They said they designed it to be a better coding model. Something that has long been true: better software engineers are better vulnerability hunters as well. I think we are seeing that play out with Mythos.

Antigravity off in the corner feeling sad about itself rn.

I love poor forgotten Antigravity. For one, you can use your Gemini account to churn Opus credits until they run out then switch to Gemini 3.1 to finish off.

Yep. They are good at it.

And if you have the better harness and the next model?

I would _hope_ that the double combo would be better, but honestly I have no idea

I do. It is better. I have done a lot of vuln research. I can get way better than one shot level results out of “inferior” models.

For a long time with sleep studies they would give participants a single unit of alcohol. Alcohol has always trashed sleep, even when younger.

You can use LLM to write less code too. Just takes more intention. Which is kind of the whole point.

I also give the agent an mcp with combined FTS and vector based semantic search using sqlite-vec so it can search up things quickly.

Communication technologies have been evolving for billions of years

Amazing how technology existed before sentient life!

Just need your own LLMs to exhaust them. The future seems like it will be owned by whoever can automate with LLMs in whatever problem domain there is.

My agent will be in touch with yours, I guess.

An authnz aware egress proxy that also puts guard rails on MCP behavior?

Gee, that's starting to sound like a whole "bloated" framework...