Yes one of our background agent is tasked with this exactly. I think you could do this via CI as well. We handle it via hooks and background agents but the goal is the same.
I think both factors are important as the goal is generally to help with planning and prioritization. A straight-forward but long task is still "expensive" with regard to prioritization and will take a while even if the cognitive load is not super high. That said, I think the observation that cognitive load is a good thing to watch out for as it introduces more risk to the estimation is very valid.
I recently posted a blog post about CodeYam, which is a software simulator. It creates simulations of every aspect of a software application - basically every function, both in isolation and in the context of the app or other function that import the original function.
We've put together a brief demo demonstrating how the software simulator can benefit a pull request workflow, creating simulations of all changes and making it easy to add/edit simulations and save them as part of a test suite. Would love to hear any thoughts people have on it.
This is all automated. It's a github app that tracks changes as they come in, analyzes and simulates them and creates simulations that can be accessed via the CodeYam website, integrated into a CI workflow, or, hopefully soon, leveraged in developer workflows.
In this way there's no set up or maintenance required (or very minimal). It updates simulations as changes are made so everything is always up-to-date.
It automatically generates a number of scenarios (data that is fed into the simulation), but you can define new scenarios through the website as well (or describe a scenario for the AI to generate).
My team and I have been working on a software simulator. It deconstructs software projects, creating simulations of all components (front-end and back-end) in isolation and in context, so you can easily see, test, and share any area of an application or the application as a whole. The blog post has more details.
It's starting to work pretty well and we're looking for people who might be interested in trying it out. Would also love to hear any feedback or questions people have about the concept.
If you want to try it out and don't want to register via the website you can email me at my first name (jared) at puzzleschool.com and I'll send you the zip file containing the cards and a few sample programs that can be printed out and photographed directly.
I was running an afterschool program teaching kids to code and we were looking for a way to have them code that was more social and group oriented rather than having everyone hunched over a computer more or less by themselves all the time. I was also looking for a project to explore Computer Vision and Machine Learning. This ended up being a good fit for both needs. The video on the website shows the students working on it. It's surprisingly engaging for being just paper cards you are writing on...
I've thought about it a bit. I realize the title is annoying on Hacker News, but I think the title is ok within the general context of my blog for those who read it regularly.
I'll think about another title, and I'm sorry (sort-of as I've enjoyed the debate here) for the sensationalist title on Hacker News, but I don't think it's a huge deal outside of this specific context...
1) There are no requirements for students to be "involved in the process of planning their own education". They are only required to be attend school a certain number of hours per year (I'm not sure the exact number), and serve time on the judicial committee. There are no requirements at all around any educational goals.
2) Sudbury Valley School operates on less money per-pupil than neighboring public schools.
3) The only requirement for adults who work as staff members is that they are capable of treating students as equals.
I apologize. I don't have specific stats to share on the college success. The books published by the school have a lot of anecdotal evidence regarding the students having success in college. They don't seem to have universal success or significantly greater success then their peers from other schools, but they do seem to be able to handle and graduate from college and have gone on to a wide-range of jobs.
I should not have simplified the argument to claim that they have universal success.
I'll do my best to write more posts getting in to the specifics, but my observation so far is that none of the extreme possibilities happen. There are problems. There are expulsions. Not many, but they do happen. The students don't magically learn everything on their own, but they do seem to develop in to competent, thoughtful, curious adults on their own...
Ok, so would you predict that most of those who get accepted to college flunk out or are unable to get jobs?
I can certainly appreciate that this might not actually be "mind-blowing", but personally I think even the college-acceptance rates are a surprising result.
I don't think it's reasonable to assume that these students have any higher IQs than the neighboring public schools. I have not found any evidence to suggest that.
Yea, I know. It's tough to strike the right tone in the blog post and in the end the format was structured to be readable and get attention as I really do just want people to think about these ideas more, even if in the end they don't agree with them.
I agree. The students at Sudbury Valley and the families are not representative. That said, there is no application process outside of making sure you want to be there and your family is on board. They are not filtering out lower-performing students at all.
But it is certainly possible that this model would fail miserably when applied more generally. I don't think that can be the null hypothesis, though...