lopatin

Right, when Rachael Gunn (Raygun) embarrassed Australia and the whole of breakdancing on the olympic stage, the nice thing to say would have been "congrats on getting this far, fixing the issues won't be easy, etc..." but what really should be said something like "I'm not sure how it got to this point, but everything about this is wrong, and you should probably focus on something else".

I’m pretty sure this is rage bait. The idea that China is more interested in virtue signaling than pulling off a power move that will improve their chess position is not worth a serious reply.

This article is a bit too desperate to connect the subject matter to the medium.

Agree, bike shedding about something like writing style, which unlike tabs-vs-spaces, doesn't even have an objectively correct answer, is not productive.

I would encourage everyone to try this on some self-contained, state-machine like problems, if they have them. At my company, some experts were optimizing our clustering and failover logic by adding a bit more state (and hence complexity). Despite me not being an expert in that area, I was able to find and prevent a catastrophic bug by pointing Opus armed with TLA+ at the problem. It was a bug that was not possible in the prior implementation of the system and no one thought to write unit tests for the sequence of steps that triggers it, so initially went unnoticed. The only thing that caught it was the TLA+ invariants, which, yes, were written by Opus as well.

As a side note, there's a lot of talk about programming being not fulfilling anymore. But the above exercise was probably the most fun I've had with engineering in a long time, and would have been nearly impossible for me personally without AI. Perhaps it was the novelty of the TLA+ stuff, but I think it offers a glimpse into what our jobs could actually be in the future, beyond simply telling Claude to do what you used to do manually and then clicking enter. There are much more ambitious and fulfilling use cases for it.

[flagged]

I'm not following because a) The bun rewrite was a success b) the C compiler wasn't a rewrite and c) "Software is still the best specification for existing behavior" seems to imply that rewrites are achievable because we already have a working version that functions as a spec?

Referencing Joel Spolsky's article about how you should never do a rewrite is starting to feel outdated as well.

I'm in the process of evals for these tools after my org adopted them. My RTK findings are the same. It worsens task performance and overall you don't save money. I wanted to give the same treatment to other tools like ponytail and caveman (especially caveman, I mean there's no way that telling a computer to talk like a caveman is a valid engineering technique right?). To my horror, caveman is looking to be the only tool that actually doesn't regress on reasoning while taking costs down. But I still have a lot more evals to write, so this isn't conclusive or anything. (Also I haven't tried Lumen yet)

Claude just wants to tell you its honest truth

I didn't realize this counted as smart. I think at best it's an LLM intelligence arb that may exist for a few months.

I'm not following the news. Why should we not upload pictures of family members to OpenAI? Are any other cloud providers safe?