News for hackers. Stuff that matters.
Re:Qwen3.8-27B by enraged_camel on Friday August 14, 2026 @01:26PM (#49301866)
>> We have an internal eval that measures performance on tasks for a handful of embedded systems repos for our mmWave radios

Okay but the parent said real-world usage, presumably meaning coding tasks.

We have a whole bunch of complex evals that Haiku 4.5 passes. That doesn't mean it is a good model for coding.

Re:Qwen3.8-27B by spmurrayzzz on Friday August 14, 2026 @01:36PM (#49301999)
Yes, these are coding tasks in the embedded systems domain (I mentioned Rust and C).
Re:Qwen3.8-27B by graceful6800 on Friday August 14, 2026 @03:00PM (#49303165)
They literally stated in their first sentence that it was coding tasks.