Innovation That Matters

Gaza

Gaza Strip area: 365 km²

Gaza Strip population (2022): 2,375,259

Isle of Wight area: 381 km²

Isle of Wight population (2019): 141,606

When people face an existential threat they will fight to the death. What other option is there?

Not optimistic this cycle of violence between Israel and Palestine will be broken anytime soon. I fail to see what the plan is, on either side. Hawks in Israel seems to think they can push the Palestinians into Egypt, or kill enough that they are no longer a people; just a displaced and subjugated minority, living in a reservation.

As the old “joke” goes, the irony of the US selling/sending Apache helicopters to deal with ethnic cleansing and genocide is lost on many…

May 16, 2024 0

Modelling 101

In this article I would like provide some high-level guidance for domain (data) modelling. This article is for you if you are relatively new to domain or concept modelling. It uses Accord Project Concerto but the principles should apply to many modelling languages.

May 2, 2024 0

Zig Programming — Trial by JSON

The past couple of days I’ve been learning Zig, a relatively new low-level programming language, described by its creator as “a DSL for assembly”, and a potential successor to C.

Continue reading →

March 20, 2024 0

Semantics of Contracts and Clauses

One of the more challenging aspects of digitising contracts (making then computable) is understanding how to assemble a contract from a reusable set of clauses. There is inherent tension between the notion of a clause as an atomic reusable snippet of text, and the assumptions that a clause makes about its host contract, or the other clauses that must be present in the contract.

In this article I dive deeper into what assembling contracts from clauses means in terms of semantics, and sketch out some Concerto data models to capture those semantics.

Continue reading →

March 13, 2024 0

Miss Manners with Claude Opus

I repeated my experiment with the Miss Manners benchmark using Clause Opus (Clause Pro). The results were better than GPT4, but inferior to Mistral (Large).

Continue reading →

March 7, 2024 1

Miss Manners LLM Benchmark

Recently I’ve been evaluating the ability of LLMs to perform simple reasoning, using the Miss Manners benchmark. This article ranks the LLMs on this benchmark and summarises the results.

Continue reading →

February 28, 2024 2