AI & LLM
Building Long-Term memories using hierarchical summarization
Learn how hierarchical summarization builds efficient Long-Term memories by capturing, summarizing, and organizing data for faster context retrieval.
← All posts
Jim Bennett
Jim Bennett is the worlds most energetic developer advocate, and head of developer advocacy at Pieces for Developers, focusing on enabling developers to be more productive by leveraging contextual awareness of not only the code they write, but the content the read and the conversations they have. He’s British, so sounds way smarter than he actually is, and lives in the Pacific North West of the USA. In the past he’s lived in 4 continents working as a developer in the mobile, desktop, and scientific space. He's spoken at conferences and events all around the globe, organized meetup groups and communities, and written books on mobile development and IoT.
He also hates and is allergic to cats, but has a 12-year-old who loves cats, so he has 2 cats.
Posts by Jim Bennett
Engineering
An under the hood look at how Pieces implemented an MCP server
At Pieces we’ve just announced our new MCP server, allowing you to interact with your Pieces Long-Term Memory from any MCP client, such as Cursor or GitHub Copilot.
Podcast
Ep.07 – Investing in AI, with Amir Shevat, Early stage startup investor, author
Amir Schvatz, investor at Dark Mode, shares insights on AI, developer platforms, and the rise of "PM Coding" in software creation.
AI & LLM
How MCP helped my team do more with less
Discover how Model Context Protocol (MCP) helped our team streamline workflows, reduce development time, and increase productivity, all while doing more with less
AI & LLM
IBM outperforms OpenAI? What 50 LLM tests revealed
50 LLMs benchmarked for real dev tasks: see how IBM outperformed OpenAI and what it means for the future of AI tooling.
Podcast
Ep. 05 - Phillip Carter, Principal PM, Honeycomb | Can AI Improve Observability?
AI in observability: What works, what doesn’t. Phillip Carter shares where humans still lead and where AI fits in.
Podcast
Ep.06 - David Packman, Co-Founder Packabby Robotics | Social Robots & AI That Remembers
Explore social robots, emotional AI, and long-term memory with David Packman, co-founder of Packabby Robotics.
Podcast
Ep.4 with Shaundai Person, Netflix | Building a strong engineering culture & the role of AI
Shaundai Person on engineering culture, AI for productivity, and the "Shaundai Hierarchy of Needs" for developers!
Podcast
Ep. 3 with Daniele Bernardi, CEO at Toolhouse |Toolhouse, Groq, and the Future of Affordable LLMs
Learn how Toolhouse simplifies AI, Groq’s impact, and the future of affordable AI beyond the US. Tune in now!
AI & LLM
Forget everything else — Long-Term Memory is all you need
Forget everything else — Long-Term Memory is the key to smarter, more efficient AI. Discover how it revolutionizes learning, recall, and decision-making.
AI & LLM
Off the shelf copilots are dead | Build your own with your data
Off-the-shelf copilots are obsolete! Build a custom AI copilot powered by your own data using Pieces AI for smarter, more personalized automation.
AI & LLM
Why companies are turning to small language models? (SLMs)
Discover what Small Language Models (SLMs) are and how they can revolutionize AI adoption. Learn how SLMs offer efficiency, privacy, and cost-effective AI solutions for businesses.
AI & LLM
What are LLM parameters and what is their role?
Language models, both large and small, have their size measured in parameters. The big, cloud models, like GPT-4o use trillions of parameters, whereas smaller models you can run locally have billions of parameters.
AI & LLM
What is the best LLM for coding as of today?
Discover the best LLM for coding - whether you’re generating code or just asking questions, understanding cloud vs local LLMs can make you more effective.
AI & LLM
You can do what with Pieces AI when offline?
Enable offline AI with on-device LLMs, enhancing your productivity in privacy-focused environments.
Product Updates
New for 2025 – more local models in Pieces, including Qwen Coder and Phi-4
Pieces has added more local models to power the copilot and long term memory including Qwen coder and Phi-4
Insights
Be more productive with Pieces and GitHub Copilot
Combine Pieces and GitHub Copilot to build a powerful workflow with long-term memory and AI assisted coding
Insights
Everything a dev community should know about using Pieces in Cursor
Combine Pieces and Cursor for a powerful AI assistant with Long-Term Memory and agentic workflows to boost productivity
Engineering
What is Leverage Engineering?
Leverage Engineering is a team at OpenAI that dogfoods openai to improve internal processes. Learn more about these types of roles.
Insights
You can do what with Pieces? Jim’s top 5 copilot prompts
Discover 5 powerful prompts for Pieces to enhance your productivity and workflow as a software engineer.
Product Updates
Pieces now powered by Ollama for enhanced local model integration
Chat with LLMs offline or in secure environments using Pieces. Seamlessly switch between cloud and local models, now powered by Ollama.
AI & LLM
Best practices for prompt engineering with AI Copilots
Check out best practices for prompt engineering with AI Copilots. Learn clear and concise prompts, ensuring optimal responses and improved results.
AI & LLM
LLM prompt engineering | Tutorial for developers
Master LLM prompt engineering with this step-by-step tutorial for developers. Learn techniques to craft effective prompts and optimize AI responses for better results.
AI & LLM
Set an LLM to unit test an LLM
LLMs are non-deterministic, so are hard to unit test. Learn how to do so by using one LLM to validate another
Insights
Learn How Jim Made a Mess With the Pieces Confetti Cannon
Discover how we created a Raspberry Pi-powered confetti cannon demo using Viam robotics and Pieces for developers at FlutterCon.