# Llama-2 Projects at AI Tinkerers > Canonical HTML: https://aitinkerers.org/technologies/llama-2 > Markdown URL: https://aitinkerers.org/technologies/llama-2.md > Technology record last updated: 2026-02-22T17:01:16Z > Generated: 2026-09-21T04:44:48Z Llama 2 is Meta AI's powerful, openly accessible family of large language models (LLMs), featuring models from 7B to 70B parameters for research and commercial applications. Llama 2 is Meta AI's next-generation LLM family, released for free research and commercial use. The collection includes both pre-trained foundation models and instruction-tuned 'Chat' variants, scaling from 7 billion (7B) up to 70 billion (70B) parameters. Key technical upgrades over Llama 1 involve training on 2 trillion tokens (40% more data) and doubling the context length to 4096 tokens. The Llama-2-chat models were rigorously aligned using Reinforcement Learning from Human Feedback (RLHF), positioning them as a top-tier, openly available option for developers building advanced generative AI solutions. - Official technology site: https://ai.meta.com/llama/ - Public AI Tinkerers demos and talks: 227 - Result page: 1 of 10 ## Recent Public Talks and Demos ### [Self-Improving Agents with Honcho](https://nyc.aitinkerers.org/talks/rsvp_u3mcI_u6ioA) Learn how you can use Honcho to create a stateful agent that learns and improves itself over time. Remove context window and context engineering burdens, let your OpenClaw know what it needs when it needs it. - Event context: 🦞Demo Night: OpenClaw ft Convex — 2026-02-17 — New York City - Public talk page: https://nyc.aitinkerers.org/talks/rsvp_u3mcI_u6ioA ### [Stop Cloud Waste: AI Checks Costs Before Deploy in AWS](https://raleigh.aitinkerers.org/talks/rsvp_MX33E7LzJoM) Ever had your IT team spin up cloud resources that cost way more than expected? I've developed an AI-powered assistant that reviews cloud infrastructure plans before deployment - like having a financial advisor check your shopping cart before checkout. Instead of finding out you spent $10,000 after the fact, teams get instant feedback: "This database is oversized for a dev environment - similar projects in your company use something 5x cheaper" or "You forgot the required cost tags that finance needs for billing." In this 5-minute demo, I'll show: Upload a cloud infrastructure plan (Terraform file) AI analyzes it against your company's cost policies written in plain English Get a breakdown: estimated monthly cost, policy violations, and smart suggestions See how it learns from your organization's past projects to give better recommendations The magic? It understands context - not just "this violates rule 247" but "this looks expensive for what you're building, here's what similar teams did." - Event context: AI Tinkerers Raleigh Meetup — February 11, 2026 — 2026-02-11 — Raleigh - Public talk page: https://raleigh.aitinkerers.org/talks/rsvp_MX33E7LzJoM ### [Should You Obey Your AI Reviewer?](https://brussels.aitinkerers.org/talks/rsvp_3tv20yxQ8mQ) "Code Quality" is a system that posts feedback comments on your pull requests. We'll take a deep dive into how we hide non-determinism caused by LLMs and how we optimize the LLM's accuracy. - Event context: AI Tinkerers Ghent Meetup - February 11 — 2026-02-11 — Brussels - Public talk page: https://brussels.aitinkerers.org/talks/rsvp_3tv20yxQ8mQ ### [AI agents as interface layer for mobile apps](https://tiruchirappalli.aitinkerers.org/talks/rsvp_qrJiLeqgTOo) Mobile interfaces are reaching their limit. More features mean more screens, more taps, and more friction. This talk explores a different direction. AI agents not as assistants bolted onto apps, but as the interface itself. Through a live demo of Kuralit, I show how user intent can bypass traditional UI and directly trigger real actions inside an app. No buttons. No navigation trees. Just intent to execution. This is not about voice for convenience. It is about interface evolution. From visual control to intent-driven software. The goal is to question a simple assumption. If software can understand what a user wants, why does it still wait for clicks? - Event context: AI Tinkerers Trichy: January Meetup & Live Demos — 2026-01-31 — Tiruchirappalli - Public talk page: https://tiruchirappalli.aitinkerers.org/talks/rsvp_qrJiLeqgTOo ### [Violex — I’ll demo my project that enables learning to play the violin in a fun yet professional way, especially for people who have difficulty reading musical notation.](https://eindhoven.aitinkerers.org/talks/rsvp_BcDWQ0V1L38) Violin is a very hard instrument to play. I’ll present my ongoing project called Violex, it is intended to help reading music sheets and mapping them on the instrument in a fun, intuitive and engaging way. The system also records your play and creates an AI/ML based feedback on how well you are performing! I’ll showcase my progress, the technical hurdles and the feedback mechanisms needed for creating an AI powered hardware like this. - Event context: AI Tinkerers – Eindhoven Inaugural Meetup · 22 December 2025 — 2025-12-22 — Eindhoven - Public talk page: https://eindhoven.aitinkerers.org/talks/rsvp_BcDWQ0V1L38 ### [Coding Agents Are Good at Algorithms](https://eindhoven.aitinkerers.org/talks/rsvp_OMCQjnHBa1o) I've been working on a solver for a word game called Strands. Wanting to try out the latest coding agents, I let Claude take a shot at writing an algorithm. I expected a little vibe-coding would get me most of the way there, but the computational complexity proved to be a lot more challenging than I thought. Along the way though, I learned to collaborate with my coding agent in a way that wasn't just a time save, it truly extended my abilities. - Event context: AI Tinkerers – Eindhoven Inaugural Meetup · 22 December 2025 — 2025-12-22 — Eindhoven - Public talk page: https://eindhoven.aitinkerers.org/talks/rsvp_OMCQjnHBa1o ### [Gotchas while building ChatGPT Apps](https://seattle.aitinkerers.org/talks/rsvp_ysWTzBfVe4w) A ChatGPT app that helps you organize your next travel trip. - Event context: The Holiday Science Fair (Hot Cocoa, Cookies, and Demos!) — 2025-12-19 — Seattle - Public talk page: https://seattle.aitinkerers.org/talks/rsvp_ysWTzBfVe4w ### [Stop Generating, Start Understanding: Building a "Diagnosable" ColBERT for Grounded Late-Interaction Reasoning](https://brussels.aitinkerers.org/talks/rsvp_d9B2-FA9J54) In a landscape obsessed with generative tokens, how can we build millisecond-latency reasoning engines that are interpretable by design and debuggable at the token level? In this demo, I will pop the hood on ClinicalEncoder25 to show how we achieve hallucination-free reasoning through the novel Diagnosable ColBERT architecture. I will walk through a live Jupyter notebook to demystify Late-Interaction Retrieval, visualizing the actual tensor operations that preserve token-level geometry instead of squashing documents into single embeddings. We will inspect the raw vector outputs of clinical text and, using my pre-computed ClinicalMap vector database, demonstrate a live debugging loop where we mathematically map specific token vectors back to SnomedCT concepts. You will see how the model connects the dots betwen a patient working at a "car repair shop" and his "lead contamination" to nudge the vector representation of the latter towards "past history of exposure to lead-based paint," proving that deep semantic understanding is possible without generating a single token. - Event context: AI Tinkerers Brussels - December 17 — 2025-12-17 — Brussels - Public talk page: https://brussels.aitinkerers.org/talks/rsvp_d9B2-FA9J54 ### [Shifting Out: Using AI to Translate Across the Organization](https://atlanta.aitinkerers.org/talks/rsvp_ws8aA88TM4Y) I will explores how AI can act as a translation layer across the organization. Not replacing people, but helping teams shift perspective without losing meaning. How to: Translate executive intent into actionable product and engineering scopes Normalize language between product, design, engineering, and marketing Preserve context while shifting between abstraction levels (strategy ↔ tactics ↔ implementation) Reduce “telephone game” loss across async, distributed teams Rather than focusing on prompt tricks