasses the memory and compute bottlenecks of traditional GPUs, delivering consistent, ultra-low-latency performance and superior energy efficiency. This technology, accessible via the GroqCloud platform or on-premise GroqRack clusters, enables real-time application deployment for demanding enterprise customers. Founded in 2016 by former Google engineers (including a lead designer of the TPU), Groq is setting the new standard for real-time AI compute.
- Llama 3 70BLlama 3 70B: Meta's flagship 70-billion parameter model, delivering state-of-the-art performance for complex reasoning and instruction-following.This is Llama 3 70B, Meta's premier open-source large language model. It features 70 billion parameters, pre-trained on a massive 15-trillion token dataset for superior language understanding. The model uses an optimized transformer architecture, including Grouped-Query Attention (GQA), ensuring high-performance, scalable inference. Released in April 2024, the instruction-tuned version immediately set new industry standards: it outperformed models like Gemini Pro 1.5 and Claude 3 Sonnet on key benchmarks. Llama 3 70B is built for demanding commercial and research use cases (advanced chat, coding, sophisticated NLG).
- Doomscroll DetectorWe deploy real-time behavioral analytics to detect compulsive consumption of negative content, initiating a hard block to restore user focus.This system is a critical intervention tool: it uses a proprietary algorithm to identify 'doomscrolling' patterns (excessive, rapid scrolling on news or social platforms) and deploys immediate countermeasures. The current Chrome extension, for example, offers customizable blocked sites and scroll distance limits (Version 0.4.1 details). Our objective is non-negotiable: reduce user anxiety, improve sleep quality, and boost daily productivity. We provide the boundary; the user reclaims control over their digital consumption.
Related projects
Using NLP/ML and cloud functions to automate peer groups.
New York City
Learn how to automate peer group creation using NLP/ML on GCP Cloud Functions and Firestore. This talk showcases…
Big Swarm
New York City
The session demonstrates how to design, coordinate, and monitor large-scale multi‑agent systems, covering architecture, communication patterns, and practical…
Searching Millions of Tables with AI
New York City
Explore how to search millions of web tables semantically and by joinability. This talk shares technical details on…
Friends & Fables
New York City
This talk explains how AI is integrated into an RPG platform, revealing the technical processes behind game mechanics…
AI Startup Scout
Seattle
A sub‑agent scans Hacker News, flags potential startup stories, adds founder data from external sources, and generates concise…
Fluffy - An answer-engine for public repos & open-source libraries.
New York City
Learn how Fluffy, an answer-engine for public code, helps developers overcome documentation gaps, fix specific bugs, and quickly…