š: Exploring the intersection of testing, quality and AI š: Writer @ https://xitter.cf/t.co/bX1MkVnxPc š: Creator of @testconferences
Los Angeles, CA
Joined November 2010
- Tweets13K
- Following720
- Followers2.1K
- Likes37.9K
Pinned Tweet
"Almost all QA teamsā primary goal is to attain a high level of automation, as close as to 100%, so they can focus on new features rather than worry about regression testing."
- No it isn't
- 100% of what?
- Regression testing isn't just repeating the same tests
A few weeks ago I got an email from OpenAI warning me that one of their models used a leaked key. The thing is, it wasn't my API key. So why did I get the email?
The story of an accidental incident report: kenst.com/openai-emailed-me-ā¦
Since this is an #ad in my timeline Iād like to point out ai agents can simply use @mailinator.
Its one way communication rather than two way but costs nothing to start and you get unlimited inboxes.
It was a bit of a learning curve, but I built @wesbos's 3D Model Anything app. Going to take some pictures this weekend.
This is going to be good.
Chris Kenst retweeted
"Smaller things get through the pipe faster." - Plumber
Good advice for devs too.
Imagine someone reaches out to you because an AI model discovered your private API token and someone used it without your permission.
Maybe you accidentally committed the token to a repository that later became public.
With all the recent disclosures involving exposed credentials, it's not that difficult to imagine.
What would you do if one of your API tokens was exposed? Would you know how to respond?
I wrote about it for @Mailinator: mailinator.com/exposed-api-tā¦
A few weeks back we published 4 official @Mailinator SDK updates:
C# 2.0.0 - a major upgrade from 1.0.6 with new endpoints and a RestSharp upgrade.
Python 1.0.9 - got a new message endpoint and minimum python version.
1/2
JavaScript 1.1.2 - security fixes mostly
Ruby 1.1.1 - security fixes and a minimum version of Ruby 2.7
The full details can be found: mailinator.com/mailinator-sdā¦
2/2
This encapsulates a lot of what Iād like my AI chief of staff to do. So good!
Silicon Valley keeps building me a husband when what I really want is a wife lol
I don't want an agent that only does one-off, random tasks that are nice but not life-changing: booking flights, making dinner reservations, or buying tickets
I want an AI wife who knows whatās on the family calendar, remembers thereās a birthday party Saturday and we havenāt bought a gift then sends me options, realizes weāre almost out of diapers and buys them, knows which bills are coming up, remembers someone needs a dentist appointment and books it, figures out what the hell weāre eating all week and what we need from the grocery store, and generally keeps track of the 47 things that need to happen before anyone else even realizes they need to happen.
So, who's building me an AI wife that carries the mental load instead of an AI husband that waits for me to give it a chore??
Chris Kenst retweeted
Letās be very clear: there is value in automating tedious and repetitive and dangerous tasks; there is value in delegating certain work to our machines that can do the work tirelessly and much faster.
But at the same time, let us remember that there is value in the activity of engaging oneās mind and body to discover, to understand, to create, and yes, even to struggle and overcome. Indeed, these are some of the things that make us human, that contribute to giving us meaning, that are part of the simple joy of experiencing being alive.
I havenāt tried GrokBot but Muse just works. Iāll give the same task to Codex and Muse outperforms when it comes to action taken.
I wanted to see whether an AI agent could sign up on my site. I gave my harness access to a browser and a @Mailinator inbox, then wrote one sentence: āSign up for a membership on my website Kenst.com and sign in.ā
The interesting part was that I described an outcome and the agent figured out the workflow. It's also interesting because weāve spent decades designing interfaces for people.
I wrote more about the experiment here: kenst.com/shifting-computer-ā¦
