From a first experiment to everyday work. See how others use basal — and add your idea to the story.
I use basalEach story comes from a model user and appears after administrator approval.
In SemanticHub, we match articles to thematic targets — for example, “Medical websites” — to select material suitable for a particular website or campaign. Previously, we used a Jev cascade, costing around USD 1.42 per 100,000 as…
As part of my tests, I have tried flagging suspicious emails. At the moment, I am testing the model (4.5M) on a Mac M1 and it runs rather slowly — 17 seconds per request — although this may be down to that particular hardware.
We are currently testing Basal and Laya against our existing solution based on a traditional LLM. The traditional model still performs best, but it is extremely slow compared with Laya and Basal. Laya is fastest, but its assessme…
I am testing basal-1.0-4.5B as a food-product classifier. The model receives only the product name and brand, then chooses one of eight categories described in plain text in the request, such as “dairy and eggs”, “snacks”, “ready…
An experimental decision layer for an autonomous AI engineering workflow. I am testing basal as a small System One model for fast classification of problems, failures and findings before harder cases reach larger reasoning models…
You don't need a large deployment. A small experiment can inspire someone else's next step.
Tell us about your use case