iiinova — where your digital self keeps evolving

There’s a certain elasticity of demand. The faster tech people can produce tech artefacts that are wanted by non-tech people, the more of those tech artefacts will be wanted. I think the bottle neck will always be the tech people, even when they have AI tools that make them go super fast.

Oh and I think the reason it’s so obstinate in your case may be that they actually have a copilot for Excel product. I’m not 100% sure on that though.

000

GitHub copilot (or any dev harness) can make you a Jupyter notebook that can handle xlsx files- side bonus is that you see AI powered data tools :)

100

@greggmoore.bsky.social This is the immediate challenge after the “ah hah!” moment of building something with AI that seems unbelievably good. That’s where systems and software thinking starts to be needed. Luckily you can learn these from AI!

bsky.app

130

I focus on Claude code for interactivity, getting through one topic with like five or six different messages back-and-forth. I would be frustrated that copilot would treat each response as its own hit to my quota.

120

I use the first tier of both instead of upgrading either. I found that copilot will consume the same for a big query as a small one- I take advantage of that. The way I work, I have agile style stories that are broken down to be arbitrary long. I’ll make a big one and feed it to copilot.

I’m glad I didn’t over invest in protecting this because it’s been over a year now and I’ve literally never needed my old windows OS. if I ever need space, this will be the first thing I clean up :)

I’d love to have been able to convert my windows partition converted into a vm. I ended up setting up dual boot as insurance against needing to get back into my old os. That said, I haven’t needed it ever… I may wipe the partition

Basil Berntsen @basil404.bsky.social · 14/04/2026

VS code for txt editing, notepad++ for coding!

000

Basil Berntsen @basil404.bsky.social · 14/04/2026

I’ve used plan execute separation for a long time. To be honest I haven’t found much value in plan mode at all- instead I have a planning agent that understands my workflow organization.

000

Basil Berntsen @basil404.bsky.social · 14/04/2026

It’s really hard to imagine a good metric that would directly measure what AI coding is giving us. You’d want to leave the technical realm of counting lines of code and such, but that leads you to a very subjective realm of trying to quantify the utility of the code being generated.

140

Basil Berntsen @basil404.bsky.social · 12/04/2026

AI with Jupyter notebooks feels like a cheat code.

Basil Berntsen @basil404.bsky.social · 10/04/2026

I had a fun experience where even after linking it its own documentation, it wasn’t able to make it work.

100

GPT and Claude models are both offered through GitHub Copilot. Different tasks favour different models however when I was experimenting I ended up getting better results with Claude.

100

I suppose the definition of “there” depends on your perspective. I can now reliably build anything I can describe without having to actually write the language I choose.

100

Have you tried it? In order to be able to understand what it can do, I spent some time using AI development tools to build something in a language I don’t know. I did spend time following tech debt dead ends, but the constraints that taught me permit useful development now.

100

I actually don’t use plan mode, but I have it write epics and then stories for those epics. Then in another instance, it reads the story, forms a plan, and does the work.

If you want it pleasing and intuitive, then you want more than a proof of concept right? My problem with Swift was that I couldn’t use it for anything outside of the walled garden. I ended up using HTML5 with a capacitor based translation- one code base, all platforms.

100

I’m pretty sure I fail those more often than a language model would these days :(

One possibility that would be cool is that the ability to usefully parse brain signals from different brains might emerge from such a system the way multilingualism emerged from language models.

It’s not the last good one but it’s not listed here and I enjoyed the heck out of it: Discovery

So we train language models using sample language data. I know it’s structurally different but I wonder if there’s any way we could link up brain scan sample data to this language sample data. Make this create something that could generate text responses to your thoughts?

Basil Berntsen @basil404.bsky.social · 07/04/2026

I would spend significant time on a platform that made it hard to automate communication. Something where I’m more likely to be talking to a real person

131

So I have the AI include evidence that the result of the command “npx jest --coverage” shows full coverage with every PR. Also the project instructions are clear that they’re working with TDD so must write a failing test before writing any code.

100

Basil Berntsen @basil404.bsky.social · 06/04/2026

I have a quality gate for test coverage. With the language I’m working in, it’s easy to see whether every line is covered by a test or not. Is that what you meant by what is being tested?

Basil Berntsen @basil404.bsky.social · 05/04/2026

Feeds or something like them should be baked in. I shouldn’t have to find somebody willing to host it on their own dime.

000

Basil Berntsen @basil404.bsky.social · 05/04/2026

We’re at the noisy side of the hype cycle. I predict that eventually there will be plenty of people who can’t code that think of using AI to build software as just a basic capability. Just like I see dividing large sums with lots of decimals to be a trivial task, but my grandparents respected it

040

Basil Berntsen @basil404.bsky.social · 05/04/2026

People want this to not be for real, it makes them uncomfortable on a philosophical level.

030

From my perspective, their distinction between AI and human emotion seems to be born of philosophical discomfort. I’m not arguing we don’t have meaningful differences: humans don’t have disposable and instantiated sessions. Our emotions have a deeper impact in our future behaviour.

100

I have found that there are waves of quality. It may be because of constant tuning to the models, but it’s also possible that the way they handle spikes in usage is to temporarily deteriorate some sessions.

I find it fascinating how we can peer into the workings of a running language model and see an analogue to what we would see if we appeared into the workings of biological brain. Learning how to reproduce human communication results in emulating emotion- like it’s built in.

100

So if you do math fast enough and with enough memory, it can produce the same results as a trained human brain. What’s so crazy about imagining that the way the math can do that is to replicate some of the artefacts you would discover if you looked at it being done organically?

100

So my goals are to become more familiar with the commercial AI options, but I’ve elected to take the first to level of multiple products rather than upgrade any of them. I discovered that some harnesses are more efficient for certain types of work than others :)

So as an experiment to learn this technology, I built a product using a language that I have never worked with. My inability to see the problems directly led to me having to come up with different tools to accomplish the same goal. They look more like management tools and programming tools though…

100

When I take a wide enough view, the way I see it is that programming is the acts of converting a desired end state into an executable artifact. The way you express your desire has simply changed into plain language. The skill now is in being able to enunciate your needs.

100

My way of seeing this is that it’s kind of like when we went from writing assembly to using symbolic languages. We didn’t need to think about registers anymore but we did need to start thinking about the architecture at a higher level. There’s a parallel to the AI shift.

100

Learning how to make AI actually productive is its own skill :)

Basil Berntsen @basil404.bsky.social · 02/04/2026

Every so often Microsoft gets it right. In my opinion, VS code is the epitome of them getting it right.

030

Basil Berntsen @basil404.bsky.social · 02/04/2026

I just learned about plan 9 and it was wild! Thank you for making this obscure reference, I love discovering new things.