zrg
zrg on Hacker News
allot of the models are just constantly eval maxxing
Posted by
zrg on Wednesday September 23, 2026 @02:04PM
from the bearing-linter.com dept.
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
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
Posted by
zrg on Wednesday May 07, 2025 @03:02PM
from the cosine.sh dept.
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?
Posted by
zrg on Monday August 12, 2024 @10:49AM
from the cosine.sh dept.
GraphQL doesn't solve engineering problems it solves human problems. It's a mechanism to patch bad employee communication
Posted by
zrg on Tuesday March 19, 2024 @09:28AM
from the github.com dept.
Isn't this the job of a catalytic converter?
F# is now supported within the .NET core world so it opens up the deployment scenarios beyond anywhere traditional .NET would live.
I give gitlab 2 months before they implement and launch encrypted git
AMD are actually selling a portion of the GPU stock in bundles so that they don't all get snapped up by miners.
With any luck this might make google rethink their strategy on AMP page prioritisation