Profile avatar
dylancastillo.co
About: dylancastillo.co Projects: dylancastillo.co/projects
28 posts 31 followers 103 following
Regular Contributor
Conversation Starter
Posts 12 Comments 17

It's late but I finally finished my 2024 review. Last year: 💵 I worked on 9 projects with 7 clients. Doubled revenue, costs are up by 155%. 💻 Coded 322 days. Wrote 14 blog posts. 🧠 Struggled with focus. Nearly burned out. 📸 Debi tirar mas fotos. dylancastillo.co/posts/2024-...

submitted 8 hours ago • 0 comments

I got an email from Google saying that one of my side projects, deepsheet, got 1,000% more clicks. After a bit of digging, I realized that it was just due to people misspelling "DeepSeek." There are now people out there who think that China's top AI is a 💩 that makes charts.

submitted 35 days ago • 0 comments

New pinned tab

submitted 49 days ago • 0 comments

Always remember that using a response schema for an LLM is not the same as using one for your API. Sounds easy, but happens to everyone. Here's OpenAI breaking the CoT reasoning of an LLM judge.

submitted 56 days ago • 0 comments

Note to self: your only job is not to break the chain.

submitted 61 days ago • 0 comments

Found 2 big issues with Gemini's structured outputs (SO): 1. Using constrained decoding seems to lower performance in reasoning tasks. 2. The Generative AI SDK can break your model's reasoning. Just re-ran Let Me Speak Freely benchmarks with Gemini and got some interesting news

submitted 63 days ago • 1 comment

Structured outputs can decrease LLM's performance in some tasks I replicated @willkurt.bsky.social / @dottxtai.bsky.social rebuttal of Let Me Speak Freely? (LMSF) using gpt-4o-mini The rebuttal correctly highlights many flaws with the original study, but ironically, LMSF's conclusion still holds

submitted 89 days ago • 1 comment

Recently, a dataset of 1M Bluesky posts unexpectedly sparked backlash on Bluesky, including accusations of theft, calls for legal action, and death threats. It also uncovered strong anti-AI sentiment on the platform. This write-up reflects on what happened and why. eugeneyan.com/writing/anti/

submitted 90 days ago • 16 comments

Me after using ChatGPT to reproduce and patch a security vulnerability in a package downloaded 1 million times per month.

submitted 91 days ago • 0 comments

There's 0% chance that @bsky.app survives long-term without AI tools for moderation, filtering bots, etc. h/t @alpindale.bsky.social and @danielvanstrien.bsky.social for helping with that goal

submitted 102 days ago • 0 comments

The typical anti-AI person writing an angry post on their way home doesn't realize that AI: 1. Silently fixes their spelling mistakes on their iPhone 2. Calculate the fastest way home on Uber 3. Pick the right music for the ride on Spotify 4. Keeps their credit card safe to buy their subscriptions

submitted 102 days ago • 5 comments

Crypto is to greed what porn is to lust. You can be skeptical about its real-life utility (which I am), but it's hard to bet against such powerful motivators.

submitted 108 days ago • 0 comments