I would expect most drivers to support (anonymous) stored procedures so you can batch/pipeline multiple queries into one statement to be executed by the database. Probably more a problem of developers not knowing how to use databases properly, not so much a limitation of technology.
Voters in democracies are usually not people who deeply understand issues. We outsource that to politicians, but politicians have a second agenda, serving the people who paid their campaign.
I don´t see why industrialized software development with AI Agents could not be better at quality. Medical equipment or airplane safety requirements validations are also done in an industrialized manner. We don't really care if engineers working on these products like what they are doing or they feel like a craftsman.
You do need to regulate what is common sense to protect employees. There's a lot of pressure from employers to do things that go against common sense, accidents happen. The employee is hurt, employer doesn't care. A large role of regulation is to protect employees from greedy employers. That's why some employers like illegals, they don't complain about not following regulations.
Everything is getting industrialized. We buy most products made in China (tv,laptop, mobile phone etc), furniture is mostly cheap IKEA furniture. Many craftsmen lost their profession to industrialized automation. If we don´t care our furniture is subpar, our products are cheap plastic china products, why do we expect anybody to care about software craftsmanship?
Sure, it's not yet clear what impact LLMs will have on software development, but the impact it will have will not depend on if developers like to use it or not. If it is going to make software development 10x faster, companies will adopt it, whether devs like it or not.
But does anybody really care about what you like? What about all those other professions that got replaced by technology, did anybody care what they liked? The big question is how is software going to be build most efficiently and most effectively in the future and how do you prepare yourself for this new world. Otherwise you’ll end up with all those other professions that got replaced, like the mineworkers, hoping that the good old days will someday return.
I moved from a lenovo thinkpad p1 gen 2 core i9 32Gb (2020) to a macbook pro m1 max 32gb (2021), and the experience in parallels beats the experience in the lenovo machine.
That's also just something you can include in the prompt in Claude, instruct claude to ask questions until it is completely clear about the database schema you need. See this video: https://youtu.be/i4Jfl1IW-_U?si=yXiFvanIjGgZjQRA&t=178
In my experience most AI coding tools can work with databases, especially if you give it an MCP tool to connect to your (development) database. It will generate mermaid er-diagrams by reading from your database catalog, it will generate SQL to create tables, views, etc. It will generate queries, validate them and return data. It will optimize your query performance by running the query, running explain plan, looking into pg_stat_statements (or whatevery your database uses), and propose SQL optimization, indexes to be created. It will also create demo data with realistic use cases like black friday or back to school discounts for prices, etc.
A SQL MCP + mermaid is all you need.
Btw, it can also do an awesome job turning query plans into readable mermaid flow diagrams, adding details to the chart, using color to highlight bottlenecks.
Maybe it's about adding knowledge to LLMs, and not how many people read your website? I would be very happy if i had a simple way to get my insights, knowledge and best practices into the next version of an LLM so I have a way to improve it.
I'm running linux, millions of lines of code i never verified, and may or may not have been verified by trustworthy people. In the end it's one big risk. When i'm developing in go, it's pulling in many lines of code i don´t have time for to validate, same with java, so many jars. Who knows what i'm running...
Agreed, and that is why big countries should also be broken up. No more countries over 50m citizens. Many people in Europe don’t want the EU, but there’s really no alternative when competing with large countries like China and US.
I wrote a swing app a long time ago (20+ years ago) that was used in operating theaters to register organs for transplantation. Swing has saved many lives since. Swing has been good enough for a long time.
Most teachers want to do better, but are stuck in a system where they're not able to. Overwhelmed with large classes, small budgets, ridgid programs, demanding parents, it's hard to also dedicate energy to reflection or student attention.
You’re free to avoid it but maybe your competition will do it and may outpace you because of it. Conways law just states that architecture follows organizational structure so it’s only to be expected that ai generated software has an ai influenced architecture.
I expect much of this can be solved with better architecture: smaller, more independent components. Break large code bases up into independent libraries, and LLMs can work again because they need much less code in their context.
I’ve experimented with feature chats, so start a new chat for every change, just like a feature branch. At the end of a chat I’ll have it summarize the the feature chat and save it as a markdown document in the project, so the knowledge is still available for next chats. Seems to work well.
You can also ask the llm at the end of a feature chat to prepare a prompt to start the next feature chat so it can determine what knowledge is important to communicate to the next feature chat.
Summarizing a chat also helps getting rid of wrong info, as you’ll often trial and error towards the right solution. You don’t want these incorrect approaches to leak into the context of the next feature chat, maybe just add the “don’t dos” into a guidelines and rules document so it will avoid it in the future.
An LLM within the right context/environment can also converge: just like with humans you need to provide guidelines, rules, and protocols to instruct how to implement something. Just like with humans I’ve used the approach you describe: generate something one until it works the way you want it, then ask it so document insights, patterns and rules, and for the next project instruct it to follow the rules you persisted. Will result in more or less the same project.
Humans are very non deterministic: if you ask me to solve a problem today, the solution will be different from last week, last year or 10 years ago. We’ve learnt to deal with it, and we can also control the non-determinism of LLMs.
And humans are also very prone to hallucinations: remember those 3000+ gods that we’ve created to explain the world, or those many religions that are completely incompatible? Even if some are true, most of them must be hallucinations just by being incompatible to the others.