selestify

How are they cheap? Does your organization offer unlimited spend, or does your subscription not run into the same limits as mine?

> But we've also spend a lot of effort over the past year and a half to make the codebase and tooling more approachable to LLMs so they know how we like to do things and follow our standards.

Anything more you can say about this? We desperately need to restructure and standardize our codebase right now.

> if a company offered a 20$/mo service that brings subscribers to the endpoint, carried in a luxury litter by robotized carriers, I would feel that my hobby has been devoided of sense.

As someone else who hikes: why? I do not understand. Do you not enjoy the hobby of hiking for the sake of hiking?

The views will be just as beautiful, the air just as fresh, and the feeling of moving my legs just as energizing, regardless of how others may decide to get to the destination themselves. Why would the experience of others have any impact on my own experience of a trail?

> I don't understand why this question comes up so often.

You don't understand because baked into your entire reply is the assumption that a decent standard of living is guaranteed.

Based on current trends around economic inequality, it seems quite likely that the average person may be given very little to subsist on once their main source of leverage (their ability to perform valuable labor) has been removed.

How is this any more of an upwards money funnel than the prohibitively expensive spreads and commissions that hindered lay access to the markets?

So that some team at Google can hit their OKRs for user adoption and get promoted.

Because some people care a lot more about Ukraine than about a side with pretty unsavory combatants and a radicalized population that supports said unsavory combatants?

Any good descriptions of what it feels like to take part in a formal Turing test, and why it is so humbling?

Geez that's even worse. Google has a deterministic conventional programming fix to the problem and still can't be arsed to fix it?

Why would the turnaround time need to be so small?

What a great analogy, can't believe I haven't heard it before

Ok, but my problem is that what it builds is not right. It's never right on the first try, or the second or third tries. There's always a ton of incremental corrective feedback needed.

Do you run into this problem? If not, then I need to figure out how to stop running into it myself.

If so, then how do you give it all the incremental corrective feedback without a conversation?

The behavior, while slightly exaggerated, rings entirely true for me. From the other comments in this thread, it seems I am prompting poorly in a similar way to the options offered.

I am guessing you prompt differently than what is shown in the game?

Is your harness available for install somewhere?

Surely you still have to give feedback to Claude. How do you do that without talking to Claude directly? By using a different model? But wouldn't that AI have no more common sense than Claude?

What legitimate issues are there around making a fucking button blue?

How is "Make the shopping button blue" not specific? Any human with a lick of digital common sense would be able to understand what I obviously mean. How am I supposed to anticipate every single way the AI could possibly misinterpret a simple fucking instruction like that?

So how would you prompt it instead? Because that's exactly how I prompt it, because any reasonable human being would know exactly what I mean by "Make the shopping button blue", and I am sick and tired of getting shitty results.

How does one learn to interact with Claude more effectively?

Care to share any more?

Very good in theory. In practice, how do you actually understand yourself? I have done plenty of meditation and plenty of reading on mental health and psychology. I still don't understand why I specifically act the way I do.

Well, with all due respect you could've worded that better. It sounded as if you were making a blanket statement over all individual jobs that involve RSUs, as opposed to a statement over all jobs as an aggregated statistic.

Cost of medical care is already sky high (in the US). Are you sure you want to introduce even more administrative overhead?

This was not my experience working at FAANG. RSU's started out as 30% of my comp and ended up well over 60% by the time I left.

Either way, definitely not "might as well round to zero". I have never worked anywhere where that was the case.

Just ask for citations by forcing the LLM to provide a verbatim quote from a linked source. If the LLM is incapable of doing so without hallucinating (cough, Gemini, cough) use a better one.

I don't get the LLM hate on this site sometimes. Just because it is easy to use an LLM irresponsibly doesn't mean all LLM usage has to be irresponsible.

And lawyers bill by 6-minute increments, yet that doesn't mean you get access to all of a law firm's internal discussions and notes about you and your case.

Just because you paid for the lawyer time/LLM tokens doesn't mean you get access to everything that happened within that time/tokens.

I'm not saying they're not useful, of course they are. I am disputing that they are part of the agreed bargain between you and the proprietary LLM providers.

They explicitly do not promise reasoning traces. You (general you) agree to those terms and pay for that bargain anyways.

How is that a more fair comparison? The consulting firm in this case never promised you the interim reports, only the summaries of the reports. They also promised you the final output that the reports led to. You decided that report summaries + final output was worth paying for. You got exactly what you were promised.

I have never talked to sales. How do they find this out smoothly, without insulting the person being talked to for not having any actual authority?

Why was that? What causes such fads? Why did everyone go along with it?

The Chinese market for one seems pretty optimistic about AI and the presence of AI in apps.