906 karma · joined June 19, 2018
I inherited some vibe-coded scripts that dealt with AWS services like Bedrock and S3. These scripts needed create various AWS SDK clients. These clients needed to know which account/region to use.
Had this been well designed, there would have some function/module responsible for deciding what account/region to use. This decision point might be complex: it might consider things like environment variables, configuration files, and command line arguments. It might need to impose some precedence among these options. Whatever these details, the decision would be authoritative once made. The rest of the code base should have expected a clear decision and just do what was decided.
Instead, the coding assistant added optional account/region arguments in many submodules. These arguments were nullable. When left unspecified, "convenient" logic did its own environment lookups and similar. The result was many "works on my machine" failures because command-line arguments affected only certain portions of the program, environment variables others, config files still others.
This is grim stuff. It's a ton of code that should not exist, spreading the decision all over the code.
This is a beautiful articulation of a major pet peeve when using these coding tools. One of my first review steps is just looking for all the extra optional arguments it's added instead of designing something good.
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.
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.
For now, I’m focusing my mentorship energy on promising women and minorities, and helping them network.
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.
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.
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.
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.
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?
I think I would much rather own the critique myself than say “the team thinks x.”
For context, I’d probably start with “what happened with that deployment that was rolled back?” and let them self-diagnose and share their perspective. By listening, I might learn there were extenuating issues, or I may see they are already aware of the issue.
If they’re able to critique their own work, I can agree and reinforce the whys. There’s no hostility and we can talk about what ideas we have for what we can do going forward.
If not, and I think we must do better, I can talk about my concerns, my expectations, and the consequences that I am worried about or frustrated by, and propose more prescriptive remedies.
Writing dumb scripts that can call out to sophisticated LLMs to automate parts of processes is utterly game changing. I saved at least 200 hours of mundane work this week and it was trivial.
I’ve never spent more than 20k for a car. With prices like this, I’m just going to keep my old one as long as I can.
Anyway, they won. It’s over. Bygones.
I do very much agree with your ideal of nobody persecuting one another.
I don’t see how you square that ideal with, e.g., anti-abortion policies, mass deportations, support for brutal policing, anti-trans hysteria including CPS interventions, bringing bibles and chaplains into schools, and the like.
Maybe we’re all the same. I see vaccines and espousing tolerance and demanding respect for people’s preferred pronouns and such as justified for what I see as the social good. Perhaps you see strong borders and order and christian values as a similarly imperative for the social good. We both feel victimized and like the other is a massive hypocrite, because we just want different worlds?