A few random notes from Claude coding quite a bit last few weeks • Hacker News Board

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

#691

Post by ppseafield » Wed, Jan 28, 2026, 4:26 PM UTC

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.

The argument Socrates is making is specifically that writing isn't a substitute for thinking, but it will be used as such. People will read things "without instruction" and claim to understand those things, even if they do not. This is a trade-off of writing. And the same thing is happening with LLMs in a widespread manner throughout society: people are having ChatGPT generate essays, exams, legal briefs and filings, analyses, etc., and submitting them as their own work. And many of these people don't understand what they have generated.

Writing's invention is presented as an "elixir of memory", but it doesn't transfer memory and understanding directly - the reader must still think to understand and internalize information. Socrates renames it an "elixir of reminding", that writing only tells readers what other people have thought or said. It can facilitate understanding, but it can also enable people to take shortcuts around thinking.

I feel that this is an apt comparison, for example, for someone who has only ever vibe-coded to an experienced software engineer. The skill of reading (in Socrates's argument) is not equivalent to the skill of understanding what is read. Which is why, I presume, the GP posted it in response to a comment regarding fear of skill atrophy - they are practicing code generation but are spending less time thinking about what all of the produced code is doing.

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

#692

Post by fragmede » Wed, Jan 28, 2026, 4:27 PM UTC

SenHeng wrote: post #684

daxfohl wrote: post #65

I worry about the "brain atrophy" part, as I've felt this too. And not just atrophy, but even moreso I think it's evolving into "complacency". Like there have been multiple times now where I wanted the code to look a certain way, but it kept pulling back to the way it wanted to do things. Like if I had stated certain design goals recently it would adhere to them, but after a few iterations it would forget again and g…

Another thing I’ve experienced is scope creep into the average. Both Claude and ChatGPT keep making recommendations and suggestions that turns the original request into something that resembles other typical features. Sometimes that’s a good thing, because it means I’ve missed something. A lot of times, especially when I’m just riffing on ideas, it turns into something mundane and ordinary and I’ll have lost my earli…

yeah but that's like recommending a webserver for your Internet facing website. If you want to give an example of scope creep, you need a better example than double entry book keeping for an accounting app.

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

#693

Post by kakapo5672 » Wed, Jan 28, 2026, 4:28 PM UTC

vardalab wrote: post #93

spaceman_2020 wrote: post #53

Once again, 80% of the comments here are from boomers. HN used to be a proper place for people actually curious about technology

I'm almost a boomer and I agree. THis dichotomy is weird. I am retired EE and I love the ability to just have AI do whatever I want for me. I have it manage a 10 node proxmox cluster in my basement via ansible and terraform. I can finally do stuff I always wanted but had no time. I got sick of editing my kids sports videos for highlights in Davinci Resolve so just asked claude to write a simple app for me and then us…

Same demographic, same experience. AI has been incredibly liberating for me. I get all sorts of things done now that before were previosly impossible for all practical purposes. Among other things, it cuts through the noise of all the layers of detail, and allows me to focus on ideas, design, and just getting stuff built asap.

I also don't get all the hand-wringing. AI is an amazing tool. Use it and be happy.

Even less do I get all the cope about it not being effective, or even useless at some level. When I read posts such as that, it feels like a different planet. Just not my experience at all.

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

#694

Post by apercu » Wed, Jan 28, 2026, 4:29 PM UTC

laserlight wrote: post #587

apercu wrote: post #564

Earlier quoted context omitted.

HN is where I keep hearing the “50× more productive” claims the most. I’ve been reading 2024 annual reports and 2025 quarterlies to see whether any of this shows up on the other side of the hype. So far, the only company making loud, concrete claims backed by audited financials is Klarna and once you dig in, their improved profitability lines up far more cleanly with layoffs, hiring freezes, business simplification,…

I have friends who make such 50x productivity claims. They are correct if we define productivity as creating untested apps and games and their features that will never ship --- or be purchased, even if they were to ship. Thus, “productivity” has become just another point of contention.

100% agree. There are far more half-baked, incomplete "products" and projects out there now that it is easier to generate code. Generously, that doesn't necessarily equate to productivity.

I've agree with the fact that the last 10% of a project is the hardest part, and that's the part that Gen-AI sucks at (hell, maybe the 30%).

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

#695

Post by beepbooptheory » Wed, Jan 28, 2026, 4:38 PM UTC

aswegs8 wrote: post #619

daxfohl wrote: post #65

I worry about the "brain atrophy" part, as I've felt this too. And not just atrophy, but even moreso I think it's evolving into "complacency". Like there have been multiple times now where I wanted the code to look a certain way, but it kept pulling back to the way it wanted to do things. Like if I had stated certain design goals recently it would adhere to them, but after a few iterations it would forget again and g…

"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 (being a relatively early Plato dialogue). Socrates, characteristically, doesn't really give his take on writing. In the text, he is just trying to help his friend write a horny love letter/speech!

I can't bring it up right now, but the end of the dialogue has a rather beautiful characterization of writing in the positive, saying that perhaps logos can grow out of writing, like a garden.

I think if pressed Socrates/Plato would say that LLM's are merely doxa machines, incapable of logos. But I am just spitballing.