or specific models, this talk centers on organizational leverage: where AI creates clarity, where it introduces risk, and how to design workflows that make translation reliable instead of fragile. - Event context: Co-Co-Code & Cocoa: The AI Tinkerers Atlanta Holiday Meetup — 2025-12-16 — Atlanta - Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_ws8aA88TM4Y ### [Automating my own Job](https://bremen.aitinkerers.org/talks/rsvp_299EfBd2mus) how i combine llms, smolagents, chats and live rendering of ui components into a hybrid interface to collaborative work together with ai agents on critical tasks - Event context: AI Tinkerers Bremen — 2025-12-10 — Bremen - Public talk page: https://bremen.aitinkerers.org/talks/rsvp_299EfBd2mus ### [Conversation Games with AI](https://chicago.aitinkerers.org/talks/rsvp_8_C1ufLf42g) I made an app/game that gives fun little AI-powered voice challenges. I will demo it, talk about my approach to prompting and how the app works, and briefly get on a soapbox why I think you should "lean in to the AI medium" when doing creative design. - Event context: AI Tinkerers Chicago December Meetup ft Turing — 2025-12-09 — Chicago - Public talk page: https://chicago.aitinkerers.org/talks/rsvp_8_C1ufLf42g ### [fastworkflow is now SOTA on Tau Bench!](https://houston.aitinkerers.org/talks/rsvp_k2AwqMGR9Wo) During the last talk a few months ago, we demo'd fastworkflow results on Tau Bench retail and airline benchmarks comparable to GPT4o. With our latest refinements, fastworkflow beats ALL models including Sonnet 4.5! And it does this using models as small as 7B and 14B parameters. I will demonstrate the results and talk about the refinements that made this possible as well as our roadmap for the next 6 months - Event context: AI Tinkerers Houston Meetup: Code, Demos, and Agentic Architectures (December 9, 2025) — 2025-12-09 — Houston - Public talk page: https://houston.aitinkerers.org/talks/rsvp_k2AwqMGR9Wo ### [Using the gh cli with local agents for pr responses and guidance](https://seattle.aitinkerers.org/talks/rsvp_jYDzYWaL_As) I often find the UI for assigning agents (like copilot, etc) to tasks directly in github to be restrictive -- they lack context and can't be guided as easily. But I do like the github PR UI for providing specific feedback. Use both -- have the local agent use the gh cli to open the pr and respond to comments. Extra feedback can be given in the local chat if needed - Event context: AI Tinkerers Seattle Meetup: Dev Tools Track — December 8, 2025 — 2025-12-09 — Seattle - Public talk page: https://seattle.aitinkerers.org/talks/rsvp_jYDzYWaL_As ### [Building AI personas to reduce LLM hallucinations and improve reliability of agentic systems.](https://portland.aitinkerers.org/talks/rsvp_zOOQR9hFzSs) Andrew Becker — AI Engineer - Event context: Portland: Agentic Systems Deep Dive — Building the Next Generation of AGI — 2025-12-04 — Portland - Public talk page: https://portland.aitinkerers.org/talks/rsvp_zOOQR9hFzSs ### [Code Mode: Reduce Token Cost and Increase Efficiency](https://boston.aitinkerers.org/talks/rsvp_nXh8xYPjl7c) Anthropic and Cloudflare recently published articles describing a more efficient way for agents to call MCP functions. Ultimately, it's far more efficient for the LLM to write code for the agent to call tools rather than calling individual tools. - Event context: AI Tinkerers Boston Meetup December 2025 — 2025-12-02 — Boston - Public talk page: https://boston.aitinkerers.org/talks/rsvp_nXh8xYPjl7c ### [Production Incident (PI) to Pull Request (PR) In Minutes](https://bengaluru.aitinkerers.org/talks/rsvp_x17wU05fOj8) At Oodle AI, we are reimagining Observability with the help of Agentic AI workflows. In this talk, I will go over: 1. Our approach for AI-assisted debugging to provide you relevant insights on an alert. This workflow involves coordinating multiple agents using Google ADK along with tools specifically designed for providing relevant information to Agents. Integration with Cursor/Claude Code to go from a firing alert to a PR becomes possible. 2. Using ideas from WebMCP to enable users to perform day to day tasks like creating grafana dashboards, creating alerts, exploring metrics using prompts. I plan to give a short demo + go over implementation ideas for above. - Event context: AI Tinkerers - Bengaluru - November meetup — 2025-11-29 — Bengaluru - Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_x17wU05fOj8 ### [Long running, workflow context aware conversational agent solutions on Temporal](https://bengaluru.aitinkerers.org/talks/rsvp_pAuEWcjhhvA) We built a long running Temporal workflow based solution to build conversational agents, that allows you to have multi turn conversations, can live for 12 hours at a go, works on suspension/rerun models, has inbuilt retries, error handling and dependency management, and works to trigger complex workflows. We also built a DeepRAG model that allows agents to gain greater context across complex storage options - Event context: AI Tinkerers - Bengaluru - November meetup — 2025-11-29 — Bengaluru - Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_pAuEWcjhhvA ### [The Hitchhiker’s Guide to DFDs: AI Edition](https://bengaluru.aitinkerers.org/talks/rsvp_F0YrRA4D9P8) After nearly two decades of building systems, I can tell you that Data Flow Diagrams or Level 0 diagrams only look simple—until you sit down to draw one. Teams wrestle with fuzzy boundaries, missing actors, and those never-ending debates about which way the arrows should actually go. Most system descriptions aren’t written with diagrams in mind, so turning text into flows often feels like educated guesswork. The tooling doesn’t always help either—manual tools are clunky, and semantic tools regularly miss the nuances that matter. In this talk, I’ll walk through the different approaches I tried, the LLMs I experimented with, the test cases I built, and why—even after all that—I still don’t have a perfect solution and sometimes end up back at the manual method. - Event context: AI Tinkerers - Bengaluru - November meetup — 2025-11-29 — Bengaluru - Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_F0YrRA4D9P8 ### [DSPy + Visão computacional](https://saopaulo.aitinkerers.org/talks/rsvp_WwpwtYbsN1E) Apresentar, como Podemos usar o DSPy em conjunto com visão computacional para uma melhor retorno ao usuario. - Event context: Ai Tinkerers São Paulo na ESPM com Neo4j e Oracle - Novembro 2025 — 2025-11-27 — São Paulo - Public talk page: https://saopaulo.aitinkerers.org/talks/rsvp_WwpwtYbsN1E ### [The Engineer BS Detector: Why Authenticity Wins](https://belgrade.aitinkerers.org/talks/rsvp_1bAv865gK0U) How to build and communicate engineer-oriented products without fluff. I’ll cover how technical audiences signal feedback, what they value in a product, how to market to them honestly and clearly, and where AI helps (or hurts) when communicating real product value. - Event context: AI Tinkerers Belgrade Opening Meetup with PostHog — November 27, 2025 — 2025-11-27 — Belgrade - Public talk page: https://belgrade.aitinkerers.org/talks/rsvp_1bAv865gK0U ### [Claudio: repo as agent](https://sf.aitinkerers.org/talks/rsvp_2C0H-nIGUWo) Claudio is an experiment in how to create persistent, self improving agents by a simple mechanism of forking and deploying onto VM. - Event context: AI Tinkerers x Google Cloud SF Meetup — 2025-11-21 — San Francisco - Public talk page: https://sf.aitinkerers.org/talks/rsvp_2C0H-nIGUWo ### [Unstructure your CRM data with an AI node via n8n](https://san-diego.aitinkerers.org/talks/rsvp_6SXBaQqZdVg) I am open to presenting how to connect CRM to any AI model API via n8n. The use case that I would demo would be showing the webhook setup in a Hubspot private app, a live demo of the n8n flow once triggered (showcasing the AI agent), and the output of that flow. I think this is a cool topic because people always talk about structuring unstructured data, while I'm showcasing the value of doing the opposite. The value of this operationally is that in a sales pipeline, users down funnel actually really appreciate summarized/unstructured data to review, rather than reviewing fragmented structured data. - Event context: AI Tinkerers x Google AI Meetup, San