W and J are the SI units for power and energy. Those units make the most sense to use in Europe, regardless of the type of energy.
Wh is an abomination that has come about because professionals think consumer brains would expose if they ever saw the unit watt-seconds (J). No consumer had any preconceived notion of either Wh or J, so had we used J from the start, it wouldn't have been a problem...
(Yes, same with Ah vs C, though the battery pros also shot themselves in the foot by starting to use C (electrical charge) to mean "the capacity of this battery" when talking about charge rate, a.k.a. current.)
I dunno, 1kWh seems quite natural as a unit of building-scale energy usage when you know a kettle or space heater is about 3kW. We think about energy usage much more in terms of kW and hours than in watts and seconds. And even in small devices like an LED bulb, 5W is more obviously 0.005kW than, say, 2 hours is 7200 seconds.
And in this context it's much more obvious that it can notionally deliver energy at a peak rate of about 1% capacity per hour. If you said 1MW/360GJ, I don't think that would be nearly as clear.
Same for batteries, which started with car batteries/deep cycle batteries, rather than AA batteries, which usual don't even say, and phones. A battery that provides 1 amp (at 12V, but that's already given in a system) for 50 hours. Makes immediate practical sense, especially when equipment is often labelled in current draw and you can measure amps with an ammeter. 2.16MJ far less so.
I can understand the argument, but it's like your blood flow carrying the news that "cells are the point; not the human they make up." Every level of complexity thinks it's the main character.
I share the author's beliefs that organizations must be for the people, not the other way around. The big problem is not the existence of the tool, but that it's being used to explain layoffs instead of expansions, suggests that something else is broken in society. That could also just be media bias.
This idea that generative tools are bad is weird. I'm using Claude Code almost daily, and I find myself having to babysit it quite a lot because it keeps reverting fixes I made. Like an API URL that it strongly believes should be something it made up on its own. There's somewhat more time for sword fights, but it's not like I spend 10 minutes at the start of the day setting up Claude, and then come back at the end of the day to a finished solution.
It feels a bit like a practical P vs NP bruteforce attack on my problem space: applying heuristics to come up with solutions that I then simply verify the applicability, correctness and quality of.
My biggest issue with k8s on Hetzner is that there is no way of going from tiny (1 machine) to medium (10-100 machines) purely on bare metal. I was able to get Gateway API to provide ingress nodes after a bit of Envoy tinkering, but storage is an issue. You can't run Ceph Rook on a single machine (too heavy,) and I couldn't find a think local volume wrapper that lets me easily migrate from local volume management to distributed.
Feels like there should be a PV daemon that can do local, and transparent migrations and is lightweight enough to run on a single machine. Once my PV has been migrated to Ceph, the proxy could configure itself away from that job.
Is it just me that feels www.chiark.greenend.org.uk/~sgtatham/putty/ has some kind of sentimental value? I built a locked-down version fof PuTTY for their termainl-based (book) library system in 1998. It's been with me a long time.
but what would be the deducted amount, in dollar value, when the work is voluntary? Do you get assigned a dollar value per line, per hour worked, or you just guestimate?
I'm amazed at how prolific he is. I've interacted with him a couple of times, and he's always super polite and helpful. In spite of the fact that he is also churning through issues/code on a number of projects.
It looks like they may have used the sheet metal from the cybertruck to build it, so perhaps it was a way to make use of a stockpile of steel? And real estate is a good investment. I'm sure there's a tax subsidy in here somewhere too.
I predict microservices will get a huge push forward. The question then becomes if we're good enough at saying "Claude, this is too big now, you have to split it in two services" or not.
If LLMs maintain the code, the API boundary definitions/documentation and orchestration, it might be manageable.
Why not just cleanly separated code in a single execution environment? No need to actually run the services in separate execution environments just for the sake of an LLM being able to parse it, that’s crazy! You can just give it the files or folders it needs for the particular services within the project.
Obviously there’s still other reasons to create micro services if you wish, but this does not need to be another reason.
Why microservices? Monoliths with code-golfed minimal implementation size (but high quality architecture) implemented in strongly typed language would consume far less tokens (and thus would be cheaper to maintain).
Won’t this cause [insert LLM] to lose context around the semantics of messages passed between microservices?
You could then put all services in 1 repo, or point LLM at X number of folders containing source for all X services, but then it doesn’t seem like you’ll have gained anything, and at the cost of added network calls and more infra management.
What type of work do you do? And how do you measure value?
Last week I was using Claude Code for web development. This week, I used it to write ESP32 firmware and a Linux kernel driver. Sure, it made mistakes, but the net was still very positive in terms of efficiency.
> This week, I used it to write ESP32 firmware and a Linux kernel driver.
I'm not meaning to be negative at all, but was this for a toy/hobby or for a commercial project?
I find that LLMs do very well on small greenfield toy/hobby projects but basically fall over when brought into commercial projects that often have bespoke requirements and standards (i.e. has to cross compile on qcc, comply with autosar, in-house build system, tons of legacy code laying around maybe maybe not used).
