Yep, if you haven't lost the will to put a bit of curation work upfront, RSS never stopped being the right answer.
Substack has been a pretty good addition to the landscape, bringing lots of people into blogging (without calling it that). But for the skimming/reading interface, RSS beats the app.
I've been using Claude to work on a medium-sized (100+kLoc) codebase, and it's a great productivity multiplier. Putting hours into creating a good AGENTS file is more improved results a lot. I find that over time it picks up the codebase quite well. Tedious tasks that would take a day are now a matter of a few prompts.
Still... I'm not ready to give it more autonomy. Even as it gets high-level things quite well, I still look at the code, give feedback, and have 3-4 rounds of tweaks until I'm happy with it, and also happy that I stil feel I have a good handle on the codebase.
Try to quantify those 3-4 rounds of tweaks into a set of rules to put into your AGENTS. Instead of iterating, have it start over from AGENTS file and see if it's correct now.
Ngl, that’s gold right here. I’ve been trying to automate my sessions, and what I’ve found cool is that you can ask Claude about how to improve on how to ask Claude things, and from there ask Claude to iterate on your session cycles
No. Because they still hallucinate at times. Confuse things. Forget things. Or none of the above, as it is anthropomorphizing, but the result is the same. They can make incredible working one shots, you start to trust them, then you trust too much and .. feel the result.
Yes. I am fighting with the disobeyance of LLM on working through my pipeline commands. I believe these violations are caused by its hallucinations. So I am still developing a mechanical system to monitor agents’ behaviors automatically. I believe these routines and monitors will play as a set of scaffold to keep leading the LLM on the right way all the time.
The percentage of times I prompt claude "what about checking if there are any child processes running?" or "Would using a lock here greatly simplify the design?" only to have myself be correct is approaching 100%. That is it isn't just claude sycophantically agreeing with me. The code itself becomes smaller, simpler, and more reliable with fewer bugs.
The agents tend to produce working code but the larger the scope the bigger the mess they tend to make. They will happily evolve toward a local maxima but leave world-destroying bugs lurking in the implementation.
The other issue is that claude regularly ignores explicit instructions in CLAUDE.md or in prompts. It will "helpfully" decide to just start doing whatever it wants or reinterpret instructions completely differently than it did the last 100 times.
It has nothing to do with losing control or trust. LLMs are not conscious. They have no executive function. They aren't even thinking. They're just models predicting the next word in the script. They are very useful tools but that's all they are: tools.
I also feel like we still need to steer Claude. It doesn't always help to have stuff in the CLAUDE.md (even when it's lean). I have a lot of cases where I still need to remind the agent to do something even if it's routine.
To me I think that connects with working longer on the planning and specs. It requires reading and re-reading, but when that's done, implementation is usually much cleaner and adheres to your standards
Yes. They are tools. So my approach, at least try to approach is to keep on polishing the skills and check the output of LLM in loops with mcp to alert the abnormality asap so the LLM won’t go to next step to make things worse.
I basically skipped React. I went from jquery to Vue3, and use even that sparingly. When React got really popular, I read the docs and played with it, but I prefer the Vue model where the component runs once and sets up its reactive tree. Why would you want to recreate the component's inner functions every time it renders? And manually declare dependencies, when every other framework is doing them automatically?
My favourite front-end architecture is MPA actually mostly server-rendered, with Vue only on the pages that need high interactivity, and vanilla JS on the others.
If postgres is too heavyweight for you but you still want client-server, I'd consider MySql. It's an old classic, pretty fast and scalable, and has much better mainstream support and a bigger ecosystem than Firebird.
I'm not really sure what Firebird is for at this point in life really. It was pretty exciting when it was open sourced in the early 2000s, before postgres became the mature beast it is, before mysql acquired something as basic as transactions, and before sqlite became the default embedded db. But then it never really went anywhere.
It's called euthanasia. You can ask the medical system for an assisted suicide if your life situation is extra painful with no hope for recovery.
This case got heaps of media popularity because the christian right wing latched on it, and the father tried as hard as he could to impede the euthanasia. Ultimately got told that the lady unequivocally wants it and qualifies, and he can't override that.
> Ultimately got told that the lady unequivocally wants it and qualifies, and he can't override that.
Not just once, but five times by different courts, finalized by the European Court of Human Rights!
> Her request had been approved on July 18, 2024, by the Catalonia Guarantee and Evaluation Commission. The commission found that she met all legal requirements, as she had a “nonrecoverable clinical situation,” causing “severe dependence, pain, and chronic, disabling suffering.”
> But in August of that same year, her father – advised by the ultraconservative religious group Christian Lawyers – began a legal fight to stop the process
> From then on, her father initiated a long legal process that delayed Noelia’s euthanasia for 20 months, going through five judicial levels: a Barcelona court, the High Court of Justice of Catalonia, the Supreme Court, the Constitutional Court, and the European Court of Human Rights.
I come from a society that doesn't value compassion that much, so now when I live in Spain which has a lot of it, it's hard not to feel good about it. Wish it was the same in more places in the world, we're all human after all.
Helping someone avoid "nonrecoverable pain, forever" isn't "cold-blooded murder" in my mind, but I figure there is no point is arguing against someone who doesn't understand nuance.
What kind of context has you deploying into old systems that don't ship a recent perl? If that is a legacy requirement for whatever reason, then at least I'd use docker or podman to get a recent runtime. Or would you also write Python 2 or Php 7?
What are you using for parameter type checking? I switched to native function signatures, native try/catch and might look into the new class system soon, but I don't recall native type checking...
This looks like a huge project, even with AI help... I have a sweet spot for perl but I'm honestly not sure if the current community has the bandwidth and interest to sustain an alternative implementation. At the very least it should be ported to MacOS too. Breaking with XS is a bold decision. Best of luck though!!
reply