Diego — 2025-11-21 — San Diego - Public talk page: https://san-diego.aitinkerers.org/talks/rsvp_6SXBaQqZdVg ### [Introducing Youz: Your Smart Travel Guide](https://nurnberg.aitinkerers.org/talks/rsvp_RVnHATk2Uck) Have you ever visited a historical or scenic site and wondered about the meaning behind its symbols, architecture, or history? Usually, you’d have to rely on tour guides, who may not speak your language fluently or might give rushed, incomplete explanations. If you don’t fully understand them or have follow-up questions, grasping the full story can feel nearly impossible. That’s where Youz comes in! What is Youz? Youz is a smart, AI-powered app that removes language and information barriers while traveling. Just install the Youz app on your phone, point your camera at a historical monument, temple, museum, or scenic site, and Youz instantly delivers detailed, accurate information about the location in your native language — both as clear audio narration and on-screen text. Youz is powered by the latest version of Gemini to answer your questions intelligently. To provide precise and relevant information (for example, about a specific temple), Youz first uses geofencing to detect nearby landmarks. It then queries a specialized vector database containing rich, curated information about historical and cultural sites, building the perfect context to answer your question accurately. With Youz, you’re no longer dependent on tour guides or language skills — you get a personal, expert guide in your pocket, anytime, anywhere. - Event context: AI Tinkerers Nürnberg Meetup – Nov 20 — 2025-11-20 — Nürnberg - Public talk page: https://nurnberg.aitinkerers.org/talks/rsvp_RVnHATk2Uck ### [LLM Gateways, a Software Engineering Perspective](https://amman.aitinkerers.org/talks/rsvp_uFflftd2KAM) Taking a deep look into LLM Gateways (LiteLLM or similar), and the software engineering concepts behind the scene. We will be looking into the features of an LLM Gateway, from loadbalancing, moderation, abstractive approach and more. - Event context: AI Tinkerers Amman Meetup — November 15, 2025 — 2025-11-15 — Amman - Public talk page: https://amman.aitinkerers.org/talks/rsvp_uFflftd2KAM ## Related Technologies - [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos - [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos - [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos - [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) — 115 public demos - [PaLM 2](https://aitinkerers.org/technologies/palm-2) ([Markdown](https://aitinkerers.org/technologies/palm-2.md)) — 116 public demos - [RoBERTa](https://aitinkerers.org/technologies/roberta) ([Markdown](https://aitinkerers.org/technologies/roberta.md)) — 118 public demos - [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos - [Claude-3](https://aitinkerers.org/technologies/claude-3) ([Markdown](https://aitinkerers.org/technologies/claude-3.md)) — 110 public demos - [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos - [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos - [Transformers](https://aitinkerers.org/technologies/transformers) ([Markdown](https://aitinkerers.org/technologies/transformers.md)) — 148 public demos - [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos - [scikit-learn](https://aitinkerers.org/technologies/scikit-learn) ([Markdown](https://aitinkerers.org/technologies/scikit-learn.md)) — 84 public demos - [TensorFlow](https://aitinkerers.org/technologies/tensorflow) ([Markdown](https://aitinkerers.org/technologies/tensorflow.md)) — 90 public demos - [Keras](https://aitinkerers.org/technologies/keras) ([Markdown](https://aitinkerers.org/technologies/keras.md)) — 74 public demos - [ONNX](https://aitinkerers.org/technologies/onnx) ([Markdown](https://aitinkerers.org/technologies/onnx.md)) — 83 public demos - [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos - [Generative AI](https://aitinkerers.org/technologies/generative-ai) ([Markdown](https://aitinkerers.org/technologies/generative-ai.md)) — 45 public demos ## More Results - Next: https://aitinkerers.org/technologies/llama-2.md?page=2