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.

This is about as insightful as the "draw the rest of the owl" meme, with a bit of Lex Fridman style forced humility in the title.

This is bound to cause some confusion with the other tool called Ax for agentic development: https://axllm.dev/ (which is DSPy for other languages)

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?

One founder. Zero results. Honest truth. Verified, not inferred.

I asked a current generation LLM to make me $1k a week and it hasn't so far.

To my horror, it kept the metaphor going on and off the whole article. Half way through, there is a section called "Three cars failed the crash test".

The poster's username is "ed-is-ai" so I don't know how unproven it is.

lol I wanted the joke to work, but unlike the fairphone thing, the use of intentional makes sense here.

I love the premise of the game. I mean ultimately what I think we need is a fighter between two Linux users, each representing their own operating system. Each OS can have its own power ups. Maybe that can be v2 :) good stuff!

You can sue whoever you want. But this reads of backpedaling and righteousness to me.

The quote below are not my words, but are from a prior comment on HN, which I think are relevant.

``` I in no way mean this to be rude, but I think a big part of why the EU isn't in the same galaxy as the US in the realm of business in general, is in some part, the knee jerk reaction to turn to the government to make products and services better. Governments cannot make you an alternative, they can only make something that already exists, different (usually worse).

I have zero interest in creating in the gaming space, however, my gut reaction would be to start down the path of how I could create competition to companies that rug pulled their games.

And yes, I get that "just make a competitor" is easier said than done. But at least by going down that road, you end up with more games, better games, and people learning skills throughout the process. And who knows, maybe one is a mega success.

Sure, you can stand there pounding your chest for "democracy," but I contend that those who are building their own things are practicing it far more than those who are demanding others make things for them. ```

https://news.ycombinator.com/item?id=47130596

I'm reviving my multi-player Snake game Snaketron. It's written in Rust and probably the most technically interesting thing about it is that it's built for auto scalable Cloud hosting. The websocket isn't tied to the host actually running the game. And it can scale and rebalance in the middle of the a match without disrupting the game.

https://snaketron.io

https://github.com/lopatin/Snaketron

> But I’m assuming, surely, Zed writes their own copy

I've written my fair share of landing pages and copy lately. I start out with Claude for ideation and headlines it produces are almost always low effort word salads. Case in point:

"Software is made between commits"

It never fails to emphasize the last part, even if it bears no weight.

The only response to that headline is "Sure I guess".

It doesn't give you an idea of what problem it solves, doesn't sell you a vision or get you excited about the future. It's not even that insightful and is borderline factually incorrect.

I guess that brings up the question of why do people use Codeberg in the first place. From what I understand, it's a decision based on values right rather than cost, functionality, or convenience. Well here you go, more values, enjoy!

Calling it model bias is as disingenuous as calling newspaper ads media bias.

After spending way too much time with Fable a few days ago, I noticed a new hallmark of AI generated text is using the word "honest" everywhere, in a somewhat self congratulating way.

Some things that give it away to me:

- "Honest numbers (WSL2, 12 cores, 25 GB RAM, NVMe via VHDX)"

- "an honest peak projection (working set, KV, MTP row, reconstruction buffers) so the kernel OOM-killer never fires."

- "Honest caveat from the same measurement: ..."

It's the new "It's not X, it's Y". I have no issue with this, I just found it amusing.

Cool project btw!

Auditing the generated code would defeat the purpose of reckless insubordination.

I'm building an AI, that uses AI to operate AI.

Without it you likely would have been in the same quagmire, but just slower?

It could have taken you years to realize that "oh I'm just exploring stuff and have no output".

Set an ambitious goal that is achievable using Claude Code, and focus on delivering it. Even if it doesn't turn out to be a hit, the experience of releasing it and using AI to accelerate it, will be a talking point to your 10-year-older self.