Loft engineer Jan Svoboda is studying Grammatical Evolution – a technique that mimics biological evolution as described by Darwin, to create new software. It’s able to generate computer code based on user-defined cost functions, such as unit tests. It creates random fragments of code and evaluates how good they are using the cost function. It then combines the relatively good solutions together, which usually leads to even better solutions. In this way, in theory, we can use AI to develop new software programs to achieve a defined goal, in any arbitrary language, based on a formal definition of its grammar.
There’s a great TED talk by Maurice Conti about Evolutionary Design, which is closely related. (The above screenshot is from this talk.)
For a more technical introduction, you can read this paper from Utrecht University’s Department of Computing and Information Science.
Date posted
31 March 2017Share
1 min read
More in tech notes
How much does security cost?
Simple question, difficult answer. Security could cost nothing, but end up costing you everything. COVID-19 has changed the IT landscape. Suddenly, security audits focused on offices and infrastructure are barely valid anymore. A large part…
7 reasons you should modernise your legacy systems
Application modernisation Let’s admit it. Every company has a skeleton in the closet - where one of the biggest skeletons is often a legacy system.What is a legacy system? Wikipedia defines a legacy system as: an…
Seven ways to optimise your AWS spend
In these challenging times, every business should be looking at their infrastructure spend to ensure every aspect is fully optimised to deliver maximum returns. This article by Loft Head of Engineering, Zdenek Machek, provides a…
New Relic as an aid to massive scalability
We have a number of large scale projects on at Loft at present, and with this in mind massive scalability is one of our primary areas of new research and development. We are looking at…
