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

A few random notes from Claude coding quite a bit last few weeks

twitter.com

Post reply on HN
Print view View original

731–740 of 870 posts

Re: A few random notes from Claude coding quite a bit last few weeks

#731

Post by danans »

ryandrake wrote: post #658
KronisLV wrote: post #554

Earlier quoted context omitted.

> I feel like most apps at most companies can just build an app and deploy it using some modern paas-like thing. Most companies (in the global, not SV sense) would be well served by an app that runs in a Docker container in a VPS somewhere and has PostgreSQL and maybe Garage, RabbitMQ and Redis if you wanna get fancy, behind Apache2/Nginx/Caddy. But obviously that’s not Serious Business™ and won’t give you zero downt…

> Most companies (in the global, not SV sense) would be well served by an app that runs in a Docker container in a VPS somewhere and has PostgreSQL and maybe Garage, RabbitMQ and Redis if you wanna get fancy, behind Apache2/Nginx/Caddy. That’s still too much complication. Most companies would be well served by a native .EXE file they could just run on their PC. How did we get to the point where applications by defaul…

> That’s still too much complication. Most companies would be well served by a native .EXE file they could just run on their PC

I doubt that.

As software has grown to solving simple personal computing problems (write a document, create a spreadsheet) to solving organizational problems (sharing and communication within and without the organization), it has necessarily spread beyond the .exe file and local storage.

That doesn't give a pass to overly complex applications doing a simple thing - that's a real issue - but to think most modern company problems could be solved with just a local executable program seems off.

Re: A few random notes from Claude coding quite a bit last few weeks

#732

Post by energy123 »

cactusplant7374 wrote: post #649
energy123 wrote: post #427

Earlier quoted context omitted.

I don't know when but I'm going off: - "OpenAI is partnering with Cerebras to add 750MW of ultra low-latency AI compute" - Sam Altman saying that users want faster inference more than lower cost in his interview. - My understanding that many tasks are serial in nature.

Speed is really important to me but also I would like higher weekly limits -- which means lower cost I suppose. Building out complex projects can take 6 months to a year on a Pro plan.

Same experience with Pro.

My trick is to attach the codebase as a txt file to 5-10 different GPT 5.2 Thinking chats, paste in the specs, and then get hard work done there, then just copy paste the final task list into codex to lower codex usage.

Re: A few random notes from Claude coding quite a bit last few weeks

#733

Post by rustyhancock »

mlrtime wrote: post #534
rustyhancock wrote: post #486

Earlier quoted context omitted.

One challenge is, are those decisions making tangible differences? We won't know until the code being produced especially greenfields hits any kind of maturity 5 years+ atleast?

It's not that challenging, the answer is, it depends. It's like a junior dev writing features for a product everyday vs a principle engineer. The junior might be adding a feature with O(n^2) performance while principle has seen this before and writes it O(log n). If the feature never reaches significance, the "better" solution doesn't matter, but it might! The principle may write once and it is solid and never touche…

There's that, but I actually think LLMs are becoming very good at not making the bad simple choice.

What they're worse at is the bits I can't easily see.

An example is that I recently was working on a project building a library with Claude. The code in pieces all looked excellent.

When I wrote some code making use of it several similar functions which were conceptually similar had signatures that were subtly mismatched.

Different programmers might have picked each patterns. And probably consistently made similar rules for the various projects they worked on.

To an LLM they are just happenstances and feel no friction.

A real project with real humans writing the code would notice the mismatch. Even if they aren't working on those parts at the same time just from working on it across say a weekend.

But how many more decisions do we make convenient only for us meat bags that a LLM doesn't notice?

Re: A few random notes from Claude coding quite a bit last few weeks

#734

Post by pvab3 »

direwolf20 wrote: post #708
pvab3 wrote: post #705

Earlier quoted context omitted.

because it doesn't have any skin in the game and can't be punished, and can't be rewarded for succeeding. Its reputation, career, and dignity are nonexistent.

This doesn't seem to have stopped anyone before.

Stopped anyone from doing what? Assigning responsibility to someone with nothing to lose, no dignity or pride, and immune from financial or social injury?

Re: A few random notes from Claude coding quite a bit last few weeks

#735

Post by Davidzheng »

lucianbr wrote: post #637
netcraft wrote: post #618

> Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. This is true to an extent for sure and they will go much longer than most engineers without getting "tired", but I've def seen both sonnet and opus give up multiple times. They've upd…

The glorified autocomplete. Why would the LLM "work on something else then get back on this", is it's subconscious going to solve the problem during that time? But because people say it, it says it too. Making sense is optional.

not impossible right? the new context can provide some needed hints, etc...

