1/ One of the hidden details in this article on Microsoft testing process is culture and politics. Over a decade ago when a bigger company bought my startup, they had to go through a similar culture/politics

2/ My company was lean/agile, with daily builds that went through a full automated unit/regression test that could release daily updates to customers. Their company was Microsofty waterfall development with a long period of manual testing as part of the release cycle.
3/ Culture change becomes political as people defend their jobs. The workers skilled at manual testing may lose their jobs in a shift to purely automated tests, as they may not have the skills necessary to build automated tests.
4/ It wasn't simply testing. Their update packages were inherently brittle, built in a way that was likely to fail. They were unwilling to make the architectural changes necessary to avoid the brittleness.
5/ They were therefore convinced a long period of manual testing was needed and it took years to move them off that principle.
6/ Google (including Chrome) has automated regression tests that complete in a day whereas Microsoft requires weeks of testing. Weeks of testing means bugs deliberately don't get fixed because of the risk it might introduce an even larger bug.
7/ With automated regression/unit testing measured in hours, it means you are free to keep fixing that bug multiple times until you get it right, and it only impacted the schedule by a few hours instead of a few months.
8/ We eventually got down to hourly builds and release packages that were less brittle, but it took a lot of political/cultural fights to get there. A lot of QA folks were never quite convinced in the value of automated tests.

More from All

1. Mini Thread on Conflicts of Interest involving the authors of the Nature Toilet Paper:
https://t.co/VUYbsKGncx
Kristian G. Andersen
Andrew Rambaut
Ian Lipkin
Edward C. Holmes
Robert F. Garry

2. Thanks to @newboxer007 for forwarding the link to the research by an Australian in Taiwan (not on

3. K.Andersen didn't mention "competing interests"
Only Garry listed Zalgen Labs, which we will look at later.
In acknowledgements, Michael Farzan, Wellcome Trust, NIH, ERC & ARC are mentioned.
Author affiliations listed as usual.
Note the 328 Citations!
https://t.co/nmOeohM89Q


4. Kristian Andersen (1)
Andersen worked with USAMRIID & Fort Detrick scientists on research, with Robert Garry, Jens Kuhn & Sina Bavari among


5. Kristian Andersen (2)
Works at Scripps Research Institute, which WAS in serious financial trouble, haemorrhaging 20 million $ a year.
But just when the first virus cases were emerging, they received great news.
They issued a press release dated November 27, 2019:

You May Also Like