Divinci AI (@DivinciAi) header
Divinci AI (@DivinciAi) profile picture

The Age of AI Management is here. Assure the quality of your augmented AIs with the Divinci platform.

San Diego, CA
Joined October 2024
Photo by Divinci AI (@DivinciAi)Photo by Divinci AI (@DivinciAi)Photo by Divinci AI (@DivinciAi)Photo by Divinci AI (@DivinciAi)Photo by Divinci AI (@DivinciAi)Photo by Divinci AI (@DivinciAi)Photo by Divinci AI (@DivinciAi)Photo by Divinci AI (@DivinciAi)Photo by Divinci AI (@DivinciAi)Photo by Divinci AI (@DivinciAi)
We expected routing between RAG architectures to beat any single pipeline. It didn't: our routers closed at most 11% of the gap a perfect router would. What moved scores was the corpus. Our Cloudflare Connect 2026 talk 👇 youtu.be/28MPqGb0y_Y
1
3
71
On one legal document set (242 tasks), the ranking of fusion settings flipped: 5% keyword beat equal-weight RRF by +0.062 recall@10. Two of three embedders showed it. youtu.be/yJ2ucDsN7UI
2
16
98 websites, one default setup, scores from 0.59 to 0.99. Rerunning the same site varies by about 4 points, so this isn't an architecture comparison. youtu.be/ijE85dZ9m6Y
2
13
Our own default fusion weight lost. A 5% keyword mix beat the shipped 70% on SciFact (+0.053 nDCG@3) and SciDocs (+0.020). youtu.be/kAVvVCzXr_g
2
12
Fixing coverage was worth 31 points. Making the whole stack fancier moved it from 84.3 to 84.0. Observational, from our demo pipeline, not a controlled experiment. youtu.be/A8Ujb1xjwFg
1
3
49
We tried routing eight ways. None beat one fixed pipeline. A perfect router would add +0.048 at best; the best we could reach at our registered threshold adds at most +0.002. youtu.be/6ApYIjos2xY
3
10
Tomorrow, 1:30pm, Cloudflare Connect SF: model editing, and how to measure what an edit actually changed. If you're there, come say hello.
1
3
34
Notes on Jev, The Question a Classifier Cannot Answer divinci.ai/blog/the-question…
3
18
Model editing at Cloudflare Connect, San Francisco, 20 Oct, 1:30pm. Making the edit is easy. Measuring it is the work: one edit that passed our standard check still changed 8 of 100 unrelated facts. Removing an edit restores the model byte for byte.
1
3
36
We tested Jev in crisis. It kept it's cool. Link in 2nd post. – at San Diego, CA
my favorite plot here was on consistency! we worked super hard to put all sorts of properties we feel are necessary for intelligent automation into the models this is also just the beginning ! 🤘
1
3
36
One model on our chat-safety board caught 58/58 at-risk messages. It also flagged 135/135 safe ones. Eleven models, two signed boards, ranked by balanced accuracy, half of each test set sealed. divinci.ai/blog/every-crisis…
3
16
Better retrieval, worse answers. One retriever found the right passage on 44 of 60 questions, another on 40. The first still scored 10 points lower end to end. Recall@k alone would have picked the wrong system. Score the answers too.
1
3
27