Absolutrly cursed breakfast (I added gherkins to my ramen and egg) ((it was delicious))
Absolutrly cursed breakfast (I added gherkins to my ramen and egg) ((it was delicious))
I’m still seeing people sharing #LLM prompts like “You are an expert programmer. Write tests for this code, considering all edges cases…”.
This strikes me as a little bit delusional. This is not how LLMs work.
“You are an expert programmer” doesn’t change the output. People have cargo-culted that in from prose output prompts, where it _did_ matter: saying “write this essay as if you were an ancient Sumerian” produces qualitatively different output. But at no point did the LLM actually start believing it was an ancient Sumerian, because they don’t believe anything. Similarly, if you _don’t_ put “you are an expert programmer” at the front, it doesn’t suddenly start thinking “oh, my code can be rubbish, then,” (because it doesn’t think.)
“Considering all edge cases” doesn’t change the output, prove me wrong. Because all it does is pattern match your code. If similar-enough code with decent test coverage existed somewhere in its training set, then there is a good chance you’ll get half-decent tests out of it.
And I think this because I’ve been running experiments. And what I’ve discovered is that they are generally very bad at writing exhaustive tests, in the style that you want. I find it very worrying when I see people say things like “I asked it to write tests for the code, and 95% of them passed”. Yes, but what about the tests that it _missed_?
I don’t know whether it’s a context window problem, or that the “exhaustive” and “write like this” prompts are pulling the output in different directions.
However, I have discovered you get markedly better output if you first ask it to describe the tests in the #Gherkin #BDD language, and then ask it to convert the Gherkin to code, which does support the “pulling in different directions” hypothesis.
Seguimos con el tutorial "Automatización de pruebas BDD con Cucumber y Selenium" y he publicado la parte 4 donde exploramos la sintaxis del lenguaje Gherkin.
Nota: imagen generada con IA generativa.
🧩 Join Michigan Python: Make Testing Fun Again with Gherkin & Python!
Learn how to create human-readable test scenarios that your whole team will understand! Robson Luan do Nascimento de Sousa will demonstrate how Gherkin + Python can transform your testing approach using an exciting chess game example.
WHEN: 2025-03-06 at 7pm ET
WHERE: Washtenaw Community College or Online
👉 Details & RSVP: https://www.meetup.com/michigan-python/events/305384913/
Scampi, Chips, Mushy Peas and a Gherkin 😋
#Scampi #Chips #MushyPeas
#Gherkin #FishAndChips
#Food #Scran #Scranodon
🇫🇷 Intégration du framework de test #spockframework avec #Cucumber :
Les experts écrivent en #gherkin 🥒 le comportement et travaillent main dans la main avec le développeur qui va implémenter les assertions dans #Spock 🖖
Want to try contributing to an #opensource project? config-command is a #Gherkin project that has open issues. Check out this issue on GitHub: https://github.com/wp-cli/config-command/issues/180
On may 14 we have a new #meetup in #Eindhoven , We have @timobakx to speak about testing API endpoints using #Behat and #Gherkin Possibly a must-attend event if you develop APIs... ;)
For more information and RSVP: https://www.meetup.com/php-laravel-eindhoven/events/300028573/
JIRA + AI = LOVE или Как Product manager-у найти друзей и перестать страдать
Развитие AI-инструментов на базе современных LLM запустило в последние годы тренд на автоматизацию всего, что прибито меньше, чем на 2 гвоздя, и первыми адоптерами здесь традиционно выступает IT сообщество. Как Луи Пастер некогда ставил себе и друзьям намешанные на голой коленке вакцины, так сейчас разработчики активно ставят Code Copilot-ы, дизайнеры экспериментируют с Midjourney, скромно к этой очереди пристраиваемся и мы, Product Manager-ы. Меня зовут Алексей, и я более 15 лет занимаюсь управлением b2b-b2c продуктами и руководством командами в энтерпрайзе и стартапах. И сейчас предлагаю продолжить исследование того, какое влияние AI и ML инструменты оказывают на бизнес. Предыдущий эксперимент касался применения современных моделей машинного обучения в решении задачи прогнозирования цены в золотодобыче, в статье же ниже мы рассмотрим пример того, как очередные порождения ChatGPT могут помочь в управлении продуктовой разработкой и повысить эффективность взаимодействия в команде.
https://habr.com/ru/companies/raft/articles/799953/
#ai #llm #chatgpt #bdd #behavior_driven_development #gherkin #jira_plugin #product_management #qa_automation #three_amigos
They had one of those cooking competitions on TV, where pompous restaurant critics were selecting for the final round, which was to be at the top floor of the Gherkin, the (then) new gherkin-shaped sky scraper in London. When tasting a flawless dish, one of the judges had the habit of saying "I'd be happy to send this to the Gherkin".
My wife and I now say "I'd be happy to send this to the Gherkin" whenever we want to say that a thing is just right.
Finally there is a supported fork of SpecFlow: Reqnroll
https://reqnroll.net/news/2024/02/from-specflow-to-reqnroll-why-and-how/
Live Demo of #OpenSource `robotframework-gherkin-parser`
Now we can define feature files for defining test cases!
Feature steps map #robotframework keywords. RobotCode for Gherkin plugin adds run buttons to feature files so that we can execute test case within #vscode, too.