Care to share the prompt? Sounds useful!

Sure. Please improve it and come back around to let me know.

https://gist.github.com/prostko/5cf33aba05680b722017fdc0937f...

I've spent a heck of a lot more time grinding leetcode than I have working on take-home projects. I always enjoyed doing take-home's because I could really spend time on it and make it something worth showing off - if anything it always felt like the perfect low-stress way to show what you can do. It's amazing how many candidates don't take the time to make it look good (or even meet the objectives in many cases).

Haven't done one since pre-LLM era though and that path seems like it might be completely infeasible for employers now.

That said, the most productive interviews I've been a part of as both employee and employer have always been with the technical people that you'll actually work with and conversational in nature. You can learn a lot about what someone knows by listening to their experiences and opinions (but this depends greatly on the quality of the interviewer)

It would be nice to see an actual example of what a good claude.md that implements all of these recommendations looks like.

> or the most part, sexy never left, and statistics bear this out. OnlyFans brings in enormous amount of revenue, even after an expensive, failed attempt to be not-just-a-porn-site. Hypersexualized gacha games are pulling in tens of millions of dollars per month, and not just for men; the women-targeted Love and Deepspace had over $50 million in revenue in October. Marvel Rivals, criticized in some circles (such as the social circles of those in the article) for being an oversexualized "gooner game" has remained in the top 10 games played on Steam since its release a year ago. And nothing drives it home more than stumbling across the shady side of YouTube and finding videos in the "woman with large breasts not wearing a bra does something mundane" genre with multiple millions of views.

These are all things about sex but none of them are sex or lead to sex. These are outlets for sexual desires that don't require any social connection at all. You could argue that the article outlines many of the reasons why these things are so popular today - there is a much higher social price to pay for a potentially embarrassing or humiliating situation than there used to be. Easier to avoid it altogether and play gooner games.

>30 years ago it was rather normal that a manager would touch the behind of a coworker, which is clearly a bad thing. Nowadays looking in their direction a bit too long seems to be labeled 'not done'.

I was in the workforce 30 years ago and, no, it was absolutely not normal.

It was what we called an "HR violation" and a "Career limiting move."

Not sure where you were 30 years ago, but except in bordellos and strip clubs that wasn't "normal." Not even close.

It was not normal in a semse normal managers would do it and everyone would aprove.

On 1995, which is 30 years ago, it was neither normal nor accepted. You was major asshole if you did it and lawsuits were already won.

Perhaps in 1975. The earliest I remember a dude at the office getting fired for harassment was around 1988.

> 30 years ago it was rather normal that a manager would touch the behind of a coworker, which is clearly a bad thing. Nowadays looking in their direction a bit too long seems to be labeled 'not done'.

That was a huge no-no 30 years ago, at least in the US. In fact, it was a major no-no at my first job in 1979 and would get you fired.

Maybe I'm a few years off but you got my drift.

Fear is a bad advisor! I take the risk because i know that most people around me know me and trust that i say such things in good faith, without patronizing or overly flirting with people of the opposite sex. If it should have any profesional consequences, then maybe i would have the wrong employer.

You seem to be to afraid to be friends with your coworkers because of potential consequences? If that is so, i'm sorry, you are missing out a great deal in life.

I think this is right. Continue to connect with humans and try to evaluate their actions in good faith. Don’t be a creep but don’t skip life either.

Unfortunately if someone chooses to interpret your words or actions in an uncharitable way there’s not much you can do other than move on. It’s their burden to carry, not yours (except when there are real world consequences but I do think that’s a rare circumstance)

That sounds like a terrible advice that all the creeps are taking with predictable results.

A creep is going to be a creep with or without this advice.

I cannot tell if this is /s or not but yikes…

Yes! Good Working drone! You must keep on working, that’s your purpose after all!

Ah, Anglo-Saxon work culture, where one can't imagine not making friends at work because they have no social life outside of work.

Not making friends at work because you have fulfilled social life already, and not making friends at work to avoid any danger to your career are two very different things.

Not making friends at work, because it's not a good place to make friends, might push you towards ensuring having fulfilled social life outside of work.

I say this without rancor: unless I miss my mark, you don't live or work in the United States. You don't understand the stakes. I envy your life brother; I hope you appreciate it.

