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

641–650 of 870 posts

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

#641

Post by Schlagbohrer »

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…

Reminiscent of a time just a year or two ago where the LLMs would get downright frustrated and sassy

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

#642

Post by an0malous »

hollowturtle wrote: post #596
phito wrote: post #593

Earlier quoted context omitted.

It's because we see a bunch of people completely ignoring the missing 20% and flooding the world with complete slop. The push back is required to keep us sane, we need people reminding others that it's not at 100% yet even if it sometimes feels like it.

Then you have Anthropic that states on his own blog that engineers fully delegate to claude code only from 0 to 20% https://www.anthropic.com/research/how-ai-is-transforming-wo... The fact that people keep pushing figures like 80% is total bs to me

It’s usually people doing side projects or non-programmers who can’t tell the code is slop. None of these vibe coding evangelists ever shares the code they’re so amazed by, even though by their own logic anyone should be able to generate the same code with AI.

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

#643

Post by havefunbesafe »

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.

Ive found that clearing the context and getting back to it later actually DOES work. When you restart, your personal context is cleared and you might be better at describing the problem you are solving in a more informationally dense way.

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

#644

Post by bob1029 »

phito wrote: post #593
elif wrote: post #589

Why am I not surprised that a blog was written about LLM coding going from 20% to 80% useful, yet all of the HN comments are still nit picking about some negative details rather than building positive ideas toward some progress... Is the programmer ego really this fragile? At least luddites had an ideological reasoning, whereas here we just seem to have emotional reflexes.

It's because we see a bunch of people completely ignoring the missing 20% and flooding the world with complete slop. The push back is required to keep us sane, we need people reminding others that it's not at 100% yet even if it sometimes feels like it.

This kind of thought policing is getting to be exhausting. Perhaps we need a different kind of push back.

Do you know what my use case is? Do you know what kind of success rate I would actually achieve right now? Please show me where my missing 20% resides.

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

#645

Post by gyomu »

markb139 wrote: post #474

I retired from paid sw dev work in 2020 when COVID arrived. I’ve worked on my small projects since with all development by hand. I’d followed the rise of AI, but not used it. Late last year I started a project that included reverse engineering some firmware that runs on an Intel 8096 based embedded processor. I’d never worked on that processor before. There are tools available, but they cost many $. So, I started to…

> Vendors of small utilities could be in trouble

This is a mix of the “in the future, everyone will have a 3D printer at home and just 3D print random parts they need” and “anyone can trivially build Dropbox with rsync themselves” arguments.

Tech savvy users who know how to use LLMs aren’t how vendors of small utilities stay in business.

They stay in business because they sell things to users who are truly clueless with tech (99% of the population, which can’t even figure out the settings app on their phone), and solid distribution/marketing is how you reach those users and can’t really be trivially hacked because everyone is trying to hack it.

Or they stay in business because they offer some sort of guarantee (whether legal, technical, or other) that the users don’t want to burden themselves with because they have other, more important stuff to worry about.

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

#646

Post by Schlagbohrer »

mlrtime wrote: post #548
ryanjshaw wrote: post #524

Earlier quoted context omitted.

I realized a long time ago that I’m better at computer stuff not because I’m smarter but because I will sit there all day and night to figure something out while others will give up. I always thought that was my superpower in the job industry but now I’m not so sure if it will transfer to getting AI to do what I need done…

Same, I barely made it through Engineering school, but would stay up all night figuring out everything a computer could do (before the internet). I did it because I enjoyed it, and still do. I just do it with LLMs now. There is more to figure out than ever before and things get created faster than I have time to understand them. LLM should be enabling this, not making it more depressing.

Me three. I was not as smart as many of my peers in uni but I freakin LOVE the subject matter and I also love studying and feeling that progress of learning, which led me to put in the huge number of hours necessary to be successful and have a positive attitude the whole time.

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

#647

Post by simonw »

chrisjj wrote: post #527
simonw wrote: post #503

Earlier quoted context omitted.

https://gisthost.github.io/?a41ce6304367e2ced59cd237c576b817... - which built https://github.com/datasette/datasette-transactions exactly the way I wanted it to be built

> exactly the way I wanted it to be built You verified each line?

I looked closely enough to confirm there were no architectural mistakes or nasty gotchas. It's code I would have been happy to write myself, only here I got it written on my phone while riding the BART.

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

#648

Post by grogenaut »

throw10920 wrote: post #628
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…

Writing/reading and AI are so categorically different that the only way you could compare them is if you fundamentally misunderstand how both of them work. And "other people in the past predicted doom about something like this and it didn't happen" is a fallacious non-argument even when the things are comparable.

I know managers who can read code just fine, they're just not able/willing to code it. Tho the ai helps with that too. I've had a few managers dabble back into coding esp scripts and whatnot where I want them to be pulling unique data and doing one off investigations.

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

#649

Post by cactusplant7374 »

energy123 wrote: post #427
brcmthrowaway wrote: post #411

Earlier quoted context omitted.

When?

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.

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

#650

Post by gritspants »

phito wrote: post #521
gritspants wrote: post #172

Earlier quoted context omitted.

My disillusionment comes from the feeling I am just cosplaying my job. There is nothing to distinguish one cosplayer from another. I am just doordashing software, at this point, and I'm not in control.

What kind of software are you writing? Are you just a "code monkey" implementing perfectly described Jira tickets (no offense meant)? I cannot imagine feeling this way with what I'm working on, writing code is just a small part of it, most of the time is spent trying to figure out how to integrate the various (undocumented and actively evolving) external services involved together in a coherent, maintainable and resi…

No, I am not a code monkey. I have an odd role working directly for an exec in a highly regulated industry, managing their tech pursuits/projects. The work can range from exciting to boring depending on the business cycle. Currently it is quite boring, so I've leaned into using AI a bit more just to see how I like it. I don't think that I do.
Post reply on HN