Martin Fowler 1 hr ago

Experiences with local models for coding

Birgitta Böckeler now reports on her recent experiences trying local models for coding. She compares them using two standard tasks, and tries out the most pr...

1 min read Read

Martin Fowler 1d ago

Viability of local models for coding

Birgitta Böckeler recently spent some time trying out running local LLMs for some programming tasks. In this memo she outlines the factors that influence how...

1 min read Read

Martin Fowler 2d ago

Fragments: July 6

Last week, Thoughtworks ran a second Future of Software Development Retreat, this time in Europe. As with the previous event, I’ll be sharing some fragmentar...

9 min read Read

Martin Fowler Jun 16

Fragments: June 16

“Prag Dave” Thomas (co-author of the outstanding “Pragmatic Programmer”) has loved programming since he was young. Programming was how I could express myself...

7 min read Read

Martin Fowler Jun 16

Building Reliable Agentic AI Systems

One of the most interesting projects my colleagues have done with LLMs has been building a system with Bayer to allow pharmaceutical researchers to query dec...

1 min read Read

Martin Fowler Jun 2

Fragments: June 2

Greg Wilson has noticed that lots of folks are using dodgy metrics to figure out if AI tools are worth their costs. Would you measure lines of code generated...

10 min read Read

Martin Fowler May 27

Fragments: May 27

At the GOTO Conference in Copenhagen in 2025, Kent Beck and I spent some time on stage talking and answering questions from the audience - a format I refer t...

9 min read Read

Martin Fowler May 27

The test suite as a regression sensor

Birgitta Böckeler finishes her post on sensors for coding agents by examining the role of a test suite as a regression sensor, focusing on the role mutation ...

1 min read Read

Martin Fowler May 27

The VibeSec Reckoning

Vibe coding has significantly accelerated software prototyping but AI agents frequently recommend insecure configurations, creating security problems. Gautam...

1 min read Read

Martin Fowler May 21

Bliki: Vibe Coding

Vibe coding is building a software application by prompting an LLM, telling it what to build, trying it out, prompting for changes - but without looking at a...

4 min read Read

Martin Fowler May 14

Fragments: May 14

Last week I spent a day at The Orchard Retreat, hosted by Mechanical Orchard. that brought together several people working in software development to talk ab...

12 min read Read

Martin Fowler May 14

Bliki: Interrogatory LLM

When we need an LLM to perform a complex task, we often need to feed it a lot of context. Coming up with a design for a new feature requires descriptions of ...

3 min read Read