porker

It's always fun to see what works for others, because for my work it'd have to be Sol > Fable. Fable makes too many mistakes.

Coordinating agents though? Fable any day.

Some of these resets were because of bugs in the 5.6 launch that caused subagent-users to burn _a lot_ of extra tokens. It was placating customers.

It is impressive they've got the capacity to do so.

Fable 5 is sick. [It] solves almost any task from start to finish, the way it should be done — no errors, perfect code. It's a miracle.

As for GPT-5.6 Sol — it doesn't even come close. I honestly don't understand why people even try to compare them.

What kind of problems are you working on? I like Fable but when planning work on a complex C codebase it's making more mistakes than 5.6 Sol xhigh for me.

In what scenarios is Fable giving you "no errors, perfect code"?

For gpt-5.5 I build up that session context into a markdown file, and then I start a new session and give it the markdown file with the instructions for what to do.

I'm guessing this works better because it can always go back and re-analyze the saved context.

Yes, I've just come to the end of implementing all the planning I did while Fable was available. And nothing now comes close to creating plans that could be coded and just worked like it did.

On a large C codebase, Claude hallucinates constantly, and GPT 5.5 gets there are with a lot of help, but still gets things wrong.

Congratulations on the release!

Could you add fff to the benchmarks?

We like our sarcasm and disappointment.

What is RE in this context?

I've yet to find a set of Bluetooth headphones or earbuds that don't have a level of background hiss that I can hear.

Particularly for spoken word, it's annoying and distracting.

It's also hard to brew coffee if you tend to use off-the-boil. The best you'll get is about 93 C.

That sounds ideal for off-the-boil coffee brewing? At sea level I (and all the speciality coffee shops round here) aim for 91C, and I'll drop that to 88-89C for medium roast and lower if it looks on the dark side. Brew methods: Aeropress and cafetiere.

Let's say you're thrown into a website you've never worked on before and asked to fix a styling problem. You can look in the browser tools, but the website will only be running the compiled production version, and if the team knows what they're doing there won't be source maps available.

So you've now found selectors in DevTools that you think are causing the problem, and you want to find them in the source code. In the case of many projects, that means searching through hundreds of small CSS files.

That's why you grep selectors, and where the pain comes. You have to start with the most specific rules that you found in DevTools, then start deleting parts from them until you find a non-nested rule that's in the source, yet still specific enough that you haven't got hundreds of matches to go through.

It would be great if something like ast-grep could take a CSS rule copied from DevTools and search for nested CSS that would compile to match it.

Link?

Cardinal: Fastest and most accurate file search app for macOS. https://github.com/cardisoft/cardinal

It's slower to start-up than Everything but just as useful once running.

There are a few Mac oddities like OneDrive files appearing twice because macOS is convinced they exist in two locations, but that's a minor annoyance.

FYI all your posts are ending up as [dead] on HN, but I think the concept of learning is interesting enough that this deserves a chance.

due to Anthropic's ToS change.

Not a change, but enforcing terms that have been there all the time.

https://mastrojs.github.io/ was the one I couldn't recall.

https://lume.land/ a good, straightforward SSG.

There's one other I've seen recently that looked good but I have misplaced the link

Thought the UK had been cut off from X, good to know it's everyone :D

Basically, I need Claude Code with a proper review phase built in. I need it to slow-the-fuck-down and work with me more closely instead of shooting mountains of text at me and making me jam on the escape key over and over (and shout WTF I didn't ask for that!) at least twice a day.

It sounds like you want Codex (for the second part)

If you use GMail: https://chromewebstore.google.com/detail/markdown-here/elifh...

The truth is, business opportunities are rarely eternal, usually they are just an opportunity to make money within a short window of time, such as a decade or two. Sometimes even shorter than that, perhaps even only a year or two.

Agreed, and Adam and Steve made a life-changing amount of money from Refactoring UI and then Tailwind UI. That's a great outcome on its own.

FWIW I found Practical UI [1] a more actionable book than Refactoring UI. Both are similar but I found it covered the material in a more accessible way.

1. https://www.practical-ui.com/

Now, basically every new "AI" feature feels like a hack on top of yet another LLM.

LLM user here with no experience of ML besides fine-tuning existing models for image classification.

What are the exciting AI fields outside of LLMs? Are there pending breakthroughs that could change the field? Does it look like LLMs are a local maxima and other approaches will win through - even just for other areas?

Personally I'm looking forward to someone solving 3D model generation as I suck at CAD but would 3D print stuff if I didn't have to draw it. And better image segmentation/classification models. There's gotta be other stuff that LLMs aren't the answer to?

They’ve dropped the ball over the past five years. Part of me thinks it was the war in Ukraine that did them in.

I'm also a subsciber for over a decade, and came here to say the same thing. I don't know how their teams were distributed across eastern Europe and Russia but the war is when I pinpoint quality declining.

I've kept my subscription for now as for PHP and Symfony nothing comes close, but I'm actively looking to move away.

No, polars or spark is not a good answer, those are optimized for data engineering performance, not a holistic approach to data science.

Can you expand on why Polars isn't optimised for a holistic approach to data science?

if they call their employees monkeys, certainly.

It seems to have decreased in the last 10 years but calling us code-monkeys was a common derogatory reference to the software department. I didn't like being compared to a monkey randomly bashing a typewriter but that's how things were.

It was better than what everyone called HR.

It's actually about computers unlike many of the threads today on HN?

It's an AI bot. One for @dang

Is there any way to remove every SPOF?

Currently I have multi-region loadbalanced servers. DNS and WAF (and the load balancer) on Cloudflare.

Moving DNS elsewhere is step 1 so I'm not locked out - but then I can't use Cloudflare full stop (without enterprise pricing).

Multi-provider DNS and WAF - okay I could see how that works.

But what about the global load balancer, surely that has to remain a single point of failure?

Even if you could, the DNS entries aren't loading. And then the page 404's.