In this engaging discussion, Simon Willison, co-creator of Django and open-source advocate, shares his journey with AI tools in software development. He challenges notions of fine-tuning AI, highlights the potential of Retrieval Augmented Generation (RAG), and explores common misconceptions about large language models. Simon reflects on ethical concerns and the evolving role of AI, revealing that these technologies can augment, not replace, skilled programmers. Tune in for humor, practical insights, and a dose of coding wisdom!

In this conversation with Simon Willison, an independent researcher and creator of Datasette, we discover how developers can supercharge productivity using LLMs like ChatGPT and Claude. Simon shares his innovative workflows, including coding while walking his dog. He dives into effective prompting techniques, rapid prototyping with Claude’s Artifacts feature, and the evolving role of open-source and local models. The discussion also touches on the transformative impact of AI on coding practices and modern web scraping tools.

Simon Willison, a prominent web developer known for his projects like Datasette, dives into the world of large language models (LLMs) for Python development. He shares effective prompting techniques and discusses the best models for coding. Simon compares tools and highlights his open-source journey, noting how blogging has influenced his career. He also addresses the potential pitfalls of AI, urging critical evaluation of its outputs. Expect insights on coding tools, ethical implications of tech, and a whimsical look at AI's creative quirks.

Full Transcript and show notes: https://www.latent.space/p/function-agents?sd=pfTimestamps:[00:00:00] Intro[00:01:47] Recapping June 2023 Updates[00:06:24] Known Issues with Long Context[00:08:00] New Functions API[00:10:45] Riley Goodside[00:12:28] Simon Willison[00:14:30] Eric Elliott[00:16:05] Functions API and Agents[00:18:25] Functions API vs Google Vertex JSON[00:21:32] From English back to Code[00:26:14] Embedding Price Drop and Pinecone Perspective[00:30:39] Xenova and Huggingface Perspective[00:34:23] Function Selection[00:39:58] Designing Code Agents with Function API[00:42:16] Models as Routers[00:46:48] Prompt Engineering replaced by Finetuning[00:52:15] The 2 Code x LLM Paradigms[00:56:30] Smol Models for the future[00:58:54] The Evolution of the GPT API[01:03:27] Functions API Security vs Prompt Injection[01:16:18] GPT Model Upgrades[01:17:36] JSONformer[01:21:03] Closing Comments - What We Want Next Get full access to Latent.Space at www.latent.space/subscribe

This week we’re talking about LLMs with Simon Willison. We can not avoid this topic. Last time it was Stable Diffusion breaking the internet. This time it’s LLMs breaking the internet. Large Language Models, ChatGPT, Bard, Claude, Bing, GitHub Copilot X, Cody…we cover it all. Join the discussionChangelog++ members get a bonus 18 minutes at the end of this episode and zero ads. Join today!Sponsors:DevCycle – Build better software with DevCycle. Feature flags, without the tech debt. DevCycle is a Feature Flag Management platform designed to help you build maintainable code at scale. Postman – Build APIs together — More than 20 million developers use Postman for building and using APIs. Postman simplifies each step of the API lifecycle and streamlines collaboration so you can create better APIs—faster. Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster! Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs. Featuring:Simon Willison – Website, GitHub, XAdam Stacoviak – Website, GitHub, LinkedIn, Mastodon, XJerod Santo – GitHub, LinkedIn, Mastodon, XShow Notes: AI-enhanced development makes me more ambitious with my projects Cerebras-GPT: A Family of Open, Compute-efficient, Large Language Models I lost everything that made me love my job through Midjourney over night. ChatGPT plugins nomic-ai/gpt4all Houston AI Unreal Engine 5.2 - Next-Gen Graphics Tech Demo (State of Unreal 2023) Apple’s secret M1 coprocessor For our Changelog++ subs… For the fiscal year 2021, Alphabet (Google’s parent company) reported revenues of $182.5 billion, and the revenue breakdown was as follows: Advertising: $147.5 billion Google Cloud: $14.9 billion Google Play and other sources: $25.1 billion Something missing or broken? PRs welcome!

Simon Willison, co-creator of Django and Datasette, shares insights on navigating the world of LLMs. He compares LLMs to a quirky intern and discusses their evolution, emphasizing the importance of blogging for accountability. Simon dives into productive use of GitHub issues for documentation, and the nuances of prompt engineering. He also reflects on how LLMs can foster ambition in developers while addressing their limitations. Finally, he shares the exciting journey of developing a startup with his partner, blending personal and professional life.

Simon Willison, creator of Datasette and LLMs, discusses topics including improving Django's default user model, leveraging tools like co-pilot and LLMs, generating release notes with GPT-4, positive impacts of technology tools, exploring dataset's enrichments feature, and securely running software on dataset cloud.

Simon Willison, a practical expert on open source large language models (LLMs), brings clarity to their workings and limitations. The podcast explores misconceptions surrounding open source AI, ethical concerns of open source training, and democratizing access to LLMs. It also discusses the impact of AI on various professions and the benefits of open source in search engines. The hosts express admiration for Simon and delve into the complexity of the web three and crypto space. Simon's work with Data Set, an open source tool for exploring and publishing data, is also discussed.

This week we’re talking about LLMs with Simon Willison. We can not avoid this topic. Last time it was Stable Diffusion breaking the internet. This time it’s LLMs breaking the internet. Large Language Models, ChatGPT, Bard, Claude, Bing, GitHub Copilot X, Cody…we cover it all. Join the discussionChangelog++ members get a bonus 18 minutes at the end of this episode and zero ads. Join today!Sponsors:DevCycle – Build better software with DevCycle. Feature flags, without the tech debt. DevCycle is a Feature Flag Management platform designed to help you build maintainable code at scale. Postman – Build APIs together — More than 20 million developers use Postman for building and using APIs. Postman simplifies each step of the API lifecycle and streamlines collaboration so you can create better APIs—faster. Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster! Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs. Featuring:Simon Willison – Website, GitHub, XAdam Stacoviak – Website, GitHub, LinkedIn, Mastodon, XJerod Santo – GitHub, LinkedIn, Mastodon, XShow Notes: AI-enhanced development makes me more ambitious with my projects Cerebras-GPT: A Family of Open, Compute-efficient, Large Language Models I lost everything that made me love my job through Midjourney over night. ChatGPT plugins nomic-ai/gpt4all Houston AI Unreal Engine 5.2 - Next-Gen Graphics Tech Demo (State of Unreal 2023) Apple’s secret M1 coprocessor For our Changelog++ subs… For the fiscal year 2021, Alphabet (Google’s parent company) reported revenues of $182.5 billion, and the revenue breakdown was as follows: Advertising: $147.5 billion Google Cloud: $14.9 billion Google Play and other sources: $25.1 billion Something missing or broken? PRs welcome!

Simon Willison, Former software architect at The Guardian and a JSK Journalism Fellow at Stanford University, built Datasette to help journalists analyze data. He shares fun use cases of ChatGPT and discusses the intersection of data journalism and coding using GPT-3. They explore the use of ChatGPT for satirical news articles and address bias in story generation.