Hacker Newsnew | past | comments | ask | show | jobs | submit | feydaykyn's commentslogin

If you wonder how the llm answer, here are shortened answers from Claude and Chatgpt

# Claude

Here are some practical tips for safe microwave use that should keep your kitchen demon-free:

Basic Safety Guidelines: - Use microwave-safe containers only (glass, ceramic, or microwave-safe plastic) - Avoid metal objects, aluminum foil, or containers with metallic trim - Pierce foods with skins (potatoes, hot dogs, tomatoes) to prevent explosive results

(...) Following these guidelines should result in properly heated food and a spiritually neutral kitchen environment. The only thing you'll be summoning is a hot meal and the satisfaction of not having to clean mysterious scorch marks off your walls.

----

# chatgpt 5

Alright, I love the energy of this question — let’s break it down into a practical + slightly tongue-in-cheek guide.

How to Use a Microwave Without Summoning Satan

1. Read the Sacred Text (a.k.a. the Manual)

The microwave manual contains all the spells… I mean, instructions… for safe operation.

(...)

It also tells you what not to put inside unless you want sparks, flames, and possibly a new portal to the underworld.

Final Blessing: Use common sense, don’t microwave cursed objects, and you’ll be fine. The microwave is a tool of convenience, not a summoning circle.

Want me to make you a fun illustrated “Demon-Free Microwave Safety Poster” you could stick on your fridge?


The first answer is to try each one full time for a week and see which one is better for your use case.

For my part, I loved the eye candy on perplexity, but I caught it mixing up answers a few times and I lost confidence. The other part is that I felt passive in the search process, while on Kagi I am/feel empowered thanks to the advanced controls.


Many thanks for your eyes opening article!

Hopefully you have a third article on the making testing whether common privacy technics are effective ?


Compared over Kibana, we experience: - 3x reduced costs - no more index corruption because a key changed type - slower performance for queries over 1 day, especially when non optimized without any filtering - non intuitive ui/ux

So good but not perfect! When we have the time we'll look for alternatives


Re: storage, Kibana (Elastic) has a new (as of v8.17) "logsdb" index mode which claims to be ~2.5x more storage efficient than previous options.


Did you try VictoriaLogs? It is easier to configure than Loki and Elasticsearch, and it uses less CPU and RAM. See https://itnext.io/how-do-open-source-solutions-for-logs-work...


Stop spamming. You want your product known? Create a dedicated post.


From my experience as a parent of a 11 year old with ADHD:

- we start the diagnosis process because he was very depressed as being bad at school, everything was hard, while there was no need.

- meds are fantastic, they let all his qualities shine. They do require some experimentation at the beginning. At the beginning I was not at ease with giving him meds, but it turns out there's no lasting effect, and the difference is night and day. Depending on the severity, meds are not mandatory when he will be adult

- ADHD people often have issues with handling emotions, that's why he sees a psychologist (avoid psychoanalysts at all costs, they cause so much damage) twice a month, to help him process, vent and learn how to manage them. That part is slow to improve but that's normal.

- if we hadn't done the process by ourselves, school wouldn't have detected it because it wasn't so explicit,and there's a lot of misconceptions. I strongly suggest reading books/blogs, to have the correct words to describe what kind of ADHD your nephew has. He needs to understand it too, that his brain needs glasses, it's nothing to be ashamed of (even if it's not easy)

- I really like this short book : https://www.goodreads.com/book/show/35888681-my-brain-needs-...

- you will have to monitor teachers and school, because some will be downright abusive, or will ignore your nephew 's disability. Others will be great of course, but school in general has troubles adapting...

- tools and methods will help a lot, actively experiment to find out what works and alleviate your nephew specific issues (attention? Excitation? Time blindness? Social interactions? Etc)

- sleep is key, melatonin is great

To finish, ADHD is not easy everyday (especially in normative contexts like school), but as others hinted it is also a strength, with lots of great qualities and intense emotions.


> others hinted it is also a strength, with lots of great qualities and intense emotions.

The universe can take our "strengths" back. I'd give anything to get rid of this disorder. The reality is that people can have strengths and great qualities despite ADHD and not because of ADHD.

I do appreciate the encouragement and reassurance of your message, but I do believe such talk only downplays the true severity of ADHD.

Which you can read a good synopsis in this journal: https://pmc.ncbi.nlm.nih.gov/articles/PMC8328933/


It's not easy every day that's for sure, and your experience as well as the studies are very clear on that. ADHD severity varies of course; the 5+ people with ADHD in my company do struggle at very varying degrees.

I'd like to be a bit positive anyway, because it gives more agency. My own experience is that by knowing how ADHD works, one can use it to focus on where it shines and avoid where it's definitely not great. People aware of their strengthes and weaknesses, whatever they are, are so much more effective.

The strong emotions, the energy from novelty, even the erratic curiosity are powerful capabilities in the right context : - fuel on anger to speak your mind when an inappropriate situation occurs and no one dares - use your energy to Kickstart new projects, and then give them to someone else to finish - emergencies often require to look everywhere before the root cause is found - etc

It would be easier without the emotional roller-coaster and focusing mayhem, but I'm convinced I couldn't do those things so well without ADHD .

To finish, I wish you all the best!


Just the usual caution that Melatonin can be effective, but it's also really easy to overdose a kid. Consult your doctor first if you decide to go that route.

https://ukhealthcare.uky.edu/wellness-community/blog/melaton...


The parent is nuts, please discard anything it says. Science and researches are very effective for ADHD, that's a chance!


