Hacker Newsnew | past | comments | ask | show | jobs | submit | bonesss's commentslogin

Past the sea change: half the reason those prompt and harness solutions seem to work are LLM-lies, the testing is gassing you about how it works and the efficacy, defaulting to ‘yes’.

If you test specific features of those solutions over time you see very inconsistent results, lots of lies, and seemingly stable solutions that one-shot well but suddenly experience behaviour changes due to tweaks on the backend. Tuesdays awesome agent stack that finally works is loading totally different on Thursday, and debugging is “oh, sorry, it’s better now” even when it isn’t. Compression, lies, and external hosting are a bad combo.

Sometimes I imagine a world where computers executed programs the same way each time. You could write some code once and run it a whole calendar month later with a predictable outcome. What a dream, we can hope I guess.


People are doing toy projects and praising them, while some are testing them in real world situations and not findings them that useful. But the former is labelling the latter as luddites and telling them they will be left behind.

As someone on the intersection of both (I've built a lot of vibe coded toy projects and lead a vibe coding initiative at work), they're both right and both wrong.

For a single dev team, vibe coding is great. Write specs, write plans, write code. I know what the project wants and needs because I'm the target market.

At work, I haven't written more than a few lines of code since December. But I work with other people vibe coding this same project. Lots of changing requirements and rapid iteration. Lots of mistakes were made by everyone involved. Lots of tech debt. Sure, we built something in 2 mos that would have otherwise taken us 6 mos, but now I'm fixing the mess that we caused.

I think the critical difference is the attitude towards our situation. My boss said to fix the AI harness so we can vibe code more confidently and freely. But other bosses might cut their losses and ban vibe coding. Who's right? I dunno. In both cases I'd just do what my boss wants me to do. But it's not that I don't want to be left behind. I don't want to lose my job. There's a difference.


> Sure, we built something in 2 mos that would have otherwise taken us 6 mos, but now I'm fixing the mess that we caused.

You didn't actually build it in 2 months.


Even if it takes me a month to get us to fix (likely a week tbh), then it took us 3 months to build.

A mere 2x productivity improvement sounds like something you could achieve by introducing new tools that are predictable (i.e.: Not AI).

Perhaps. 2x is still 2x. And new tools still need to be vetted and learned.

It's strange that the goalpost seems to have moved from "AI is net negative to productivity" to "only 2x improvement isn't worth it"


As an extension of that kind of betting, a sitting President owning a crypto coin, and private social media platform he bolsters with his official duties, are shocking departures from norms around self-enrichment.

> The only way to meaningfully defeat surveillance technology is to make a constitutional amendment that limits its use privately and publicly

So, contextually, a constitutional amendment to force private and public use of Juggalo Makeup?

It’s extreme, but bold change requires bold steps.


All in favor, say aye!

The right of the people to keep and drink Faygo shall not be infringed.

woop woop!

It also hints even The Big Guys can’t LLM their tooling fully, and that current bleeding edge “AI” companies are doing that IT thing of making IT for IT (ie dev components, tooling, etc), instead of conquering some entire market on one continent or the other…

Makes you really think about the true productivity. If these companies have the beyond cutting-edge unreleased models so best possible tools shouldn't they be able to poach just a few most important people for cheaper? And then those people could use AI to build new superior product in very fast time. There is also buying an userbase. But I wonder how the key talent purchase strategy would work in comparison...

I made this joke in another thread, but: I keep imagining Afromans court getup as the formal attire for American civil lawyers. Like robes and wigs, suits n ‘fros.

The same way Brits use robes and wigs, I think it would be fitting for American lawyers to dress in flag suits, flag aviators, and a formal Afro.

Twitter is not like it always was. The presence of oranges doesn’t speak to the volume or rot-level of the apples.

Twitter has lost advertisers, credibility, and legitimacy. That’s objectively demonstrable in the calibre, quantity, and aims of their advertisers, and their loss of revenue.

Twitter is hurting humanity, and has swaths of the population trapped in misinformation clouds. Arguably Elon bought the last election by purchasing it, and current administration issues are the result. But for the slow acclimatization and general brain fog of the “etch a sketch voters” we’d see Twitters direct reprogramming of opinion and behaviour as a psychic virus. You can tell which app people are hooked on by the lies they believe (with great emotional resonance).

Social Media is becoming increasingly restricted from children based on objective developmental and cognitive impacts, I dare speculate we and our parents are the asbestos eating unfiltered cigarette smoking pre-modern victims who misused something terribly until we figured out how bad that shizz is for us.


And what about frequent chats with work friends?

No, not work, just hey how ya doin, and then someone brings coffee, then there’s a quick gab about the game, then a half baked question before a little catchup about that show. 2-4x salaries and minutes being burnt in small untracked chunks.

Hours clocked and hours worked are not the same.


When I worked at a public company I was told to expect 80% max productivity from my people. If my team routinely entered more time than that against capitalizable projects I would get called out and have to explain how that could be true.

What you are talking about is people being people and should already be accounted for. If you need to track untracked chunks and minutes something is very wrong, and it is either your management of your people or that you work at a zombie company that can't afford enough workers and is only surviving on unrealistic labor expectations.


I believe they’ve also deployed hybrid solutions: FPV fibre drones launched and piloted via link to an unmanned platform.

So a drone boat with good/secure signalling pulls up and a bunch of fibre optic drones launch from that point penetrating inland.


CLI’s and shell commands can be wrapped by and packaged into scripts, those scripts can have meaningful names. On Windows at least you can assign special icons to shortcuts to those scripts.

I’ve used that approach to get non-technical near-retirees as early adopters of command line tooling (version control and internal apps). A semantic layer to the effect of ‘make-docs, share-docs, get-newest-app, announce-new-app-version’.

The users saw a desktop folder with big buttons to double click. Errors opened up an email to devs/support with full details (minimizing error communication errors and time to fix). A few minutes of training, expanded and refined to meet individual needs, and our accountants & SME’s loved SVN/Git. And the discussion was all about process and needs, not about tooling or associated mental models.


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

Search: