/AI

Reshaping The Tree: Rebuilding Organizations For AI

- Ethan Mollick tl;dr: "AI is impacting organizations, and managers need to start taking an active role in shaping what that looks like. There is no central authority that can tell you the best ways to use AI - every organization will need to figure it out for themselves.” Ethan proposes some principles:" (1) Let teams develop their own methods. Given that AIs perform more like people than software, they are often best managed as additional team members. (2) Build for the oncoming future. It is clear that advanced models are coming fast. (3) Organizations that wait to experiment will fall behind very quickly. 

featured in #470


Summarizing Post Incident Reviews With GPT-4

- Wuji Zhu tl;dr: "We start by fetching the report from Confluence and parsing the HTML to extract the content of the PIR as raw text. We then remove sensitive data, including links, emails, and Slack channel names, to avoid exposing internal information to public models and ensure blameless summaries. We then send the text version of the report to GPT-4 chat completion to generate a summary." This is then archived with additional metadata and summarized onto the Jira ticket. Wuji provides an overview of how this is operationalized. 

featured in #468


Embeddings: What They Are And Why They Matter

- Simon Willison tl;dr: “Embeddings are based around one trick: take a piece of content—in this case a blog entry — and turn that piece of content into an array of floating point numbers.” Simon shows us what this looks like and argues that we can learn interesting things about the content this way - “it might capture colors, shapes, concepts or all sorts of other characteristics of the content that has been embedded.” Simon also shows us practical use cases of how this may show up.

featured in #459


So We Shipped An AI Product. Did it Work?

- Phillip Carter tl;dr: “Like many companies, earlier this year we saw an opportunity with LLMs and quickly but thoughtfully started building a capability. About a month later, we released Query Assistant to all customers as an experimental feature. We then iterated on it, using data from production to inform a multitude of additional enhancements, and ultimately took Query Assistant out of experimentation and turned it into a core product offering. However, getting Query Assistant from concept to feature diverted R&D and marketing resources, forcing the question: did investing in LLMs do what we wanted it to do?”

featured in #454


LLMs Demand Observability-Driven Development

- Charity Majors tl;dr: “Many software engineers are encountering LLMs for the very first time, while many ML engineers are being exposed directly to production systems for the very first time. Both types of engineers are finding themselves plunged into a disorienting new world—one where a particular flavor of production problem they may have encountered occasionally in their careers is now front and center. Namely, that LLMs are black boxes that produce nondeterministic outputs and cannot be debugged or tested using traditional software engineering techniques. Hooking these black boxes up to production introduces reliability and predictability problems that can be terrifying.“ Charity believes that the integration of LLMs will necessitate a shift in development practices, particularly towards Observability-Driven Development, to handle the nondeterministic nature of these models.

featured in #450


Lessons From Building A Domain-Specific AI Assistant

- Eric Liu tl;dr: Eric Liu, Engineer at Airplane, discusses how the Airplane team built a domain-specific AI assistant, the lessons they learned along the way, and what's next for the future of AI assistants.

featured in #447


How Are You Investing In AI?

tl;dr: Fundrise has fully democratized venture capital. Now you can get in early, investing in some of the most promising pre-IPO tech companies— including those leading the AI revolution. No accreditation required. No membership fees. And the lowest venture investment minimum ever.

featured in #446


5 AI Tools For Developers To Help Boost Your Productivity

- Lewis Cianci tl;dr: (1) Phind: A developer-focused search engine that provides detailed answers and related links for coding questions. (2) Bloop.ai: Helps developers understand the structure of GitHub repositories quickly. (3) Codeium: Offers real-time code suggestions within various IDEs. (4) ColPat: Design tool that helps in creating color palettes and themes for apps and websites. (5) RegExGPT: Generates regular expressions based on natural language prompts.

featured in #444


How Are You Investing In AI? 

tl;dr: Fundrise has fully democratized venture capital. Now you can get in early, investing in some of the most promising pre-IPO tech companies— including those leading the AI revolution. No accreditation required. No membership fees. And the lowest venture investment minimum ever. 

featured in #443


TDD With GitHub Copilot

- Paul Sobocinski tl;dr: The article explores the relationship between Test-Driven Development and AI coding assistants like GitHub Copilot. It argues that TDD remains essential even with AI assistance, as it provides fast and accurate feedback and helps in dividing and conquering problems. The article  shares tips for using GitHub Copilot with TDD, including starting with context, following the Red-Green-Refactor cycle, backfilling tests, and recognizing Copilot's limitations in refactoring.

featured in #441