News for hackers. Stuff that matters.

fonrex

Re:Ask HN: What's your current AI agentic setup? on Thursday November 05, 2026 @03:06AM (#50376463)
I pay for Claude Pro ($20/mo)—using Claude Code with Opus 5.5, and Google AI Premium ($20/mo) for Gemini Pro with Gemini 4.

When I write code with one, I use the other for peer review.

Re:Gemini 4 Argon on Tuesday October 13, 2026 @06:09PM (#50079601)
I completely agree; I was really surprised to find that Claude Code Opus 5.5 is significantly better. I had spent quite a bit of time using Gemini Pro for coding tasks, but when I revisited the code analysis using Opus 5.5, it revealed quite a few shortcomings in Gemini's understanding... I code using Python, which is considered the best language for writing code via LLMs (I am referring to linguistic entropy).
great article, and when i read that:

"I found the rot that develops inside applied mathematical theory when formalism becomes so detached from reality that a “breakthrough” is nothing more than an artifact of mathematicians not being able to properly specify the rules of their games in natural language."

it's like in my company, where some software developers get frustrated with an LLM that writes poor code. Understanding what you want—and providing the right examples and explanations—is crucial !

Re:Show HN: I Cut my Agent Tokens By 50% on Tuesday October 13, 2026 @08:27AM (#50070603)
oh good sound ! thank for your reply
Re:Show HN: I Cut my Agent Tokens By 50% on Monday October 12, 2026 @05:43AM (#50053821)
Question: Does this work only for Claude Code? Can your project be connected via VSCode (or Antigravity SDK) ?
Re:Show HN: PS2 games statically recompiled to WebAssembly on Monday October 12, 2026 @05:38AM (#50053772)
I hope they'll be able to do that with Forza too !