← All IntelClip / AI Tools
Still competent at 63% context, and a single-shot control test
From Ling 3.0 Flash First Test – A Surprisingly GOOD Coding Model! · ≈14:59
Long-context degradation is the usual failure for models this size, and the reviewer pairs the observation with a no-iteration chat-interface test to isolate raw first-response quality.
What’s in it
- Long-context degradation is the usual failure for models this size, and the reviewer pairs the observation with a no-iteration chat-interface test to isolate raw first-response quality.
Clip transcript
This is actually all right, especially for the size of the model with this few active parameters. I'm okay with this. And it's continuously fixed some issues. I mean, context used up right there, 63% of the 256K, and it was still competently fixing things. So, I like to see this. I want to now give it the 3D watch website test, but here from within the chat interface in Open Router, so without the ability for it to first generate a script, and then be like, "Okay, I want to fix a bunch of things here." I want to just see what it actually comes up with when given no opportunity to iterate past the first result that it thinks of. So, this is of course the website for the Slap Ass
Recommended reads
Comments
Sign in to comment.
Loading comments…