rene_d

Very clickbaity title, but interesting analysis of Reflection AI's Beam model.

To get calibrated probabilities sounds like a very good feature, if they are indeed well calibrated.

And in my experiments even Qwen 3.8 has a hard time to consistenly conform to a schema, requiring retries, JSON cleanup etc, so to have a model of similar quality (SemIf et al) that simply cannot deviate from the schema by construction could be very helpful.

But I still need to experiment with either Jev/SemIf myself.

Optionals handle this in zig:

  var value: ?T = null;

Write:

  value = 10;

Read:

  if (value) |x| x+=1