Does anyone have some tools to share?

People love these not because they are creative or good executed, but because they see the pictures and the story of the people they love.

> It remains important to be able to read the code and understand the architecture. As a result, I reduce my velocity by iterating over my PR until it reaches the same level of quality I would have produced "by hand"

I do that too and when I do it I'm not sure anymore if I'm "producing as much more" than if I was doing it by hand. I need to spend time to read the code, break down the flow so that it clicks in my head and so that I'm 100% sure that I understand what is going on and what every line does. And then I still test it (executing it), because that's where you notice the edge cases anyways. Once I understand it and test it, the part where I iterate or fix small quirks and hallucinations is the smallest part of the job and is irrelevant if i do it by myself or ask the LLM to make the change.

I'm still not convinced that I'm faster with an LLM at all, since I add this new bottleneck (the time spent understanding every line). If I do it by hand it already clicks in my head, so it's faster for me to test it, find unaddressed edge cases and then confidently ship it. Maybe the LLMs gains are not in this at all and writing every line by hand will still be the norm for a long time.

Still, LLMs make me insanely faster in: finding something in the codebase, recostructing a flow and understanding the architecture, triaging a bug (sometimes it just solves it with a prompt), writing and updating tests, reviewing changes for potential issues. These days I have almost always 2/3 agents running doing something of the above. That saves me hours and you can pry an LLM from my dead hands, but I'm still not sold that it makes me faster at producing production grade code that I fully understand and follows my company architecture and standards.

Then sure, if I need to make a prototype or a small tool for myself or some novelty thing, an LLM can do it without me ever touching or reading the code. But I think that's not what the majority of software engineers are employed to do.

Heard this exact sentence multiple times a few months ago about Opus 4.6, then 4.7 and 4.8 were considered a disappointment and today people miss "the good old times of 4.6" (referring to a few weeks of February 2026).

Very fascinating to look at all of this unfolding.

> Most (continental) philosophy is closer to art in my opinion than scientific inquiry. If you accept it as art, then you at least open the door to there being many valuably different ways of saying "love is good" or "reality is complicated" or what have you. And if you consider it as something beyond art, well, then it has some very pointed questions to answer.

I would invite you to read more philosophy if that's your idea of what philosophy is, because it feels very far from what has been discussed over the centuries by many authors way smarter than me and you.

If I have an interesting thought about a topic and I share it with an audience that is not PhDs, to them it might be interesting and insightful and provoke new thoughts. Most likely yes, someone in the 70s somewhere in the world already wrote a paper about this idea or even a book. Does it matter though? Sharing ideas gets people thinking and the fact that someone else already extensively thought about something doesn't make my thoughts less relevant. If anything, by sharing it I could get a comment pointing me to a book or paper that would help me understand better the topic or expand my ideas further.

I don't think that what's worth sharing are only documents that quote everyone else that already talked about it and their thoughts. That might work if I want to prove that my work is at boundaries of human knowledge or that is the most plausible explanation for something, but if I just want to share ideas then I find it limiting. Not just because it limits the people with the knowledge to write anything to a handful, but also because for those people there is this anxiety of "not worth it, wasting people time" if it's not researched for months like you mention. Share your thought, if some expert will find it wasteful or naive they will not read it, but someone else might and it might open their mind.

This makes me think about philosophy, if you really dig down into it virtually all philosophy ideas were already discussed first by Plato and Aristoteles. You cannot find a modern philosophy thought that isn't in some way already discussed by those two. Should then all philosopher in history not write anything because it was not really an original thought?

Can you elaborate?

Comments URL: https://news.ycombinator.com/item?id=48290888

Points: 2

# Comments: 0

We are nowhere near this scenario tbh. Token cost is very high and is currently heavily subsidized by VC money to gain market share. Also this realistically only applies to small projects, small codebases and mostly greenfield ones. No way you can rewrite the whole codebase quickly and cheaply in any mid-sized+ projects

But even assuming token cost plummets, any non-trivial piece of software that is valuable enough to generate income for the company is also big, complex, interconnected enough that cannot be rewritten quickly even by AI, also for business reasons too. If a piece of code works, is stable and is tested, then rewriting it will always bring a high degree of risk and uncertainty that in a lot of business critical applications is just not worth it. A stable system can stay untouched for years besides minor dependencies updates.

Also, I think the $200/mo plan is subsidized by VC money and is likely hemorrhaging money for Anthropic, so it's not really meaningful to reason around that.

It's based on existing GitHub PRs and Issues, the full dataset is on HuggingFace and is one year old now. All frontier models 100% have those issues and PRs in their training data so obviously they are good at reproducing fixes for them when confronted with the same codebase and similar requests. Am I missing something? How is this considered the most reliable benchmark?

Some senior people that were in the AI pilot, have been using this for a while, and are very into it claimed that it can open PRs autonomously with minimum input or supervision (with a ton of MD files and skills in repos with clear architecture standards). I couldn't replicate this yet.

I'm objectively happy to have access to this tool, it feels like a cheat code sometimes. I can research things in the codebase so fast, or update tests and glue code so quickly that my life is objectively better. If the change is small or a simple bugfix it can truly do it autonomously quicker than me. It does make me lazier though, sometimes it's just easier to fire up claude than to focus and do it by myself.

I'm careful to not overuse it mostly to not reach the montlhy cap, so that I can "keep it" if something urgent or complex comes my way. Also I still like to do things by hand just because I still want to learn and maintain my skills. I feel that I'm not learning anything by using claude, that's a real thing.

In the end I feel it's a powerful tool that is here to stay and I would be upset if I wouldn't have access to it anymore, it's very good. I recently subscribed to it and use it on my free time just because it's a very fun technology to play with. But it's a tool. I'm paid because I take responsability that my work will be delivered on time, working, tested, with code on par with the org quality standards. If I do it by hand or with claude is irrelevant. If i can do it faster it will likely mean I will receive more work to do. Somebody still has to operate Claude and it's not going to be non-technical people for sure.

I genuinely think that if anyone still believes today that this technology is only hype or a slop machine, they are in denial or haven't tried to use a recent frontier model with the correct setup (mostly giving the agent a way to autonomously validate it's changes).