Wow that's bold.

It is. It is also rare and late. Possibly too late. But let's hope it is not and that this will inspire some other people to draw lines in the sand.

Hard disagree. "I'm an expert" in that I have done tons of proofs on many systems with many provers, both academically and professionally for decades.

Also, I am a novice when it comes to programming with sound, and today I have been dorking with a simple limiter. ChatGPT knows way more than me about what I am doing. It has taught me a ton. And as magical and wonderful as it is, it is incredibly tedious to try to work with it to come up with real specifications of interesting properties.

Instead of banging my head against a theorem prover that won't say QED, I get a confident sounding stream of words that I often don't even understand. I often don't even have the language to tell it what I am imagining. When I do understand, it's a lot of typing to explain my understanding. And so often, as a teacher, it just is utterly failing to effectively communicate to me why I am wrong.

At the end of all of this, I think specification is really hard, intellectually creative and challenging work. An LLM cannot do the work for you. Even to be guided down the right path, you will need perseverance and motivation.

When I ran the numbers, I realized commuting for RTO was going to cost the equivalent of 6 full time weeks of work. My whole team is at a different location. So I am driving in to be on Zoom calls. It is deeply pointless and frustrating.

I mentioned all of this to my boss, who is great btw, and was told there is just no fighting this. After several months of trying to make the best of it, I’m done. I’m planning to leave after my next vest.

It’s really a shame. I liked a lot about the job. So many good people have been forced out.

Why does it have to be more friction?

Users had a global way to signal “do not track me” in their browser. I don’t know why regulators didn’t mandate respecting that instead of cookie consent popups.

Apple IDs could easily have global settings about what you are comfortable with, and then have their apps respect them.

At my FAANG company, our leadership is super unbalanced in favor of white/asian men.

We have some empty words about diversity but no goals or metrics, so nothing effective will actually change.

As a (white, male) manager, I have huge power over who gets to interview. My network is, sadly, largely white/asian and male. So if I don’t even think about it, I will perpetuate the imbalance.

I haven’t seen bonuses tied to diversity. I have seen a promo doc where a manager was praised for increasing diversity, with a greater percentage of women now in his department. I then discovered he had hired 1 woman and 26 men, raising his percentage of women from 0. I’m not kidding.

You could lead by example and replace your own role with a "diverse" candidate?

Yes. I’m now close to retirement and am grooming my successor to replace me next year.

For now, I’m focusing my mentorship energy on promising women and minorities, and helping them network.

Shrug. I’ve done a lot of intensely creative work in my pajamas. I’ve burned a lot of unproductive hours on commuting and pointless in-person meetings.

Me too! I can understand why many/most folks might not have a lot of sympathy for formerly highly paid tech workers tho.

Personally, even for the not-so-highly paid tech workers, if you're complaining about "some foreigner willing to do it for less", you don't get a lot of sympathy from me. If they can do it, and are willing to do it for less, good on them!

Complaining about less well off folks coming and taking our jobs seems so Un-American. I'd be upset to lose my job, no doubt. But I'd be in good company.

I know there are a lot of folks eager to tell me how naive/ignorant I am, but the bottom line is that I'm allergic to entitlement.

Will they though?

We humans are very good at rejecting any information that doesn’t confirm our priors or support our political goals.

Like, if ChatGPT says (say) vaccines are good/bad, I expect the other side will simply attack and reject it as misinformation, conspiracy, and similar.

From what I can see, LLMs default to being sychophants; acting as if a sychophant was neutral is entirely compatible with the cognitive bias you describe.

This feels like the right take.

Once we have an AI starting to do something, there’s an art to gradually adopting it in a way that makes sense.

We don’t lose the ability to have humans review code. We don’t have to all use this on every PR. We don’t have to blindly accept every comment it makes.

1 is super interesting.

I’ve found it’s nice to talk to an LLM about personal issues because I know it’s not a real person judging me. Maybe if the comments were kept private with the dev, it’d be more just a coaching tool that didn’t feel like a criticism?

Private with the Dev, the operator & everyone who uses any product of the training data they build.

I’d be curious to hear more on Attempt 2. It sounds like the approach was basically to ask an llm for a score for each comment. Adding specifics to this prompt might go a long way? Like, what specifically is the rationale for this change, is this likely to be a functional bug, is it a security issue, how does it impact maintainability over the long run, etc.; basically I wonder if asking about more specific criteria and trying to define what you mean by nits can help the LLM give you more reliable scores.

That’s an interesting point - we didn’t try this. Now that you said that, I bet even clearly defining what each number on the scale means would help.