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

A staff engineer's journey with Claude Code

sanity.io

Post reply on HN
Print view View original

361–370 of 410 posts

Re: A staff engineer's journey with Claude Code

#361

Post by zarzavat »

sunir wrote: post #308
spicyusername wrote: post #290

I guess we're just going to be in the age of this conversation topic until everyone gets tired of talking about it. Every one of these discussions boils down to the following: - LLMs are not good at writing code on their own unless it's extremely simple or boilerplate - LLMs can be good at helping you debug existing code - LLMs can be good at brainstorming solutions to new problems - The code that is written by LLMs…

All true if you one shot the code. If you have a sophisticated agent system that uses multiple forward and backward passes, the quality improves tremendously. Based on my set up as of today, I’d imagine by sometime next year that will be normal and then the conversation will be very different; mostly around cost control. I wouldn’t be surprised if there is a break out popular agent control flow language by next year…

> If you have a sophisticated agent system that uses multiple forward and backward passes, the quality improves tremendously.

Just an hour ago I asked Claude to find bugs in a function and it found 1 real bug and 6 hallucinated bugs.

One of the "bugs" it wanted to "fix" was to revert a change that I had made previously to fix a bug in code it had written.

I just don't understand how people burning tokens on sophisticated multi-agent systems are getting any value from that. These LLMs don't know when they are doing something wrong, and throwing more money at the problem won't make them any smarter. It's like trying to build Einstein by hiring more and more schoolkids.

Don't get me wrong, Claude is a fantastic productivity boost but letting it run around unsupervised would slow me down rather than speed me up.

Re: A staff engineer's journey with Claude Code

#362

Post by oblio »

codyb wrote: post #328
coldpie wrote: post #319

Earlier quoted context omitted.

I'm thiiiis close to writing a Firefox extension that auto-hides any HN headline with an LLM/AI-related keyword in the title, just so I can find something interesting on here again.

It comes and goes in cycles... I remember the hay days of MVC frameworks and oh my this one is MVVC! ad nauseum for... years lol. I stopped coming here for a year or two, now I visit once a day or so and mostly just skim a couple threads. Eventually, this entire field... just starts to feel pretty cyclical.

Keep in mind that the cycles here are not circles, they're spirals. We > progressing, it's just very slow to notice.

A bit of proof: https://www.joelonsoftware.com/2000/08/09/the-joel-test-12-s...

1. Do you use source control? - I haven't seen a software company without source control in... 2 decades?

2. Can you make a build in one step? - This is a bit tricky, but it super widespread. Maybe not universal, but very widespread.

3. Do you make daily builds? - Same as #2.

4. Do you have a bug database? - Same as #2.

5. Do you fix bugs before writing new code? - This is a debatable topic but you could argue that modern bugs are more complex and we are fixing them.

6. Do you have an up-to-date schedule? - Heh, some things you just can't win :-p

7. Do you have a spec? - Similar to #6.

8. Do programmers have quiet working conditions? - This one is the biggest modern failure, but it's not one of tech.

9. Do you use the best tools money can buy? - Similar to #2.

10. Do you have testers? - We've moved to automated testing. We've lost some flair but we've gained a lot in day-to-day quality.

11. Do new candidates write code during their interview? - Really widespread now, but not universal. Less widespread than having proper build systems.

12. Do you do hallway usability testing? - Varies a lot by field, it used to vary even back in the day.

Re: A staff engineer's journey with Claude Code

#363

Post by oblio »

sunir wrote: post #308
spicyusername wrote: post #290

I guess we're just going to be in the age of this conversation topic until everyone gets tired of talking about it. Every one of these discussions boils down to the following: - LLMs are not good at writing code on their own unless it's extremely simple or boilerplate - LLMs can be good at helping you debug existing code - LLMs can be good at brainstorming solutions to new problems - The code that is written by LLMs…

All true if you one shot the code. If you have a sophisticated agent system that uses multiple forward and backward passes, the quality improves tremendously. Based on my set up as of today, I’d imagine by sometime next year that will be normal and then the conversation will be very different; mostly around cost control. I wouldn’t be surprised if there is a break out popular agent control flow language by next year…

> and also just the Moore’s law of the hardware and energy costs.

What Moore's law?

Re: A staff engineer's journey with Claude Code

#364

Post by rhubarbtree »

M4v3R wrote: post #243
rhubarbtree wrote: post #212

Does anyone have a link to a video that uses Claude Code to produce clean robust code that solves a non trivial problem (ie not tic tac toe or a landing page) more quickly than a human programmer can write? I don’t want a “demo”, I want a livestream from an independent programmer unaffiliated with any AI company and thus not incentivised to hype. I want the code to have subsequently been deployed in production and de…

I've live streamed how I've built a tower defense game over a span of a week entirely using AI. I've also written down all the prompts were used to create this game, you can read about it here: https://news.ycombinator.com/item?id=44463967 Mind you I've never wrote a non-trivial game before in my life. It would take me weeks to do this on my own without any AI assistance. Right now I'm working on a 3d world map edito…

> Now of course you've made so many qualifiers in your post that you'll probably dismiss this as "not production", "not robust enough", "not clean" etc

Sure, my interest is whether it’s suitable for production use on an existing codebase, ie for what constitutes most of software engineering.

But - thanks for sharing, I will take a look and watch some of the stream.

