TESSERA gets its CVPR debut in Denver, the BBC hedgehog story trots on into national news, and the European Space Agency puts our model on their homepage!

TESSERA on the ESA homepage and at CVPR, GeoTessera 0.9 stabilising onto S3/Zarr, io-uring in OCaml, carbon credits in New Scientist and WSJ, and musings on internet malware again.

Publishing the OxCaml Labs year-one review, POSSE and AI content disclosure for the web, adopting the geo-embeddings Zarr convention for TESSERA, action PROPL at PLDI, the death of the grant application, and NASA's new swathe lidar mission.

Community feedback reshaped our Zarr store layout — years became a dimension, shards got bigger, and we retired the TESSERA-specific convention in favour of a shared geo-embeddings standard that also covers other models.

Reworking the TESSERA Zarr store layout after community feedback, Springer's API woes for evidence synthesis, vibecoding introspection, and git remote helpers for ATProto.

Evidence synthesis at the DEFRA science conference, TESSERA transcoding and building a new SPA, OpenStreetMap/DuckDB bindings in OxCaml, and early thoughts on vibecoding etiquette.

How we restructured TESSERA's geospatial embeddings from millions of individual numpy files into sharded Zarr v3 stores for efficient HTTP streaming, enabling everything from single-pixel mobile lookups to regional-scale analysis with just a couple of range requests.

TESSERA streaming in the browser, planetary programming at WG2.8, biodiversity action papers, FP Launchpad opens, and Docker CACM buzz

Got TESSERA working in Zarr and the browser, and a preprint of package management a la carte pushed out

TESSERA paper accepted at CVPR 2026, went to the AI Impact Summit, OCaml Zarr hacking, Shriram's talk on human factors of formal methods, and discussions on teaching OxCaml to agents.

Trip report from the Indian AI Impact Summit in New Delhi, covering the massive expo, a conversation with Yann LeCun, a hackathon/talk at IIT-Delhi, networking at the British High Commission, and reflections on the summit declaration's shift from safety to progress and equitable access.

First TESSERA hackathon held at the Indian AI Impact Summit in Delhi, exploring integration with IIT-Delhi's CoRE Stack for geospatial analysis and testing TESSERA labeling workflows.

Growing the Ceph cluster for TESSERA embeddings, a Lego brainstorming session for the Evidence TAP, hosting Echo Labs from ARIA, and Shane's IUCN Red List seminar.

PhD viva for Maddy, presenting TESSERA at ARIA, Nature covers the conservation evidence conference, giving evidence to Parliamentary POST, and a CACM interview.

Hosting the UK chief scientists for nature conservation at Pembroke to discuss TESSERA and AI for biodiversity, followed by the Conservation Evidence conference where I talked about choosing the open red pill over black-box AI for conservation decision-making.

Deploying an OxCaml zero-allocation webserver, OCaml CI maintenance and opam versioning, and OCaml Workshop and FOSDEM talks

Tracking TESSERA activity including a new preprint and podcast, wrestling with Zarr, and saying farewell to David Allsopp.

Scaling TESSERA embeddings on Vultr AMD GPUs, speaking at the AI4Nature launch in London, and picking up Tomas Petricek's new PL book.

Workshop report combining TESSERA geospatial foundation models with Concordia agent-based modeling to simulate ecosystem resilience, covering causal modeling for ecology and AI applications in nature conservation.

GeoTessera 0.7 switches to GeoParquet manifests for faster initialisation, adds Zarr tensor storage support, and provides new sampling APIs for building downstream tasks like solar panel detection.

Release of GeoTessera Python library and CLI for accessing TESSERA geospatial foundation model embeddings with interactive visualization tools.