A prompting-only fix for distribution faithfulness is a really clean result, temperature knobs were never enough haha.
@whats_ai
-
From 4o Vision Demo to Usable Computer Use: A Two-Year Journey
By
–
Took 2 years from the 4o Vision demo to reach usable computer use, way harder than the Twitter hype implied.
-
Open Memory Needed to Prevent AI App Store Monopoly Pattern
By
–
Open memory or this becomes the next app-store pattern all over again.
-
Breaking Down Scaling Laws in AI Research
By
–
The scaling-laws-as-one-thing conflation is everywhere, good to see someone finally breaking it out properly.
-
Distribution and Trust: Keys to AI Capability Deployment
By
–
6 months sounds about right, and most of that isn't raw capability, it's distribution and trust.
-
Gemini Deep Research experiencing issues for users
By
–
Is Gemini Deep Research broken for other people too?
-
Reconstructing AI timelines for informed audience understanding
By
–
One thing I am trying to do differently with these videos: not just explain who is right or wrong, but reconstruct the full timeline so people can make up their own mind with all the cards in hand. That part matters a lot in AI right now.
-
Why AI Stories Need More Context Than 30 Seconds
By
–
Most AI stories are told in 30 seconds.
That is exactly why so many people misunderstand them. Lately, I have been seeing the same pattern again and again:
viral clips, narrow takes, confident opinions… and almost none of the actual context. Then people ask me about those -
Qwen catches up fast on AIME-2026 benchmark
By
–
AIME-2026 #15 on first try after 30 min thinking, Qwen is catching up faster than I expected
-
Is Hermes Faster in Practice or Just Benchmarks?
By
–
Hermes actually faster in practice or just on benchmarks though?