Re: A staff engineer's journey with Claude Code

#365

Post by rhubarbtree »

infamousclyde wrote: post #257
rhubarbtree wrote: post #212

Does anyone have a link to a video that uses Claude Code to produce clean robust code that solves a non trivial problem (ie not tic tac toe or a landing page) more quickly than a human programmer can write? I don’t want a “demo”, I want a livestream from an independent programmer unaffiliated with any AI company and thus not incentivised to hype. I want the code to have subsequently been deployed in production and de…

Jon Gjengset (of MIT Missing Semester, Rust for Rustsceans, etc) shared a stream doing complex changes of increasing complexity to a geospatial math library in Rust. He’s an excellent engineer, and was able to pick apart AI-suggested changes liberally. The caveat is that the video is a bit long, but segmented nicely. I think he had a positive experience overall, but it was clear throughout the stream that he was not…

Thanks! This looks great (correct link in the child comment).

Re: A staff engineer's journey with Claude Code

#366

Post by rhubarbtree »

Difwif wrote: post #296
Aeolun wrote: post #265

Earlier quoted context omitted.

> I suspect videos meeting your criteria are rare because most AI coding demos either cherry-pick simple problems or skip the messy reality of maintaining real codebases. Or we’re just having too much fun making stuff to make videos to convince people that are never going to be convinced.

I took a quick informal poll of my coworkers and the majority of us have found workflows where CC is producing 70-99% of the code on average in PRs. We're getting more done faster. Most of these people tend to be anywhere from 5-12 yrs professional experience. There are some concerns that maybe more bugs are slipping through (but also there's more code being produced). We agree most problems stem from: 1. Getting laz…

> Having too much fun turning ideas into products to care about proving a point.

This is a strange response to me. Perhaps you and others aren’t aware that there’s a subculture of folks who livestream coding in general? Nothing to do with proving a point.

My interest in finding such examples is exactly due to the posting of comments like yours - strong claims of AI success - that don’t reflect my experience. I want to see videos that show what I’m doing wrong, and why that gives very different results.

I don’t have an agenda or point to prove, I just want to understand. That is the hacker way!

Re: A staff engineer's journey with Claude Code

#367

Post by rhubarbtree »

MontyCarloHall wrote: post #280
rhubarbtree wrote: post #212

Does anyone have a link to a video that uses Claude Code to produce clean robust code that solves a non trivial problem (ie not tic tac toe or a landing page) more quickly than a human programmer can write? I don’t want a “demo”, I want a livestream from an independent programmer unaffiliated with any AI company and thus not incentivised to hype. I want the code to have subsequently been deployed in production and de…

Forget a livestream, I want to hear from maintainers of complex, actively developed, and widely used open-source projects (e.g. ffmpeg, curl, openssh, sqlite). Highly capable coding LLMs have been out for long enough that if they do indeed have meaningful impact on writing non-trivial, non-greenfield/boilerplate code, it ought to be clearly apparent in an uptick of positive contributions to projects like these.

Yes, this would be really useful.

AI coding should be transforming OSS, and we should be able to get a rough idea of the scale of the speed up in development. It’s an ideal application area.

Re: A staff engineer's journey with Claude Code

#368

Post by rhubarbtree »

simonw wrote: post #261
rhubarbtree wrote: post #212

Does anyone have a link to a video that uses Claude Code to produce clean robust code that solves a non trivial problem (ie not tic tac toe or a landing page) more quickly than a human programmer can write? I don’t want a “demo”, I want a livestream from an independent programmer unaffiliated with any AI company and thus not incentivised to hype. I want the code to have subsequently been deployed in production and de…

Armin Ronacher (long-time Python and Rust open source community figure, creator of Flask and Jinja among others) has several YouTube videos that partially fit the bill. https://www.youtube.com/watch?v=sQYXZCUvpIc and https://www.youtube.com/watch?v=Y4_YYrIKLac and https://www.youtube.com/watch?v=tg61cevJthc

I’d say they’re a good match, thanks for sharing! Will watch in detail.

Re: A staff engineer's journey with Claude Code

#369

Post by rhubarbtree »

adastral wrote: post #332
rhubarbtree wrote: post #212

Does anyone have a link to a video that uses Claude Code to produce clean robust code that solves a non trivial problem (ie not tic tac toe or a landing page) more quickly than a human programmer can write? I don’t want a “demo”, I want a livestream from an independent programmer unaffiliated with any AI company and thus not incentivised to hype. I want the code to have subsequently been deployed in production and de…

PostgresTV livestreams "vibe coding" 1h sessions implementing small PostgreSQL features with Cursor (mostly claude-4-sonnet model) every week, by experienced PostgreSQL contributors. [0] is their latest stream. I personally have not watched much, but it sounds just like what you are looking for! [0] https://www.youtube.com/watch?v=3MleDtXZUlM

Yes, good enough for me, thanks. I look forward to watching it. This is particularly interesting as it’s a group stream.

Re: A staff engineer's journey with Claude Code

#370

Post by rhubarbtree »

dewey wrote: post #232
rhubarbtree wrote: post #212

Does anyone have a link to a video that uses Claude Code to produce clean robust code that solves a non trivial problem (ie not tic tac toe or a landing page) more quickly than a human programmer can write? I don’t want a “demo”, I want a livestream from an independent programmer unaffiliated with any AI company and thus not incentivised to hype. I want the code to have subsequently been deployed in production and de…

One of these things where you just have to put in the work yourself for a while and see how it works for your workflow and project.

That’s unusual though? I think programming languages, idioms, features - for example - are adopted by consensus, not by every programmer starting out from scratch and evaluating each one.
Post reply on HN