🐜 🍯

@anthonybecker.bsky.social

I like my mutuals, we are pals. I’m a lovely man who works as a software engineer in California. Extremely mystical. Alt text: pfp is me. I have curly black hair. Banner is Laniakea, art by @markgarlick.com He/Him

This time, I had Fable built me a casual Van Gogh city building game that I faked in an AI video last year. The key mechanic the AI came up with is painting the landscape with big brushstrokes & an environment that evolves with weather and seasons. Chill and pretty. Play it: the-sower.netlify.app

the whole 'nothing has gotten better' discourse is of course fucking stupid in a million ways, but I just wanted to note that average dog lifespan in the United States has increased by two years since 2000.

I’m working on my grasp of agentic development. current toolbelt: - conversation history introspection - command rewriting - “use plain language“ - /handhold - in-depth code walkthroughs as HTML documents Developing: - spec driven development with strict gates - debugging visualizations - /quiz-me

a thing about coding LLMs is you can be working entirely old school, manually, and still love them because for the first time in your life there's someone actually interested in the details of your work, willing to take the time to look and comment intelligently and say something nice.

I see a lot of you talking about "dopamine" and I wish you'd go back to talking about your astrological signs because at least then you wouldn't be confusing yourself about a real thing

Using LLMs should allow us to think bigger, harder to grasp, difficult to execute, longer to develop, ideas. That idea that’s been in you brain since forever but you hadn’t had the time because you had to retool and what not. Trust yourself. Go for that shit. Now is the fucking time.

Clément Canonne@ccanonne.github.io · 4d ago

"We're all worried," as what it means to do research (in my field, Theoretical CS) seems to be shifting, and shifting fast. What to do? Senior researchers must lead by example, knowing that not everything will pan out. What I'm suggesting below may not work everywhere, but here's my own advice: 1/

The whole thing is about abstracting away complexity to places where I don't have to think about it, so I can apply my brain to the work at bigger and bigger scales.

Its funny to me to assert that you need to know every detail about what your code does at every level, given that the computer does several billion things I only have a fuzzy understanding of every single second.