Let's make quality the System One Month
This is actually pretty cool. I think the undertalked about part of this for TypeSafe is that they generate reasonably reliable text which doesn't need to be solved by AI. Signed up for the beta! :) would love to see parsing/ocr covered in future benchmarks. The Doom demo really sold for me that this could be a complete game changer for local applications.
This is the sweetest thing I've seen in a minute. The whole thing is a
Will need hands on to truly tell, but the doom demo seems very promising. If it can play chess and rubic cube better than LLM ? ( may be go too ? ).
This is amazing. I wonder if this could be a great tool for accelerating QA at my gamedev studio. Signed up for early access. One application that sounds pretty interesting would be the litmus test. "Does not hallucinate" is not the same as "is never wrong". So the ATC test could be the benchmark. Many big companies are starting now to test agentic coding to automate business processes. This could be a complete game changer for local applications.