HNHacker News
TopNewBestAskShowJobs

someoneontenet

40 karma · joined July 1, 2024

submissionscomments
someoneontenet··on Scaffolding to Superhuman: How Curriculum Learning Solved 2048 and Tetris
Curriculum learning helped me out a lot in this project too https://www.robw.fyi/2025/12/28/solve-hi-q-with-alphazero-an...
someoneontenet··on Figure 03, our 3rd generation humanoid robot
How did I know this was gonna be speed lol
someoneontenet··on Show HN: RULER – Easily apply RL to any agent
Love these write ups!
someoneontenet··on Ask HN: Does it make sense to be in SF if you are bootstrapped?
Come visit for a few weeks and see if it’s right for you :)
someoneontenet··on JSLinux
I’ve tried to set this up and get a little bogged down on some of the finer points of compiling nixos to wasm. It’s not very straightforward unfortunately :/
someoneontenet··on JSLinux
My dream is have a in browser nixos vm on wasm. If I could have a bare vm, I can bootstrap it easily with a nixos config. From there I can start thinking about running web services in browser tabs instead of physical hardware.
someoneontenet··on Bonobos use a kind of syntax once thought to be unique to humans
I think that you might be taking that example in bad faith.
someoneontenet··on Ask HN: Does anyone still use code snippets?
At that point you may as well use a typewriter
someoneontenet··on Relax while watching bouncing particles making connections when they get closer
Neat, I’ve also made something like this with processing https://robw.fyi/constellation.html
someoneontenet··on Agentic patters from scratch using Groq
The readme was the most important part for me!
someoneontenet··on Sanding UI
Sounds like op is manually fuzz testing.
someoneontenet··on Anthropic's Prompt Engineering Interactive Tutorial
I talk to ai like a caveman mostly. Instead of over optimizing my prompt I just try to find the minimal amount of representation to get the llm to understand my problem and solve it for me and I have been very productive with this strategy. What would someone like me get out of prompt engineering? Or is it more for things like agents, bots, and assistants?
someoneontenet··on Neon Postgres vs. Supabase
Seems weird to compare them since I see them as complimentary services.
someoneontenet··on Three years in North Korea as a foreigner (2021)
I’m sure some countries are more willing to treat guests to the vegetable treatment than others.
someoneontenet··on Don't use booleans (2019)
How is this done for js?
someoneontenet··on Five common English words we don't know the origins of–including 'boy' and 'dog'
Fantasize?
someoneontenet··on My Python code is a neural network
Newtons Method approximates square roots. Its useful if you want to approximate something like that without pulling in the computational power required of NN.