76 karma · joined June 22, 2013
The reason this bothers me is that comments like this reinforce the believes of people that could otherwise find value in these tools.
But I think points like this would be better made in shared chats or screenshots, since we do not have something like a core dump or stacktrace to attach.
And while I am not saying OP did this, I have seen technically skilled engineers asserting/implying that llm/chatbots aren’t good or not useful to them look at their chat log that a multitude of topics that I am sure would impact the result of the query.
Yes. It can be an UX problem. Yes. It can be an algorithmc problem. But they are just tools that can be used wrong and not a perfect mechanical brain.
Beyond that, I am enjoying a little bit too much customizing Fish, bobthefish, FZF, and replacements for established CLI apps (e.g., find/fd). I spend too much time asking Claude how to do various things. And I am the happiest with my current setup—until I have to SSH into the barren lands of a production host.
As a way to show the wonderful complexities of compilers check the TOC of https://shop.elsevier.com/books/optimizing-compilers-for-mod...
Sorry for the direct link, couldn’t get archive.is to work with this one.
From another point of view, seems like we had a shared document automatically created of the meeting transcription/summary it would reduce the friction and other biases. (Oh look, the LLM is dumb, it wrote that the project is over budget and we depend of risky integrations)
Idk why it works but I find it smoothing and allows me to control how I am being seen. Just my personal experience.
The thought process is that if there is random steel laying around releasing unhealthy amounts of radiation, would it be nice to know before going to the doctor?
Thankfully the payback machine is there for you: https://web.archive.org/web/20150621044359/http://secrets.bl...
I should start donating money to those guys
Or search for "Shape from Shading" or "shape from occluding contours"
[1]http://www.cs.rutgers.edu/~decarlo/readings/koenderink-perce...