So no shade - I'm just really curious what kind of project you were able get such good results writing ESP32 FW and kernel drivers for :)
And the chance of that working depends on the weather, the phase of the moon and the arrangement of bird bones in a druidic augury.
It's a non-deterministic system producing statistically relevant results with no failure modes.
I had Cursor one-shot issues in internal libraries with zero rules.
And then suggest I use StringBuilder (Java) in a 100% Elixir project with carefully curated cursor rules as suggested by the latest shamanic ritual trends.
This is my experience too. Also, their propensity to jump into code without necessarily understanding the requirement is annoying to say the least. As the project complexity grows, you find yourself writing longer and longer instructions just to guardrail.
Another rather interesting thing is that they tend to gravitate towards sweep the errors under the rug kind of coding which is disastrous. e.g. "return X if we don't find the value so downstream doesn't crash". These are the kind of errors no human, even a beginner on their first day learning to code, wouldn't make and are extremely annoying to debug.
Tl;dr: LLMs' tendency to treat every single thing you give it as a demo homework project
> Another rather interesting thing is that they tend to gravitate towards sweep the errors under the rug kind of coding which is disastrous. e.g. "return X if we don't find the value so downstream doesn't crash".
Yes, these are painful and basically the main reason I moved from Claude to Gemini - it felt insane to be begging the AI - "No, you actually have to fix the bug, in the code you wrote, you cannot just return some random value when it fails, it actually has to work".
Claude in particular abuses the word 'Comprehensive' a lot. You express that you're unhappy with its approach, it will likely comeback with "Comprehensive plan to ..." and then write like 3 bullet points under it, that is of course after profusely apologizing. On a sidenote, I wish LLMs never apologized and instead just said I don't know how to do this.
In my experience in a Java code base, it didn't do any of this, and did a good job with exceptions.
And I have to disagree that these aren't errors that beginners or even intermediates make. Who hasn't swallowed an error because "that case totally, most definitely won't ever happen, and I need to get this done"?
Running LLM code with kernel privileges seems like courting disaster. I wouldn't dare do that unless I had a rock-solid grasp of the subsystem, and at that point, why not just write the code myself? LLM coding is on-average 20% slower.
Ironically, AI mirrors human developers in that it's far more effective when working in a well written, well documented code base. It will infer function functionality from function names. If those are shitty, short, or full of weird abbreviations, it'll have a hard time.
Maybe it's a skill issue, in the sense of having a decent code base.
The web project is Nuxt v4, which was just released, so Claude keeps wanting to use v3 semantics, and you have to keep repeating the known differences, even if you use CLAUDE.md. (They moved client files under a app/ subdirectory.)
All of these are greenfield prototypes. I haven't used it in large systems, and I can totally see how that would be context overload for it. This is why I was asking GP about the circumstances.
I work in FAANG, have been for over a decade. These tools are creating a huge amount of value, starting with Copilot but now with tools like Claude Code and Cursor. The people doing so don’t have a lot of time to comment about it on HN since we’re busy building things.
I feel this, honestly. I get so much more work done (currently: building & shipping games, maintaining websites, managing APIs, releasing several mobile apps, and developing native desktop applications) managing 5x claude instances that the majority of my time is sucked up by just prompting whichever agent is done on their next task(s), and there's a real feeling of lost productivity if any agent is left idle for too long.
The only time to browse HN left is when all the agents are comfortably spinning away.
I also work for a FAANG company and so far most employees agree that while LLMs are good for writing docs, presentations or emails, they still lack a lot when it comes to writing a maintainable code (especially in Java, they supposedly do better in Go, don’t know why, not my opinion). Even simple refactorings need to be carefully checked. I really like them for doing stuff that I know nothing about though (eg write a script using a certain tool, tell me how to rewrite my code to use certain library etc) or for reviewing changes
I don't see how FAANG is relevant here. But the 'FAANG' I used to work at had an emergent problem of people throwing a lot of half baked 'AI-powered' code over the wall and let reviewers deal with it (due to incentives, not that they were malicious). In orgs like infra where everything needs to be reviewed carefully, this is purely a burden
I work in a FAANG equivalent for a decade, mostly in C++/embedded systems. I work on commercial products used by millions of people. I use the AI also.
When others are finding gold in rivers similar to mine, and I'm mostly finding dirt, I'm curious to ask and see how similar the rivers really are, or if the river they are panning in is actually somewhere I do find gold, but not a river I get to pan in often.
If the rivers really are similar, maybe I need to work on my panning game :)
Wh is an abomination that has come about because professionals think consumer brains would expose if they ever saw the unit watt-seconds (J). No consumer had any preconceived notion of either Wh or J, so had we used J from the start, it wouldn't have been a problem...
(Yes, same with Ah vs C, though the battery pros also shot themselves in the foot by starting to use C (electrical charge) to mean "the capacity of this battery" when talking about charge rate, a.k.a. current.)
reply