Blog
Explore our latest insights
Delve into our recent articles, offering a diverse range of topics, expert perspectives, and thought-provoking ideas across various fields.

Using LLMs for Descriptions of Plants, Insects, and Fungi
We tested LLMs to improve multilingual descriptions of plants, insects, and fungi where Wikipedia entries were inadequate. GPT-4o outperformed smaller models such as GPT-4o mini and Mistral Pixtral 12B, especially in grammar and factual accuracy. It performed better in widely spoken languages and common species. In the end, GPT-4o was used to generate descriptions in 28 languages, providing better coverage for the Kindwise API.
.png)
Production release: insect.id & mushroom.id
Explore the exciting news and improvements in insect.id and mushroom.id comming out with production release.

Summer 2024 Plant.id Model Update
The Plant.id model upgrade resulted in significant improvements in accuracy. It reached over 85% accuracy in the first response (TOP 1). The increase is greatest for European and North American plants, with 6.0% and 3.6%, respectively.
.png)
Admin panel - new enhancements
In our efforts to introduce new features that cater to your clients and enhance their experience, this time we directed our focus towards you, our valued customers!

Suggestion filters: create custom species lists
Plant.id now allows plant species to be filtered by various criteria such as geographical distribution, morphology, ecology or practical use. This increases identification accuracy and confidence in the model.
Our most popular solutions