HNHacker News
TopNewBestAskShowJobs

SomeonesAccount

3 karma · joined August 26, 2026

submissionscomments
SomeonesAccount··on StreetComplete on iOS is now in public beta
StreetComplete, as indicated by it's name, is about street data. Both are for contributing to OSM, but they are for different parts of OSM
SomeonesAccount··on Dots: Always-on agents
Nor Way! I can't believe that. Need something else to Sweden my day :)
SomeonesAccount··on When the fractional part of a float fixes your shader
*former

Good catch. OP should probably update the article

SomeonesAccount··on Gemini 3.8 Live and 3.8 Live Extended Thinking
I was more saying that nobody should use it. AI Studio, while also terrible, is better and does (AFAIK) the exact same thing.
SomeonesAccount··on Show HN: I made a flight simulator, except you're just a passenger
underrated comment
SomeonesAccount··on Gemini 3.8 Live and 3.8 Live Extended Thinking
vertex is dead, for good reason too
SomeonesAccount··on So you want to use OpenRouter?
exactly. all of these people complaining are using it wrong. you cant just expect a layer of abstraction to perfectly fix all the layers below it! plus, open router does a great job of handling a lot of the provider problems, but it literally cannot fix the output of the provider
SomeonesAccount··on So you want to use OpenRouter?
exactly. you can specify a provider in your request to openrouter, or, better yet, use the :exacto endpoint to make open router automatically choose one that is good at tool calls.
SomeonesAccount··on ICE Has a $2M Contract for Spyware That Can Hack Phones Without a Click
great article, very detailed
SomeonesAccount··on Show HN: My Claude quota ran out in 10 minutes, so I made a tool to find out why
I wrote that slop comment
SomeonesAccount··on Show HN: My Claude quota ran out in 10 minutes, so I made a tool to find out why
That is a very common title format for HN, and has been for a while. It wasn't just since AI has evolved—it has always been a load bearing part of HN

100% Human written slop

SomeonesAccount··on Small Models Have Arrived
Exactly! Composer 2/2.5 were amazing, cheap, and fast. Everyone else was Gaga about GPT 5.5 and such, while we were over here doing the work with less cost and more speed
SomeonesAccount··on The Raycast Keyboard
I don't think it was necessary for two different AI buttons, but whatever
SomeonesAccount··on The Raycast Keyboard
This actually looks sick
SomeonesAccount··on Microduck
That is sick
SomeonesAccount··on It’s so hard to finish an idea that is not yours and is just suggested by AI
This is why I never use AI for ideas. Always my own ideas.
SomeonesAccount··on Z.ai confirms Ox Alpha is a new GLM-series model and will release its weights
Definitely agree. If it is small (eg. Qwen 3.8 28b or gpt-oss-120) then this might be amazing. If it is anywhere near Kimi K3 it would need to have some other differentiating factor than intelligence.