Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Appearing productive in the workplace

nooneshappy.com

Post reply on HN
Print view View original

471–480 of 686 posts

Re: Appearing productive in the workplace

#471

Post by tardedmeme »

randycupertino wrote: post #292
dr_kiszonka wrote: post #176

Earlier quoted context omitted.

I work under the assumption that the primary audience of everything I write at work is an AI. Managers will take what I send and have it summarized and evaluated by some chatbot or agent. (Of course, I cannot send them the summary myself.) So like ATS checkers for resumes, I find myself needing an AI checker for my text. Ultimately, we will have AI write everything for another AI to parse, which will be a massive was…

I go through this with my vendor budgets and contract negotiations right now. We are encouraged to put all their proposals in AI and have it refute each point. I know for a fact they are putting my negotiations in their own AI and having it counter-propose my points. It's an arms race of my AI fighting against their AI. Where does it end.

Ends when you tell them "this AI shit is ridiculous so we are choosing a different vendor"

Re: Appearing productive in the workplace

#472

Post by wartywhoa23 »

randycupertino wrote: post #292
dr_kiszonka wrote: post #176

Earlier quoted context omitted.

I work under the assumption that the primary audience of everything I write at work is an AI. Managers will take what I send and have it summarized and evaluated by some chatbot or agent. (Of course, I cannot send them the summary myself.) So like ATS checkers for resumes, I find myself needing an AI checker for my text. Ultimately, we will have AI write everything for another AI to parse, which will be a massive was…

I go through this with my vendor budgets and contract negotiations right now. We are encouraged to put all their proposals in AI and have it refute each point. I know for a fact they are putting my negotiations in their own AI and having it counter-propose my points. It's an arms race of my AI fighting against their AI. Where does it end.

Where is uncertain, but how is: badly.

Re: Appearing productive in the workplace

#473

Post by tardedmeme »

stefan_ wrote: post #430
mediaman wrote: post #130

Earlier quoted context omitted.

I think it likely performed well in A/B preference tests with chat users. I've noticed Claude does far fewer listicles than ChatGPT. I suspect that they don't blindly follow supervised learning feedback from chats as much as ChatGPT. I get Apple vs Google design approach from those two companies, in that Apple tends not to obsess over interaction data, instead using design principles, while Google just tests everythi…

There was a time when also Claude would absolutely fill code with emojis, which is why now their system prompt has > Claude does not use emojis unless the person in the conversation asks it to

I think it's funny how we are all tweaking LLM output by adding instructional tokens instead of, say, finding a vector that indicates "user asked for emojis", and forbidding emoji tokens in the sampling unless that vector passes a threshold.

Re: Appearing productive in the workplace

#474

Post by Pannoniae »

reverius42 wrote: post #344
Pannoniae wrote: post #278

Earlier quoted context omitted.

Sure but even wiring that utility function in is work :D If you have even just a 2-3-million LoC codebase, not even something truly enormous - making global changes does require typing, and a whole lot of it...

If you have a codebase that big, can you even fit enough of it into a context window for the LLM to make correct and meaningful changes across all of it? Admittedly I've only used LLM-based coding for smaller projects.

All of it hell no :D But just with any things, you break things down into subtasks. Then you break it down even more. You as a human don't hold all that stuff in your head either, so why would an LLM?

My current codebase is ~3 million LoC all in all (not greenfield, really old code), working on it by myself, the complexity is definitely manageable between Claude and me :)

Re: Appearing productive in the workplace

#475

Post by tardedmeme »

jeremyjh wrote: post #243
beachy wrote: post #230

Earlier quoted context omitted.

My friend built a construction management SaaS entirely via Claude. It looked damned impressive, and it kind of worked to demo, but he is in no way a programmer, though he understood the problem domain very well. I asked a few basic questions: - where is the data stored? - How would you recover from a database failure? - does it consume tokens at runtime? - what is the runtime used at the back end? - why are the web…

One of the riskier bets my team is currently making is that this is exactly what is needed, and nearly nothing more. We have LOB prototypes vibe coded by enthusiastic domain experts that we are supporting in a “port and release” fashion. A senior engineer takes the prototype and uses Claude code to generate a reasonable design, do an initial rough port (~80% functional, 100% auth & audit logging) and (hopefully) all…

Is CRUD low stakes? Even if all you do with the employee database is read and write employees, losing it or corrupting it is disastrous, potentially business-ending.

Re: Appearing productive in the workplace

#476

Post by skydhash »

mike_hearn wrote: post #434
zbentley wrote: post #202

Earlier quoted context omitted.

Another commenter above this proposed a pretty compelling theory for the source of this style: SEO-inflated prose online. If the models were trained on the internet, "higher quality" content needed to be indicated to them during RL somehow. Search engine ranking is an easy-to-obtain metric that's kind of like "quality" if you squint, turn around, and lobotomize yourself. So the AIs have a high likelihood of producing…

That's circular though. Why does that content get ranked highly? Because it gets a lot of backlinks, long clicks, etc. So people seem to like it.

> Why does that content get ranked highly?

Search engines only show a snippet of the content and that always looks convincing. It's the whole content that is off and, unfortunately, a few seconds/minutes can pass before you realize it (If you ever do).

Re: Appearing productive in the workplace

#477

Post by tardedmeme »

LinuxAmbulance wrote: post #92
funimpoded wrote: post #57

Earlier quoted context omitted.

I increasingly see “AI” as a sort of virus tuned to target management, specifically. Its output is catnip to them, and it’s going to be unavoidable for those who want to look good to superiors and peers (i.e. the #1 priority for managers) even as it adds no actual value whatsoever to what they do. People under them, too, will have to start burning tokens on bullshit to satisfactorily perform competence and “doing wor…

AI has made my work about 5-8x quicker, just because I'm able to have it cover a lot of the grunt work (update 42 if statements in 32 different files) that took time, but no particular skill. I think the use cases where AI makes an economic improvement to the status quo for a business are rare, but they do exist, and they can be a significant improvement. It's like the early days of the dotcom boom and bust - people…

Does your work primarily consist of updating 42 if statements in 32 different files? We all do that occasionally, but if you're doing it constantly, is it possible that a different system design would make your work much easier?

Re: Appearing productive in the workplace

#478

Post by tardedmeme »

2ndorderthought wrote: post #237
spaniard89277 wrote: post #204

Earlier quoted context omitted.

Guys just go and ride it. It's their money. They decided to do this. They think you guys are stupid. Suck. Them. Dry. Or say goodbay, which is what I did on my previous role when the BS started to get obvious. Now I do LLM-assisted coding on my own terms. I decide what to do, review output and push back agains overengineered BS. But I'm a lucky one, as far as I can see. --- NO-ONE is going to be able to understand th…

I couldn't do it. It made me feel crazy. Looking back though, now I don't have a job and that stinks. Oh well at least I don't get nightmares about debugging the next production issue on call.

Can't you just tell Claude to fix it and if Claude can't fix it, it must be impossible to fix so oh well?

Re: Appearing productive in the workplace

#480

Post by tardedmeme »

danaw wrote: post #129

i have a strong suspicion that the most productive software teams that leverage llms to build quality software will use it for the following: - intelligent autocomplete: the "OG" llm use for most developers where the generated code is just an extension of your active thought process. where you maintain the context of the code being worked on, rather than outsourcing your thinking to the llm - brainstorming: llms can…

I'd add rapid mockups/prototyping as well. Not suitable for production use but very suitable for iterating until it looks right, and then you go and make it for real.
Post reply on HN