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

allot of the models are just constantly eval maxxing


I'm currently very much on the jujutsu train as the author also mentioned, i do recommend y'all give it a try


I've written go most of my career. I've "written" tonnes of AI assisted go. Since February however all my new software projects and production services have been written in rust. I never even wrote rust before December. I've barely even looked at any of the source code, I find i just trust the AI to write rust way more.

But perhaps that's also a side effect of maybe having prior opinions about go and the number of foot guns I've let off


tldr it is not


This is one of the approaches im considering for my own, Roder.

The approach mostly being communicating over json rpc which has become the standard for MCP so it makes it more approachable to agent developers.

Obviously its very much NOT mcp, its a low level events based rpc system for registering capabilities and extending low level primitives of the agnet itself not the model


I'm actually very close to being ready to release exactly that also in rust. I completely agree with your statement, extensibility is the most importnat feature.

https://x.com/PandelisZ/status/2055633346831548902

The two things I want to get right before actually releasing it is properly eval it againt other harnesses and make sure its better.

And the licence. I don't think a GPL licence will yield addoption so I would like to MIT Roder or figure out the right licence


I've been experimenting with providers offering similar functionality for the last year and it is really vastly superior experience this codex like approach than cursor, devin etc


I posted about these guys last year when they published at the time what was a sota swebench score in summer 2024. Does anyone have insight into what they are doing to achieve this?


I posted a blog post by these guy's last year where they also claimed to have a SOTA swe-bench score in summer 2024. They seem to be reporting even better scores than o3. Does anyone have insight into what they are doing? Is this legit? Or are they eval maxing?


GraphQL doesn't solve engineering problems it solves human problems. It's a mechanism to patch bad employee communication


Stating this alternatively, it removes the need for coordination and communication and allows teams to work independently. Which is good.


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

Search: