News for hackers. Stuff that matters.

d-sanoj

It is just we are not able to comprehend it until someone pointed it out.
Congrats on the launch. This seems interesting.
Re:MAI Code 2 and Code 2 Flash on Tuesday November 17, 2026 @03:08PM (#50537419)
I don't put much weight on launch benchmarks for coding models anymore. I think most of us use OpenAI and Anthropic models anyway. These models will catch up sometime with the OpenAI and Anthropic and maybe then there could be a difference where we could actually reply on. For example, if we consider image generation, nano banana was better and so were image models like Qwen and Flux which provide same if not sometimes better outputs.
I think the harness matters less when we are measuring the work done. There are all kinds of benchmarks in differ cases showing one model is better than the other. The existing ones like Claude Code or codex work well with their models.
Re:How the Claude Code team thinks about verification on Tuesday November 17, 2026 @02:59PM (#50537260)
I had an agent write a feature and its tests, and the tests were green while the feature was wrong. The tests just agreed with the bugs sometimes.