171–180 of 754 posts
Earlier quoted context omitted.
"No one has the intention of building a wall" - Walter Ulbricht, chairman of the central committee, a couple of months before the Berlin Wall was built. The AI companies and their associates are beginning to surpass that level of denials and lies.
It’s disrespectful to immediately jump to adversarial conclusions from a simple desire to refactor and poor netiquette.
Very impressive that they could do this so quickly because I have been on a similar project (porting TypeScript to Rust) for 5 months. But I guess I don't have access to Mythos and unlimited tokens. I'm also close to 100% pass rate. 99.6% at the time of writing. https://tsz.dev Rust is perfect for writing all of code using LLM. It's strict type system makes is less likely to make very dumb mistakes that other languag…
I question this. Yes, strong enforcement of invariants at compile time helps the LLM generate functional code since it gets rapid feedback and retraces as opposed to generating buggy code that fails at runtime in edge cases.
On the other hand, Rust is a complex language prone to refactoring avalanches, where a small change in a component forces refactoring distant code. If the initial architecture is bad or lacking, growing the code base incrementally as LLMs typically do will tend towards spaghettification. So I fear a program that compiles and even runs ok, but no longer human readable or maintainable.
Earlier quoted context omitted.
What's your point
To demonstrate engineers may not be as skilled and knowledgeable as they appear. To make such a comment then turn around and make an announcement days later indicates that the engineers are not skilled in the tools they’re using or even possibly the domain they’re working in.
Your kind of negativity is pathological.
Earlier quoted context omitted.
Yes indeed. More than 1 million lines of code (including tests) is jumping lots of hoops but with LLMs it's not as painful so you can just ask it to do the hard things. Example of a Claude Code session after 2 hours of "Crunching" that came out without results https://github.com/mohsen1/tsz/pull/4868 (Edit I force pushed to PR to solve the problem, you can see the initial refuse message in the initial version of PR d…
You should try GPT, I’d be really interested to hear if it works better. (Exclusively using GPT for systems work at $DAYJOB, but compare with opus every couple weeks and GPT consistently gives me better results)
GPT for instance had a lot of issues using git worktrees, and didn't understand how to correctly use it to then merge stuff back into a main branch, vs Claude which seems to do this much more naturally.
GPT also left me with broken tests/code that I had to iterate on manually, Claude is much better about reasoning through code. Primarily Python.
Earlier quoted context omitted.
> I am so tired of worrying about & spending lots of time fixing memory leaks and crashes and stability issues. it would be so nice if the language provided more powerful tools for preventing these things. haven't used zig...(only used rust) but zig doesn't solve those problems?
Nope! Zig is like C in this regard. There’s no borrow checker. Managing memory is your responsibility. It gives you a few more tools than C - like a debug allocator, bounds checked array slices and so on. But it’s not a memory safe language like rust.
Earlier quoted context omitted.
I totally disagree with this! I think it's very important for experts to be able to adapt to their opinions based on evidence.
[flagged]
Earlier quoted context omitted.
To demonstrate engineers may not be as skilled and knowledgeable as they appear. To make such a comment then turn around and make an announcement days later indicates that the engineers are not skilled in the tools they’re using or even possibly the domain they’re working in.
The quote doesn’t provide warrant for this claim. The developer did a great job investigating the applicability of a new tool and it appears the investigation yielded fruit. Your kind of negativity is pathological.