Hacker Newsnew | past | comments | ask | show | jobs | submit | yehosef's commentslogin

"I told it not to deploy until it was fixed."

if Linus has unrestricted access to Mythos.


or anthropic forks linux. one day ai may fork us all



I'll be impressed when they can create an entire cell from scratch and it will start to divide. They can create all the needed precursors, bypassing millions of years of random permutation. Because until you have an entire working cell with replication, you have no retained benefit.


Evolution is so smart.


Monte Carlo smart, not optimized compiler smart.

Like the way slime molds solve mazes: explore every possible path in parallel, and push growth in all areas with greater nutrient gradients. Not by sensing any gestalt clues, like symmetries in the maze design.

Astoundingly stupidly smart.


like draw and quarter?


can an architect review a system he didn't design or build?


If you never coded that architecture yourself, you are not able to tell if it fits the problem, pros and cons, if the implementation is in accordance.

Imagine reviewing CQRS without having built one


With all the people saying that you're going to have problems because the LLM is not good at refactoring or large code bases or OOP, etc. the point may be that if you're working to develop skills, an LLM herder might be a good one. Even if the models are almost, but not quite, good enough yet - they will be.

When looking for a career move you might want to focus on the trajectory more than the current state.


can you say which llms you're using? have you tried different ones and how were they?


Team is a mix; I'm personally using Codex, gpt-5.5 high fast + Claude Opus 4.6 (occasionally Sonnet 4.6).

Mix of CLI (Codex) and GH Copilot (if I want active line selection).

We have a set of custom skills and knowledge base as well.


this is the pitch - it's open source, run it yourself. But >99% of people will not have the hardware needed to run these models at a high enough quality to be close to SOTA. So they will run the open-source models on CCP systems for a good price.


What I mean is you can use providers who also host deepseek models for pennies without touching deepseek itself.


I’m only seeing 3x the cost of DeepSeek for other providers on Open Router. Is there a better place to look?


I haven't really had this issue but deepinfra claims to have us servers and looks pretty cheap to me.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: