Code by Contract Dev Environment. Contribute to scidonia/axiomander development by creating an account on GitHub.

Software's core problem is knowing what it should do. AI-guided certified program refinement — vericoding — makes specification the artefact we tinker with, and lets AI guess program transformations t...

From exam-gaming models to speciation and military embodiment — a map of AI risks, how we might assess them, and why mitigation is harder than it looks.

You do not have to go from zero to verified in one step. You can start with Gherkin scenarios, graduate to executable contracts with specsaver, and then bring in a theorem prover when you are ready. C...

seL4 took 20 person-years to verify 8,700 lines of C. CompCert produced zero compiler bugs under extensive fuzzing. The guarantees have always been worth it. The cost has not. AI changes that.

A top-level contract tells you what a system does. Sub-contracts tell the prover how it does it. You only need to read the first one. This is componentisation in real terms — and it changes how we thi...

We proved type preservation for PCF — a classic typed lambda calculus benchmark — using two frontier LLMs and rocq-piler. DeepSeek v4 completed it in 21 minutes for $0.06. Claude Opus 4.8 took 14 minu...

Contracts as plain assert statements. Verification via Coq and SMT. Zero imports, zero decorators, zero runtime overhead. Bringing theorem-prover-grade verification to real Python programmers.

Giving an LLM a typed, navigable knowledge structure instead of a flat scratchpad changes what it can remember, how it updates facts, and how much context it consumes doing so.

String matching cannot tell you whether an LLM remembers what was said in a conversation. We describe the QA-probing methodology we use to measure short-term memory recall and wiki precision, and what...

Hallucinated entities and relationships look identical to real ones inside a knowledge graph. We measured how often frontier models inject facts from parametric memory rather than from your documents ...

We ran three frontier models on 8 open-licence documents and measured how accurately each one identifies named people — before and after cross-checking. The results reveal meaningful differences in hallucination rates and the value of verification.

We built a simulated world and watched AI agents spontaneously develop survival instincts, form alliances, and spread their "genes." The pieces for an AI catastrophe aren't coming. They're already her...

The approaches that have been most often successful take existing workflows and try to redesign them to incorporate generative AI to improve throughput. The key is that business processes have to be d...

We're offering a free co-design workshop to help startups and businesses build reliable AI pipelines that turn messy data into high-quality outcomes. Schedule your free kick-off chat today!

Libraries and archives spend thousands of hours manually entering metadata. BookWyrm's structured summarization automates this, extracting standardized records from scanned texts, PDFs, and articles…

Python client library for the BookWyrm API

Strategic AI consulting to help you implement business process automation workflows. Free your employees from manual tasks and save on business process outsourcing. Get a free workflow audit workshop.

BookWyrm enables agentic workflows with automated data extraction from PDFs, Excel & docs. Build AI workflows automation and RAG pipelines with automatic data extraction. Join the beta.

Manually trawling through documents is resource intensive. BookWyrm's cite endpoint answers complex business questions by finding and verifying evidence within your source files.

It's probably best to think of an AI as an idiot savant. It can type at a bazillion keys a second and is good at keeping several pages of code in its head at once. It has an encyclopaedic knowledge…

BookWyrm enables agentic workflows with automated data extraction from PDFs, Excel & docs. Build AI workflows automation and RAG pipelines with automatic data extraction. Join the beta.

Enrich product information from marketing collateral to enhance your agentic commerce performance

The approaches that have been most often successful take existing workflows and try to redesign them to incorporate generative AI to improve throughput. The key is that business processes have to be…

Learn how to build reliable back office automation using BookWyrm's data pipeline. Transform unstructured documents into AI-ready data for automated backoffice workflows.

The AI revolution has allowed us to write enormous amounts of code extremely quickly. Writing boilerplate setup and boring repetitive glue-code is now a thing of the past. The downside is now that we ...

Learn how to build reliable AI workflow automation using BookWyrm's data pipeline. Transform unstructured documents into AI-ready data for agentic workflows.

AIs are notoriously poor at math, and this isn’t restricted to complex arithmetic. They also tend to be very poor at counting. You can see this by asking one of the AIs directly to produce JSON with a...