This week's newsletter is brought to you by Sentry.
Hey there,
It’s the final week of Hacktoberfest, and we’re sending it off with one last challenge. The Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine is live now, with $2,850 in prizes across 21 winners. With Halloween on October 31 and Día de los Muertos on November 1 and 2, we want to see something spooky or something that honors the past, built with open-weight models or open-source AI. Think a haunted terminal that talks back, a virtual ofrenda builder, or a local tool that preserves family stories. The theme is wide open, so interpret it however you like.
Here are some Hacktoberfest streams airing on the DEV homepage this week:
Tuesday, October 27
- 1:00PM - 2:00PM ET: Software Factories, Mastra, and the Future of Agents
- 3:00PM - 4:00PM ET: Agent-Led Growth: How to Make the Best Possible Tool for Agents
Wednesday, October 28
- 10:00AM - 10:45AM ET: Which Open Model Writes Best? Inside a Free Benchmark for Creative Writing
- 1:00PM - 2:00PM ET: How We Hit $1M ARR in 24 Hours + Launching Backboard Studio
Thursday, October 29
- 3:00PM - 4:00PM ET: Build Your Own Personal Chatbot Assistant, Powered by MongoDB
- 5:00PM - 7:00PM ET: Running Local AI Models with Ollama and OpenCode
Friday, October 30
- 1:00PM - 2:00PM ET: How Sentry Debugs Its Own AI Agents
- 4:00PM - 5:00PM ET: Post-Training Models to Learn Anything! (Thinking Machines Lab)
- 5:00PM - 7:00PM ET: Building Your Own Skills with OpenCode
Finally, thank you to everyone who showed up week after week this month. Let’s make this last one count! 👻🌼
Have a great week ❤️
As always, here are our favorite posts from last week in no particular order:
- Why an 80-Year-Old Math Book Fixed My AI Coding Agent: one developer’s take on borrowing a 1945 problem-solving method to keep AI coding agents from writing code too early.
- Don’t Be a Proxy Between Me and Your AI: rethinking how AI fits into technical discussions, and what gets lost when colleagues relay chatbot answers instead of their own judgment.
- How to Become a Tech Conference Speaker (And Why You Might Regret It): real experiences from the conference circuit, from rejected CFPs to stage fright, and an honest look at whether speaking is worth it.
- AI Is Winning Literary Awards. The Data Says That’s Not What’s Happening.: exploring what the data actually says behind the headlines about AI winning literary awards.
- “Build in Public” Is Everywhere. Does It Actually Get You Customers?: a practical take on whether building in public brings in paying customers, plus a four-week experiment to test it on your own product.
- The 480 Outputs That Never Became Actions: lessons learned from a multi-agent experiment that ran exactly as designed and still produced no usable results.
- The Garden I Wait for Every Winter: personal insights from one developer’s winter garden, and the joy of making something that can’t be rushed.
$1M Back to Open Source
Sentry just gave $1,000,000 to open source maintainers and foundations this year through the Open Source Pledge, up from $750K last year. Does your company pay for the open source it depends on? See how Sentry did it and join the Open Source Pledge.
Here are some standout wins from last week's discussion:
- @steven_liechti_f357b4134a: had a LinkedIn post go viral with ~70k views, way up from their usual 500–1k 📈
- @francistrdev: wrapped up their midterms 📚
- @beusebiu: added cover images to every older post on their app’s blog, plus a test that fails if a post ships without one 🖼️
- @pengeszikra: brought HEXAW to beta, a retro assembly-style way to generate WebAssembly binaries without a traditional compiler 🚀
- @star123: scored a perfect 100/100 on their math test 💯
Well done, everyone!
Thanks for Being Awesome! 😎
Have we told you lately how awesome you are? Thanks a ton for all you bring to DEV. Your ideas, your content, your support—it's what makes this community great.
Happy coding!
P.S. Thank you again to Sentry for sponsoring this week's newsletter.