HNHacker News
TopNewBestAskShowJobs

rafaelRiv

39 karma · joined July 18, 2026

submissionscomments
rafaelRiv··on AI Agents and the Refactoring That Never Happens
Before llms : All tests + some type theory things After llms : Just slop without tests
rafaelRiv··on AI Agents and the Refactoring That Never Happens
> In the only scenario where that could actually be true you wouldn't have coworkers creating unmaintainable code with LLMs now.

Bingo. My highly qualified team was disbanded because the company went bankrupt. Apparently, the CEO had embezzled a large sum of money. That team was disbanded just before LLMs caught up.

The one that create unmaintainable code is a new team and the reason they are able to create such a large amount of unmaintainable code is because of llms.

> I've never met a single developer saying refactors are easy. It's always a minefield.

Pleasure to meet to you. You now know one. In the land of functional programming, refactoring is quite enjoyable and quite easy.

rafaelRiv··on Programming is Art
> programming is primarily problem solving

It is more than that in the sense that I have a lot of obligations to understanding the code. The reason is that if I don't understand the code, I will not be able to answer questions that are asked to me. And those answers are generally very important for the future of the business.

Code is art in the sense that I need to arrange it such as I can actually make it maintainable, readable, easy to add new features and make it that I can answers questions very easily.

LLMs remove this ability because it doesn't let me the time to absorb the change as such that I can guaranties those 4 requirements. It just concentrate on adding new features without making sure it doesn't break the other 3 requirements.

To guaranties those for 4 points, I need a mental map of the code which llm generally remove. The more we use llms, the less of a mental map you have of the code

rafaelRiv··on Is mathematics about to enter the conservatory?
This is a very incomplete transcript : "The complete transcript of ONE autonomous Claude sub-agent, "E2", "
rafaelRiv··on AI Agents and the Refactoring That Never Happens
And for me, it has created a giant pile of unmaintainable code from my coworkers because of stupid management people that think they can code.

Refactoring was never a substantial amounts of time for me before llms. Before I could spot a potential refactor and refactor it in 20 minutes and less. Never abandon it. Just constant improvement to the point the previous tech startup that I was working for just drive from itself (I am still paid a a few hours per months for it)

rafaelRiv··on Most tech revolutions made work worse for employees
> Not me! I'm 100x AI engineer who will certainly remain comfy an secure. LLMs are awesome! It's all those luddite doomer jerks who cling to their old ways of understanding how things work and manual coding that are going to be poor, and they deserve it.

We will see in 5 years ! I think you highly overestimate llms

rafaelRiv··on GCC steering committee announces AI policy
I see that the fantasy world of llms is still strong
rafaelRiv··on We have proof automation now
I do but I have no guarantee that the llms will make a sane implementation of the types
rafaelRiv··on We have proof automation now
I program very often in idris2 and I cannot agree more. LLMs tend to take the least effort possible to the point where most of the time, llms are just not useful to program with dependent types. At least, not yet
rafaelRiv··on We have proof automation now
I would say that the value of dependent types in software engineering isn't in proving all code correctness. As a user pointed out in the idris2 Zulip, most programs using dependent types don't have, and shouldn't have, proof of validity for the entire program. Instead, you simply get more correct code by construction, and I think that's the whole point.

I'm currently developing a unikernel in idris2, and the experience is very pleasant (unfortunately, I'm not quite ready to share it yet).

rafaelRiv··on The LLM Critics Are Right. I Use LLMs Anyway
As if programming by hand was sooooooo inconvenient
rafaelRiv··on The LLM Critics Are Right. I Use LLMs Anyway
Jesus ! You guys are very authoritharian. Even if it is now the norm, I prefer to not use that tool and I bet the more the time past and the more I will be faster than anyone that use LLMs (because of skills atrophy)
rafaelRiv··on The LLM Critics Are Right. I Use LLMs Anyway
What is your metric ? How do you calculate ROI ? Strange that you didn't specify that. Also, are you sure your "25% increase" is due to LLMs ? Every time I see this claim, it is always for a short time period or the increase was not due to LLMs at all
rafaelRiv··on The LLM Critics Are Right. I Use LLMs Anyway
LLMs are not deterministic and I still look at compiler result and I encourage people to look at it. That people don't look at the result of compiler is a problem and not a an argument
rafaelRiv··on After 7 years in production, Scarf has reluctantly moved away from Haskell
And you are being authoritarian by telling us which tools we should use for our careers. At this point, llms have give me more work than anything else
← PreviousPage 2 of 2