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

#696

Post by taylorius » Wed, Jan 28, 2026, 4:39 PM UTC

draxil wrote: post #533

throwup238 wrote: post #322

Earlier quoted context omitted.

How long until “the LLM did it it” is just as effective as “AWS is down, not my fault”?

This to me is the point.. LLMs can't be responsible for things. It sits with a human.

Why can LLMs not be responsible for things? (genuine question - I'm not certain myself).

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

#697

Post by SenHeng » Wed, Jan 28, 2026, 4:42 PM UTC

fragmede wrote: post #692

SenHeng wrote: post #684

Earlier quoted context omitted.

Another thing I’ve experienced is scope creep into the average. Both Claude and ChatGPT keep making recommendations and suggestions that turns the original request into something that resembles other typical features. Sometimes that’s a good thing, because it means I’ve missed something. A lot of times, especially when I’m just riffing on ideas, it turns into something mundane and ordinary and I’ll have lost my earli…

yeah but that's like recommending a webserver for your Internet facing website. If you want to give an example of scope creep, you need a better example than double entry book keeping for an accounting app.

You’ve just illustrated exactly the problem. You assumed I was building an accounting app. I’ve experienced the same issue with building features for calculating the brightness of a room, or 3D visualisations of brightness patterns, managing inventory and cataloguing lighting fixtures and so on.

It’s great for churning out stuff that already exists, but that also means it’ll massage your idea into one of them.

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

#698

Post by jjfoooo4 » Wed, Jan 28, 2026, 4:43 PM UTC

chrisjj wrote: post #278

jjfoooo4 wrote: post #87

Earlier quoted context omitted.

That was true for me, but is no longer. It's been especially helpful in explaining and understanding arcane bits of legacy code behavior my users ask about. I trigger Claude to examine the code and figure out how the feature works, then tell it to update the documentation accordingly.

> I trigger Claude to examine the code and figure out how the feature works, then tell it to update the documentation accordingly. And how do you verify its output isn't total fabrication?

I read through it, scanning sections that seem uncontroversial and reading more closely sections that talk about things I'm less sure about. The output cites key lines of code, which are faster to track down and look at than trying to remember where in a large codebase to look.

Inconsistencies also pop up in backtesting, for example if there's a point that the llm answers different ways in multiple iterations, that's a good candidate to improve docs on.

Similar to a coworker's work, there's a certain amount of trust in the competency involved.

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

#699

Post by spopejoy » Wed, Jan 28, 2026, 4:43 PM UTC

akoboldfrying wrote: post #552

gregjor wrote: post #516

Earlier quoted context omitted.

I don't understand why anyone finds it interesting that a machine, or chatbot, never tires or gets demoralized. You have to anthromorphize the LLM before you can even think of those possibilities. A tractor never tires or gets demoralized either, because it can't. Chatbots don't "dive into a rabbit hole ... and then keep digging" because they have superhuman tenacity, they do it because that's what software does. If…

You're a machine. You're literally a wet, analog device converting some forms of energy into other forms just like any other machine as you work, rest, type out HN comments, etc. There is nothing special about the carbon atoms in your body -- there's no metadata attached to them marking them out as belonging to a Living Person. Other living-person-machines treat "you" differently than other clusters of atoms only bec…

Humans and all other organisms are "literally" not machines or devices by the simple fact that those terms refer to works made for a purpose.

Even as an analogy "wet machine" fails again and again to adequately describe anything interesting or useful in life sciences.

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

#700

Post by nemothekid » Wed, Jan 28, 2026, 4:45 PM UTC

azrazalea_debt wrote: post #598

nemothekid wrote: post #400

Earlier quoted context omitted.

> I had the thought that you ought be able to provide a cargo doc or rust-analyzer equivalent over MCP? This... must exist? I've found that there are two issues that arise that I'm not sure how to solve. You can give it docs and point to it and it can generally figure out syntax, but the next issue I see is that without examples, it kind of just brute forces problems like a 14 year old. For example, the input system…

> What would be the cargo doc or rust-analyzer equivalent for good architecture? Well, this is where you still need to know your tools. You should understand what ECS is and why it is used in games, so that you can push the LLM to use it in the right places. You should understand idiomatic patterns in the languages the LLM is using. Understand YAGNI, SOLID, DDD, etc etc. Those are where the LLMs fall down, so that's…

What you describe is how I use LLM tools today, but the reason I am approaching my project in this way is because I feel I need to brace myself for a future where developers are expected to "know your tools"

When I look around today - its clear more and more people are diving in head first into fully agentic workflows and I simply don't believe they can churn out 10k+ lines of code today and be intimately familiar with the code base. Therefore you are left with two futures:

* Agentic-heavy SWEs will eventually blow up under the weight of all their tech debt

* Coding models are going to continue to get better where tech debt wont matter.

If the answer if (1), then I do not need to change anything today. If the answer is (2), then you need to prepare for a world where almost all code is written by an agent, but almost all responsibility is shouldered by you.

In kind of an ignorant way, I'm actually avoiding trying to properly learn what an ECS is and how the engine is structured, as sort of a handicap. If in the future I'm managing a team of engineers (however that looks) who are building a metaphorical tower of babel, I'd like to develop to heuristic in navigating that mountain.