I live and work in Europe but I used to travel a lot for work to the US. Friendship or making friends indeed seems to work differently there, which was hard to grasp from my cultural pov. That said, I made a good friend there.

Do you have any idea why they (seemingly randomly) will drop the ball on some system prompt instructions in longer sessions?

Larger contexts are inherently more attention-taxing, so the more you throw at it, the higher the probability that any particular thing is going to get ignored. But that probability still varies from lower at the beginning to higher in the middle and back to lower in the end.

> Both DuckDuckGo and Kagi are, purely focused on result quality in 2025 far better than Google currently

I wish this was true

You don't have to take my word for it. Open the three next to each other, type in a search query. Only one will provide part of the results as a wildly inaccurate "overview" that somehow manages to link to sources telling you the opposite or contradicts itself inside the text box, which can also not be deactivated. Those are the results you get from Google and that alone makes quality worse, pure and simple.

More subjectively, but if you want to ignore the "AI overview" and consider that not results (then why are they on my results page?!), just look for a specific, slightly older video on Youtube, a site Alphabet themselves run. You can provide the exact title down to the letter and are in many instances going to struggle to find it with Youtube search or Googles Video Search, even when wrapping in ", etc. Kagi and DDGs video search tabs meanwhile yield the desired results. Again, this doesn't mean they are amazing or massively far ahead as Google was able to reliably provide such results in the past. It just means that Google Search has regressed, yet users stuck with it because, as I've been saying, quality (or lack thereof) has a hard time overcoming brand strength.

I had DDG set as my default for years and found myself resorting back to google so often I had to finally admit to myself their results were inferior even to the diminished google result. I just didn’t seem to get the result you’re claiming on the everyday type of queries I make.

> For instance you’re probably iterating over those six plans and inserting them individually in the DB. Another approach would’ve been to accumulate all of them in memory then build and perform a single query. That’s not something people really consider because it’s “micro” optimization and makes the code look worse.

This same pitfall exists in every language. This has nothing to do with Ruby.

eh. Ruby makes it easy to do the wrong thing. imo.

Maybe, but this isn’t one of the ways it does.

I have to spend 3 days working on someone else's "narratives that are more fun to apply their creativity to" all the time, even when my intuition and experience tells me it isn't a good idea. Sometimes my intuition is wrong. I've yet to meet a product manager that isn't doing this even when they claim to have all the data in the world to support their narrative.

Personally I don't think there's anything wrong with scratching that itch, especially if its going to make you/your team more comfortable long term. 3 days is probably not make-or-break.

Both 4k and 120hz were very noticeable improvements imo.

I like the best of both worlds approach of asking Claude to refine a spec with me (specifically instructing it to ask me questions) and then summarize an implementation or design plan (this might be a two step process if the feature is big enough)

When I’m satisfied with the spec, I turn on “allow all edits” mode and just come back later to review the diff at the end.

I find this works a lot better than hoping I can one shot my original prompt or having to babysit the implementation the whole way.

I recommend trying a more capable model that will read much more context too when creating specs. You can load a lot of full files into GPT 5 Pro and have it produce a great spec and give more surgical direction to CC or Codex (which don’t read full files and often skip over important info in their haste). If you have it provide the relevant context for the agent, the agent doesn’t waste tokens gathering it itself and will proceed to its work.

Is there an easy way to get a whole codebase into GPT 5 Pro? It's nice with claude to be able to say "examine the current project in the working directory" although maybe that's actually doing less than I think it is.

I wrote a tool for that: https://github.com/simonw/files-to-prompt - and there are other similar tools like repomix.

These days I often use https://gitingest.com - it can grab any full repo on GitHub has something you can copy and paste, e.g. https://gitingest.com/simonw/llm

I wrote a similiar tool myself, mostly because your tool or repomix doesn't support "presets" (saved settings):

    [client]
    root = "~/repo/client"
    include = [
        "src/**/*.ts",
        "src/**/*.vue",
        "package.json",
        "tsconfig*.json",
        "*.ts",
    ]
    exclude = [
        "src/types/*",
        "src/scss/*",
    ]
    output = "bundle-client.txt"

    $ bundle -p client

What do you do when you repeatedly need to bundle the same thing? Bash history?

omg you rock!

Of course you did - thanks, huge fan!