Re: A few random notes from Claude coding quite a bit last few weeks

#736

Post by mattmanser »

yencabulator wrote: post #685
mattmanser wrote: post #455

Earlier quoted context omitted.

Are ghost bugs even real? My first job had the Devs working front-line support years ago. Due to that, I learnt an important lessons in bug fixing. Always be able to re-create the bug first. There are no such thing as ghost bugs, you just need to ask the reporter the right questions. Unless your code is multi-threaded, to which I say, good luck!

> Unless your code is multi-threaded, to which I say, good luck! What isn't multi-threaded these days? Kinda hard to serve HTTP without concurrency, and practically every new business needs to be on the web (or to serve multiple mobile clients; same deal). All you need is a database and web form submission and now you have a full distributed system in your hands.

Only superficially so, await/async isn't usually like the old spaghetti multi-threaded code people used to write.

Re: A few random notes from Claude coding quite a bit last few weeks

#737

Post by dempedempe »

beepbooptheory wrote: post #695
aswegs8 wrote: post #619

Earlier quoted context omitted.

"For this invention will produce forgetfulness in the minds of those who learn to use it, because they will not practice their memory. Their trust in writing, produced by external characters which are no part of themselves, will discourage the use of their own memory within them. You have invented an elixir not of memory, but of reminding; and you offer your pupils the appearance of wisdom, not true wisdom, for they…

If one reads the dialogue, Socrates is not the one "saying" this, but he is telling a story of what King Thamus said to the Egyptian god Theuth, who is the inventor of writing. He is asking the king to give out the writing, but the king is unsure about it. Its what is known as one of the Socratic "myths," and really just contributes to a web of concepts that leads the dialogue to its ultimate terminus of aporia (bein…

https://standardebooks.org/ebooks/plato/dialogues/benjamin-j...

Re: A few random notes from Claude coding quite a bit last few weeks

#738

Post by yencabulator »

mattmanser wrote: post #736
yencabulator wrote: post #685

Earlier quoted context omitted.

> Unless your code is multi-threaded, to which I say, good luck! What isn't multi-threaded these days? Kinda hard to serve HTTP without concurrency, and practically every new business needs to be on the web (or to serve multiple mobile clients; same deal). All you need is a database and web form submission and now you have a full distributed system in your hands.

Only superficially so, await/async isn't usually like the old spaghetti multi-threaded code people used to write.

You mean in a single-threaded context like Javascript? (Or with Python GIL giving the impression of the same.) That removes some memory corruption races, but leaves all the logical problems in place. The biggest change is that you only have fixed points where interleaving can happen, limiting the possibilities -- but in either scenario, the number of possible paths is so big it's typically not human-accessible.

Webdevs not aware of race conditions -> complex page fails to load. They're lucky in how the domain sandboxes their bugs into affecting just that one page.

Re: A few random notes from Claude coding quite a bit last few weeks

#739

Post by daxfohl »

Now that it's real, is there a minimum bar of non-AI-generated code that should be required in any production product? Like if 100% of the code is AI generated (or even doom-tabbed) and something goes wrong in prod, (crash, record corruption, data leak, whatever) then what? 99%? 50%? What's the bar where the risk starts outweighing the reward? When do we look around and say "maybe we should start slowing down before we do something that destroys our company"?

Granted it's not a one-size-fits-all problem, but I'm curious if any teams have started setting up additional concrete safeguards or processes to mitigate that specific threat. It feels like a ticking time bomb.

It almost begs the question, what even is the reward? A degradation of your engineering team's engineering fundamentals, in return for...are we actually shipping faster?

Re: A few random notes from Claude coding quite a bit last few weeks

#740

Post by cagenut »

daxfohl wrote: post #739

Now that it's real, is there a minimum bar of non-AI-generated code that should be required in any production product? Like if 100% of the code is AI generated (or even doom-tabbed) and something goes wrong in prod, (crash, record corruption, data leak, whatever) then what ? 99%? 50%? What's the bar where the risk starts outweighing the reward? When do we look around and say "maybe we should start slowing down before…

obviously you're not a devops eng, I think you're wildly under-estimating how much of business critical code pre-ai is completely orphaned anyway.

the people who wrote it were contractors long gone, or employees that have moved companies/departments/roles, or of projects that were long since wrapped up, or of people who got laid off, or the people who wrote it simply barely understood it in the first place and certainly don't remember what they were thinking back then now.

basically "what moron wrote this insane mess... oh me" is the default state of production code anyway. there's really no quality bar already.

Post reply on HN