fonrex's comments

fonrex · 2026-11-05T08:06:11

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.

fonrex · 2026-10-13T22:09:34

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).

senderista · 2026-10-14T00:20:30

Opus 5.5 routinely finds tons of bugs in code that Opus 5.5 wrote, so this may not reflect a difference in model capability.

dieortin · 2026-10-14T00:10:36

Sounds like you were using the older Gemini 3.1 Pro from February, and not the new release this post is about

fonrex · 2026-10-13T13:54:15

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 !

fonrex · 2026-10-12T09:43:33

Question: Does this work only for Claude Code? Can your project be connected via VSCode (or Antigravity SDK) ?

iohotspot · 2026-10-12T15:08:57

It should work with any harness that supports MCP. We have tested it with claude code, antigravity, copilot and opencode. All work with no issue

fonrex · 2026-10-13T12:27:13

oh good sound ! thank for your reply

fonrex · 2026-10-12T09:38:37

I hope they'll be able to do that with Forza too !