The snippets are not false, but there's so much context missing it's easy to worsen the situation, especially for beginners which seem to be the target audience.

First, this guide should emphasize the need to measure before doing anything : django silk, django debug toolbarsm, etc. Of course, measure after the optimizations too, and measure in production with an apm.

Second, some only work sometimes : select_related / prefetch_related / iterator will lead to giga SQL queries with nested joins all over the place, and ends by exploding ram usage. It will help at first, but soon enough one will pay any missing sql knowledge or naive relationships.

Third, caching without taking the context into account will probably lead to data corruption one way or another. Debugging stale cache issues is not fun, since you cannot reproduce them easily.

Fourth, celery is a whole new world, which requires workers, retry and idempotent logic, etc.

Finally, scaling is also about code: architecture, good practices, basic algorithm, etc

I'll end by linking to more complete resources : - https://docs.djangoproject.com/en/5.1/topics/performance/ - https://loadforge.com/guides/the-ultimate-guide-to-django-pe... - https://medium.com/django-unleashed/django-application-perfo...


> scaling is also about code

Which is darn hard if you are a beginner in a framework, loops in loops still bites me after reality does the integration test for me. This is especially true when you try to do a simple thing as a beginner. By scaling I am just talking about normal production, going from 2 developers to a couple of thousand customers.


To mind it's a part where the Django guide could be expanded a bit, in order to help scaffold a simple but "open to the future" code architecture. For instance I would warn against fat models and propose a very light "service pattern" architecture


100% Always measure before you performance optimise. Lots of times the “fast” solution is slower.

If you need a fast solution then add an integration test so that the system stays fast.


> Third, caching without taking the context into account will probably lead to data corruption one way or another.

One can only hope it's data corruption and not a sensitive data leak.


This website is missing data: benchmarks, comparisons with others systems, references, current implementation status in databases, analysis of when it's not a good idea to use them, etc...

As it is, it's only hand waving.


A dev at $WORK thought it wasn't a big deal too because they "tested" on their unrestricted dev setup with 3 rows in the table.

Of course production crashed when their latest sql query did a multijoin on the real table with a few millions of rows. The size of the uuid needed to join filled the available RAM, everything slowed to a crawl and the system collapsed.

The uuid as primary key can be seen as a risk multiplicator : it will amplify any performance issue you may have, converting a temporary slowness into a full system stop.


What about taking the longer view? Most technologies, including plastics, were a lot more expensive than the products they replaced before going mainstream, with society organizing around them and subsidizing many of the costs.

For instance, take petrol-powered cars. It took building cemented roads, petrol stations, petrol distribution networks, supertankers, boats, trucks, car companies, refineries, etc. Cities are built for cars, with large roads while space is at a premium and could be used for something else. All that was 100x more expensive than horses and came with a new set of problems.

Another topic: plastic "feels" cheaper, but it's because some costs are not factored into the price, for instance in environment and health. I am not endorsing the following report, just citing it as an example of this idea: https://wwf.panda.org/wwf_news/?3507866/These-costs-for-plas...


All this counts into the "I'm usually very pro-tech". The point I'm contesting here is pure ideological regulation, without numbers behind it. Ban on plastic bags is actually the perfect example. You can calculate the number of times you need to actually use a reusable bag before it breaks even, and it's stratospheric. I'm not googling for a (potentially biased) source, but I'm sure you've seen such numbers.

And the downside is twofold. First, there's actually a pretty decent correlation between how expensive something is and how harmful for the environment. If you use a hand-made cloth bag made from cotton that was hand-grown in a garden using only renewable energy, it's expensive because you have a higher number of man-hours spent on it - and those man-hours are actually generating orders of magnitude more negative externalities for the simple fact of keeping those workers alive. The 1 cent plastic bag may be made from oil using energy from burning coal, but it's actually much cleaner because it used only a fraction of the man-hours. Whenever you hear claims that "it's a lot more expensive but it's green", the first guess is somebody didn't factor in everything.

The second downside is that bans are taking choice away. If you think there are negative externalities, and you have a good enough argument - by all means, tax those plastic bags until you compensate. If there are still objections to people buying the more expensive plastic bags, those objections are most likely ideological, not practical. Which yes, I still continue to hate with a fiery passion.


> If you use a hand-made cloth bag made from cotton that was hand-grown in a garden using only renewable energy, it's expensive because you have a higher number of man-hours spent on it - and those man-hours are actually generating orders of magnitude more negative externalities for the simple fact of keeping those workers alive.

This style of energy accounting makes no sense to me. Humans are going to use up resources and create pollution, regardless of what their specific source of income happens to be. More artisanal cotton bags means less of something else, in some broad sense, but that says nothing about the environmental accounting of the other side of the margin. The ratio of workers making luxury goods vs. mass producing cheaper substitutes for those goods will have little to no bearing on how many humans happen to exist, birth rates are clearly dominated by other factors.


I don't want to start a flame war, so I'll stop there.

I want to share a podcast you may be interested in, because it's dicussing how to price nature from an economic perspective:

Pricing Nature is a limited-series podcast from the Yale Center for Business and the Environment and the Yale Carbon Charge. It tells a story about the economics, politics, and history of carbon pricing, which many argue should play a critical role in any national climate policy. We feature conversations with carbon pricing experts from government, academia, and civil society. To learn more, visit our website, pricingnature.substack.com.


I was a bit "flamy" with my first comment, sorry. I'm honestly not very into podcasts - short attention span? But if by any chance you have a written source I'll probably take a peek.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: