Are You Shipping More With GitHub Copilot? Is More Roadmap Work Being Done?
tl;dr: Engineering leaders are trying to figure out if their team is using GitHub Copilot, how much they're using it, and its impact on their work. Download this slide deck from Jellyfish, analyzing data from 4,200+ developers at 200+ companies, and start understanding whether you're getting adequate return on your AI investments.featured in #571
Expanding The Solution Size With Multi-File Editing
- Birgitta Böckeler tl;dr: “A very powerful new coding assistance feature made its way into GitHub Copilot at the end of October. This new “multi-file editing” capability expands the scope of AI assistance from small, localized suggestions to larger implementations across multiple files. Previously, developers could rely on Copilot for minor assistance, such as generating a few lines of code within a single method. Now, the tool can tackle larger tasks, simultaneously editing multiple files and implementing several steps of a larger plan. This represents a step change for coding assistance workflows.”featured in #568
The Impact of Generative AI on Software Developer Performance
tl;dr: BlueOptima's study of 200,000+ enterprise developers uncovered surprising insights on the reality of Generative AI: (1) Only 12% of developers commit GenAI code without modification, suggesting limited real-world integration. (2) Modest productivity gains of only 4%, indicating marketing claims are premature. (3) A decline in quality with high AI usage.featured in #559
featured in #557
Modeling Impact Of LLMs On Developer Experience
- Will Larson tl;dr: “Models are imperfect representations of reality, but this one gives us a clear sense of what matters the most: if we want to increase our velocity, we have to reduce the rate that we discover errors in production. That might be reducing the error rate as implied in this model, or it might be ideas that exist outside of this model. For example, the model doesn’t represent this well, but perhaps we’d be better off iterating more on fewer things to avoid this scenario. If we make multiple changes to one area, it still just represents one implemented feature, not many implement features, and the overall error rate wouldn’t increase.”featured in #556
OpenAI Is Shockingly Good At Unminifying Code
- Frank Fiegel tl;dr: “Usually I would just power through reading the minimized code to understand the implementation. However, I realized that I never tried asking ChatGPT to do it for me... So I copied all of the above code and asked ChatGPT to "explain the code”.”featured in #545
featured in #542
Advanced Terminal Tips And Tricks
- Daniel Kleinstein tl;dr: “I wanted to share some things I learned at relatively late stages in the game that ended up being significant productivity boosters for me: (1) Use command line editing. (2) tmux scripting. (3) Use fzf liberally in custom scripts. (4) Use /dev/stdin as a replacement for heredocs. (5) Use SSH multiplexing.featured in #534
Did You Know About Instruments?
- Thorsten Ball tl;dr: “For the longest time, I thought Instruments on macOS wasn’t for me. Whenever I saw its icon show up in the /Applications folder or pop up in a launcher, I assumed it’s part of Xcode and Xcode is an IDE for Objective-C and Swift programmers and that’s not what I do and that’s why Instruments isn’t for me. I was wrong.” Thorsten discusses how he uses Instruments as a productivity tool with anything.featured in #534
Six Tips To Improve a Conversion Funnel
- Ryan Musser tl;dr: (1) Identify the friction. (2) Streamline. (3) A/B test your solution. (4) Personalize, where you can. (5) Build trust, when you can. (6). Track everything.featured in #529