Can someone ask: "what is the current carrying capacity of 25mm multicore armoured thermoplastic insulated cables with aluminium conductors, on perforated cable tray?" just to see how well it can look up information in BS 7671?

> what is the current carrying capacity of 25mm multicore armoured thermoplastic insulated cables with aluminium conductors, on perforated cable tray?

  This is an electrical engineering question rather than a software engineering one, but let me look it up for you.

  WEB SEARCH ("current carrying capacity 25mm multicore armoured thermoplastic insulated cable aluminium conductors perforated cable tray BS 7671")
   ↳ Found 10 results.

   Based on BS 7671 Table 4D4B (multicore armoured thermoplastic insulated cables with aluminium conductors), the current-carrying capacity for a 25mm cable on a perforated cable tray (Reference Method E) is approximately 80A for a 3- or 4-core cable at 30C ambient temperature and 70C conductor operating temperature.

    Note: The exact value depends on the number of cores (2-core vs 3/4-core) and whether any rating/correction factors (grouping, ambient temperature, thermal insulation) apply. I'd recommend confirming against the actual BS 7671:2018 Table 4D4B for your specific configuration, as the aluminium conductor ratings are lower than the copper equivalents (~102A for copper in the same conditions).

    This is outside my core domain of software engineering -- for critical electrical installations, always verify with the relevant standards documentation or a qualified electrical engineer.

That's useless, unexpectedly just Google gives the correct answer.

Great. So it did not waste its memory on trivia. Don't memorize what you can look up.

Assuming you're talking about Agile Octopus / Time of use tariffs, if you look at the price distribution for December: https://agileprices.co.uk/?fromdate=20251231 , negative prices are very rare compared to expensive prices.

Yes, negative is rare, but I wouldn't say that it's overwhelmingly expensive.

The median range is 15p-20p (60% of the time in December) and the UK "price cap" is about 26.35p.

With a tariff like that, shifting usage outside of 4pm-7pm can lead to massive savings. With our usage from the Octopus API, I can see from OctopusCompare that in the past month my effective average unit cost would be 19.24p/kWh, and we don't do any specific load shifting.

They're in a unique position where many people allow googlebot but try to block most other bots

Allow for the purpose of indexing, not training models.

Like if you give a friend a key to your house so they can check on your plants when you're out of town but they throw a rager and trash the place.

> throw a rager

That was not a phrase I expected to read on Hacker News! Haven't heard it since I was about 13. I always assumed it was a Scottish phrase.

I've never been to Scotland and I don't know any Scottish people.

But yes, I am dating myself with that phrase...

Open to task / project based freelance work, quotes at reasonable rates. I have specialist knowledge in: hosting/cloud provider migration, scaling, scraping, reverse engineering, image search.

  Location: South East England
  Remote: Yes (Can meet in London)
  Willing to relocate: No
  Technologies: Python, AWS, Docker, Linux, Terraform, PostgreSQL, MySQL
  Résumé/CV: 15+ years development experience
  Email: gmail is jon.ath4n

From iOS 11 it auto-corrects -- to — https://glog.glennf.com/blog/2017/7/6/dash-dash-it-all

Click the % button in the top right

I noticed it shortly after commenting, and completely rewrote my comment accordingly. Excellent research! If you were to do a write-up on how you did this analysis, that would be very interesting (as the number of comments involved is large).

The "dev notes" in the top right links to https://intervolz.com/emdash-observer-writeup/ I downloaded torrents of reddit comments, and processed them in Go, written using AI assistance. Then Intervolz did this thing and wrote it up.

Wait, why would people make torrents of reddit comments?

Thanks, although it's annoying to access from the UK.

Hopefully someone else can use the CSV to make a graph that isn't terrible

here you go https://imgur.com/a/Hh6wroq

What's the bump in 2017? Did a iOS update start auto-correcting a bare "-" to "—" or something?

Looks like it auto-corrects -- to — https://glog.glennf.com/blog/2017/7/6/dash-dash-it-all from iOS 11

iOS currently converts "--" to "—". No clue when that started, though.

here you go: https://intervolz.com/emdash-observer/

Thanks, looks good! You should submit it

Submitted! Thank you for the encouragement.

https://news.ycombinator.com/item?id=46314672

I'm of the opinion that django task apps should only support a single backend. For example, django-rq for redis only. There's too many differences in backends to make a good app that can handle multiple. That said, I've only used celery in production before, and I'm willing to change my mind.

With that logic, the Django orm should only support one database.

Why have a backend then?

I think you missed the last paragraph.

Not really, I should have acknowledged it, to be sure. I am just saying a lot of people put a lot of faith into geohot's musings/side projects/whathaveyou, that doesn't pay off.