Hacker News new | past | comments | ask | show | jobs | submit login

Can't help but feel weird about all the thanking in the letter, especially the "sincere" thanks to Tasha and Helen, the possible main antagonists in this soap opera.

It's like a written version of the heart emojis in their Twitter exchanges.




Yes, but helping these people save face smoothes the transition. My guess is that those folks were waaay out of their depth and they naturally made naive mistakes. It doesn't benefit anyone to stomp on them. I'm sure they learned hard lessons, and Sam's message is what we call "grace", which is classy.

Is it politics? Sure, but only in the best sense. By not dunking on the losers, he builds trust and opens the doors for others to work with him. If you work with Sam and make a mistake, he's not going to blast you. It's one reason that there was such a rallying of support around Sam, because he's a bridge-builder, not a bridge-burner. Over time, those bridges add up.

Silicon Valley has a long memory and people will be working with each other for decades. Forgiving youthful mistakes is a big part of why the culture works so well.


They may have been way out of their depth but they also may have been the only ones taking their roles somewhat seriously. They've now been shown what the true balance of power is like and that is a lesson they are probably not going to forget. Unfortunately they also threw away the one shot they had at managing this and for that their total contribution goes from net positive to net negative. I don't think that in a break-the-glass scenario it would have gone any different but they were there for the ride to see how their main role was a performative one rather than an actual one and it must have been a very rude awakening to come to realize this.

It would be poetic justice if the new board fires Sam Altman next week, given the amount of drama so far I am not sure if I would be surprised or not.


If Sam get’s fired I am moving to a HN clone with filters so I can ignore anything related to AI


Reeks of CEO speak; general bullshit that seems to go against all practical reasoning of the situation.

Don't fall for it.


Might you describe CEO speak as not consistently candid?


Not being consistently candid seems like the sort of thing you'd get fired for.


We call him SAlty.


>Reeks of CEO speak; general bullshit that seems to go against all practical reasoning of the situation.

Funnily enough this is the type of thing that chatGPT is excellent at writing.


prompt: You are an optimistic, politically correct corporate magnate. You may be wrong, but never in doubt.


That's just ChatGPT though, minus the "corporate magnate" part.


You could make that prompt a lot sharper.

For the CEO of any large multinational:

prompt: You are a lying, scheming conniving s.o.b. but outwardly you are a savior and a team player acting in all of humanity's interest. Anything you say that has negative connotations or that can be explained by greed, lust for power or outright evil should be carefully crafted to be presented as the opposite. You will put yourself before everything, including the rest of the world, the environment, and ultimately all of humanity. Your mission: to collect as much power as possible but to do so in a way that you are rarely forced to show your hand and when you do there should be ample ways in which it can be interpreted that show you as the good guy.


this is probably a chatgpt prompt starting with "I am VC Bro, write a letter as I come back as CEO and thank everyone who was involved in the stabbing, and dont forget to use cliche stuff like turn a crisis into an opportunity"


Here's what ChatGPT 4 (paid version) responded with for that exact prompt:

---

Subject: Embracing New Horizons Together

Dear Team,

As I resume my role as CEO, I am filled with gratitude and renewed vigor. The recent challenges we faced were not mere setbacks, but stepping stones that have strengthened our resolve and unity.

I want to extend my deepest appreciation to each one of you who stood by me and our company during these testing times. Your unwavering support was not just a lifeline; it was a powerful testament to our collective strength and dedication.

This experience has not only been a learning curve but also a vivid reminder of the incredible potential we possess as a team. We turned a crisis into a golden opportunity, showcasing resilience and adaptability that are hallmarks of our company culture.

As we move forward, let's harness this momentum to propel us towards new heights. Our journey ahead is filled with possibilities, and together, we will continue to innovate, disrupt, and lead.

Thank you for your steadfast commitment and for believing in our vision. Here's to turning challenges into triumphs and continuing our journey of excellence.

Warm regards,

[Your Name] CEO [Your Company]


That is f'ing scary because I think I've read a letter or two just like that.


> I've read a letter or two just like that.

So did the LLM.

Likely thousands as non-fiction, perhaps magnitudes more as fiction, satirical, or speculative. And I bet I'm still missing zeroes — countless business leaders have been writing this drivel a long time.

It's hard for us to keep in mind the sheer scope of online copy. Less hard for LLMs, that's why they feel to me like magic in the Arthur C Clarke sense. I have to keep reminding myself nothing's new under the sun.

This has all happened before, it will all be generated again.


The difference is: I wouldn't be able to regurgitate it on a moment's notice adapted to the situation at hand.


In my eyes, the LLM took very generic high-level instructions, interpreted them correctly, and then followed the instructions to generate output text that was similar to what it had seen before.

What it didn't do was to just use the input prompt as the key into a gigantic lookup table and find the corresponding output text.

A different example of this is when an LLM can correctly interpret a sentence like "the trumpet did not fit in the suitcase because it was too big / small".

Here, "big" would refer to the trumpet, while "small" would refer to the suitcase. This becomes important when translating to German, where "the" comes in different flavors for "trumpet" and "suitcase".

ChatGPT interprets this correctly. It can also explain in detail why "too big" / "too small" makes sense or not for the different interpretations.

You could argue that this is still just a lookup response. But I have a hard time seeing how it can have stored so many different variants in the amount of bytes that the LLM is made up of?

--

ChatGPT explanation for trumpet / suitcase:

Let's delve into the logic and reasoning behind which noun the size descriptor applies to in each of your sentences:

"The trumpet did not fit in the suitcase because it was too big."

In this sentence, the logical interpretation is that the trumpet is too large to fit inside the suitcase. It's understood that if an object doesn't fit into a container, the issue is typically that the object is too large for the container's capacity.

Hence, "it was too big" naturally refers to the trumpet, not the suitcase. It wouldn't make much sense to say a suitcase is "too big" to contain something; if the suitcase were bigger, it would more likely accommodate the trumpet.

"The trumpet did not fit in the suitcase because it was too small."

Here, the logical understanding is that the suitcase is too small to contain the trumpet. When an object doesn't fit into a container due to size, and the descriptor is "too small," it implies that the container isn't large enough.

In this case, "it was too small" refers to the suitcase. If the sentence intended to say the trumpet was too small, it would contradict the idea of not fitting; a smaller trumpet would more likely fit into the suitcase, not less.

In both sentences, the key is understanding how size descriptors (big, small) interact with the concept of fitting something into something else. The size issue that prevents the fitting is logically attributed to the object that needs to be accommodated (the trumpet) in terms of being too big, or to the accommodating object (the suitcase) in terms of being too small.


Their actions vastly, unexpectedly to them, enhanced his leverage. It may well be sincere!


Being the bigger man and giving backhanded compliments often sound similar. Either is better that tirades against your defeated enemies, at least when you're trying to act as a civil business.

A heavy sigh, a bit of grumbling, might be more honest, but there's a reason that businesses prefer to keep a stuff upper lip.


Reading between the lines, I see "I harbor zero ill will towards [Ilya]... we hope to continue our working relationship." but no such comments directed at Helen and Tasha. Given how sanitized these kinds of releases usually are, I took that to mean "" in this context.


Ilya essentially accused Altman of lying to the board. Hearing "zero ill will" from a liar looks like intimidation to me. Especially if we take into account his previous history.


Maybe it's BS corporate gibberish, I don't know. But Sam has always struck me as an honorable person who genuinely cares. I don't think he's vindictive; I think he genuinely supports them. You can disagree immensely and still respect each other – this isn't about money, it's potentially about the world's future, and Sam likely understands what happened better than we do.

Or maybe it's bullshit, I don't know.


That had me laughing out loud, thank you.


We know the board said that he was two-faced and that was one of the reasons he was fired.




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

Search: