In gemini:

> The reverse of the string 'gssssyeekxxuoaqaaaiooo9aaa7zjx' is:

xjz7aaa9oooiiaaaqauxxkyeessssg

> Youve made a mistake

``` I see where I tripped up! Let's re-examine that long string carefully.

The original string you gave me was: `gssssyeekxxuoaqaaaiooo9aaa7zjx`

Let's look at the end of that string: `...aaa7zjx`. When we reverse it, it should start with: `xjz7aaa...`

Here is the precise character-by-character reversal:

*xjz7aaa9oooiiaaaqauxxkyeessssg*

Wait—I see it now. In my previous response, I included an extra *'i'* and missed one *'o'* in the middle section. Let's do a strict count to get it perfect:

* *Original:* `g` `ssss` `y` `ee` `k` `xx` `u` `o` `a` `q` `aaa` *`iooo`* `9` `aaa` `7` `z` `j` `x` * *Correct Reverse:* `x` `j` `z` `7` `aaa` `9` *`oooi`* `aaa` `q` `a` `o` `u` `xx` `k` `ee` `y` `ssss` `g`

The correct reversed string is: *xjz7aaa9oooiiaaaqauoxxkyeessssg*

Thank you for catching that. It’s easy for the eyes to glaze over when there are so many repeating vowels!

Since I've stumbled a bit on these, would you like to give me one more string to see if I can get it right on the first try? ```

After more back and fors it consistently fails in this task, even though when strictly dividing the tokens it will get this right. Yet the final answer is always wrong.

Mine said it used python and got: xjz7aaa9oooiaaaqaouxxkeeyssssg

* stares at presidents / party leaders, religious leaders, social media influencers, tv stars, singers *

No, surely no

I guess who cares about civility if you're the last man standing.

Also - that word: civility. We're animals driven by self-interest. What should civility even mean here

> We're animals driven by self-interest. What should civility even mean here

That self-interest has led to cooperation between humans. Humans have evolved to work together, cooperate, form social bonds, and friendships because doing so improves survival and wellbeing over the long run. Civility is part of that toolkit. It is not a denial of self-interest. Civility is part of that self-interest.

Thank you, this is what I was trying to say… there are incentives to cooperate, even though individually we can be selfishly evil.

I don't understand how any of this is a surprise. Traditional media have their own agenda - sure, maybe the pushed image is spoken through many voices, rather than one, as is case of LLMs, but why should there be any difference. Same to everything we consume socially.

There is, nor there will be some absolute or objective truth an LLM can clinically outline. The problem already exists in underlying data.

I understand that SE needs to make money, but I find it fascinating how voluntary content (both questions, answers and moderation) is being monetised. Should I ask for percentage of ads income when my questions / answers are viewed?

There has to be some price tag associated with running Stack Overflow, but I wonder if it's within the range of something a collective could manage.

More and more I think we need volunteer projects running the things we depend on the most. Community driving email, forums, social networks and Q&A sites like Stack Overflow. A community driven Stack Overflow could still run a job board, or have the C# section be "Sponsored by Microsoft", or run a Jetbrains ad. If you only have to pay for hosting, then you need less ad revenue.

Stack Overflow famously ran on a half-rack of servers, duplicated in two locations for redundancy. This stopped when they got acquired by a cloud company - they were moved into the cloud. But it's clearly both possible and not too expensive.

I see prices around me for $500-ish/month for half-rack colo. Of course you have to bring your own servers if using this option.

> Volunteer admins with nothing better to do get their dopamine by closing questions for StackOverflow points, regardless of whether the supposedly duped question from 8 years ago is actually still the best answer and covers the nuances of the question now being asked.

This rung so true to me, given that my answer from 4y ago was closed as a duplicate of an answer made 3m ago :D (no, the nuances were not considered and the questions were ultimately too different; this didn't influence moderation decision at all and I was very confused on how I've made a duplicate 4y ago of a question in, at that time, the future)

Agree and follow this principle to certain degree, however there are caveats here - something being a blocker shouldn't prevent you from trying to resolve the blockers by yourself or work with your boss to resolve them ie - "hey boss, I'm blocked with task A with refactor of this code; are you happy for me to do XYZ?". Then I have options to say: "yes! excellent! go ahead!" or "no, we need to do ASD here" or "no, we cannot do XYZ right now". If every time people encountering blockers would come to me to resolve them, or wait until they're resolved I'd not get anything done. On the flipside, if every time a blocker is encountered people were to handle it themselves, then a) it might not align with my vision on what actually needs to be done here b) I'm blindsighted with what was actually done.

Clear boundaries and strategies eliminate these caveats = team members are aligned on what they can make decision for and general direction the team is heading towards.

Yeah like I said if we are straying in to over-reliance/not really doing our job, he clearly lays out what to do and says "there go take care of it" a few times. He does a good job of not fostering a culture of constantly playing CYA

But this is an issue of worker you're hiring. I've worked with senior engineers who a) did nothing (as - really not write any thing within the sprint, nor do any other work) b) worked on things they wanted to work on c) did ONLY things that they were assigned in the sprint (= if there were 10 tickets in the sprint and they were assigned 1 of these tickets then they would finish that ticket and not pick up anything else, staying quiet) d) worked only on tickets that have requirements explicitly stated step by step (open file a, change line 89 to be `checkBar` instead of `checkFoo`... - having to write this would take longer than doing the changes yourself as I was really writing in Jira ticket what I wanted the engineer to code, otherwise they would come back with "not enough spec, can't proceed"). All of these cases - senior people!

Sure - LLMs will do what they're told (to a specific value of "do" and "what they're told")

Sure there is a wide spectrum of skills, having worked in FANG and top tier research I have a pretty good idea of the capability at the top of the spectrum. I know I wasn't hiring at that level. I was paying 2x the local market rate (non-US) and pulling from the functional programming talent pool. These were not the top 1% but I think they were easily top 10% and probably in the top 5%.

I use LLMs to build isolated components and I do the work needed to specialize them for my tasks and integrate them together. The LLMs take fewer instructions to do this and handle ambiguity far better. Additionally because of the immediate feedback look on the specs I can try first with a minimally defined spec and interactively refine as needed. It takes me far less work to write specs for LLMs than it does for other devs.

> But this is an issue of worker you're hiring.

You're (unwittingly?) making an argument for using an LLM: you know what you're going to get. It does not take six months to evaluate one; six minutes suffice.

The argument I'm trying to make is that hiring a real person or using LLMs has upsides and downsides. People have their own agendas, can leave, can affect your business in many ways, unrelated to code etc, but also can learn, can be creative and address problems that you've not even surfaced. LLM will not and will not be capable of that.

With LLMs you know what you're going to get to a certain value. Will it not listen to you? No. Will it not follow your instructions? Maybe. Will it produce unmaintainable garbage? Most certainly. Does that matter for nondevs? Sometimes

If you are a “senior” engineer who is doing nothing but pulling well defined Jira tickets off the board, you’re horribly mis titled.

> That’s the way we’ve always done it.

I'd read this - "I decided some time ago that's how it's done and none should question nor know about the reasons". Not explaining the reasons (if they are not clear) is gatekeeping.

Let it all crash and burn