maerch

Finally, someone is fixing a problem that’s tailored to me. For me, FFF obviously stands for “Fat-Fingered Finder.”

It’s already happening. This came up in a webinar attended by someone from our sales team:

"A typo or two also helps to show it’s not AI (one of the biggest issues right now)."

Huh? No, that's been established since Karpathy coined the term; you don't review the code, only use the agent and don't care about how it was done, just about the results.

However, nowadays it is used as a synonym for everything that is somehow generated by an LLM. Regardless of whether it is a spec-driven, carefully reviewed and iterative piece of software or some yolo-style one-prompter with no idea how it was done.

In that case, removing „perhaps“ would have helped a lot. It is not about maybe being hired, but about maybe being interviewed.

The closest I come to working with part-time, minimum-wage workers is working with student employees. Even then, they earn more and usually work more than five hours a week.

Most of the time, I end up putting in more work than I get out of it. Onboarding, reviewing, and mentoring all take significant time.

Even with the best students we had, paying around 400 euros a month, I would not say that I saved five hours a week.

And even when they reach the point of being truly productive, they are usually already finished with their studies. If we then hire them full-time, they cost significantly more.

Factorio 2.0 seemed to pull it off. I think that as long as users don’t feel misled by a DLC that only adds a few skins, they generally appreciate larger updates to a game.

Exactly this. I thought about getting a T7, but the price is just ridiculous. And it’s not even like you’re paying for quality, there are so many complaints about both minor and major issues.

People being prevented from doing their job because of code formatting? In my nearly 20 years of development, that statement was indeed true, but only before the age of formatters. Back then, endless hours were spent on recurring discussions and nitpicky stylistic reviews. The supposed gains were minimal, maybe saving a few seconds parsing a line faster. And if something is really hard to read, adding a prettier-ignore comment above the lines works wonders. The number of times I’ve actually needed it since? Just a handful.

Code style is a Pareto-optimal problem space: what one person finds readable may look like complete chaos to someone else. There’s no objective truth, and that’s why I believe that in a project involving multiple people, spending time on this is largely a waste of time.

My experience is it often generates code that is subtlety incorrect. And I'll waste time debugging it.

[…]

Or it'll help me debug my code and point out things I've missed.

I made both of these statements myself and later wondered why I had never connected them.

In the beginning, I used AI a lot to help me debug my own code, mostly through ChatGPT.

Later, I started using an AI agent that generated code, but it often didn’t work perfectly. I spent a lot of time trying to steer the AI to improve the output. Sometimes it worked, but other times it was just frustrating and felt like a waste of time.

At some point, I combined these two approaches: I cleared the context, told the AI that there was some code that wasn’t working as expected, and asked it to perform a root cause analysis, starting by trying to reproduce the issue. I was very surprised by how much better the agent became at finding and eventually fixing problems when I framed the task from this different perspective.

Now, I have commands in Claude Code for this and other due diligence tasks, and it’s been a long time since I last felt like I was wasting my time.

I still have a bad taste in my mouth after all those GPT-5 hype articles that claimed the model was just one step away from AGI.

The agent follows references like a human analyst would. No chunks. No embeddings. No reranking. Just intelligent navigation.

I think this sums it up well. Working with LLMs is already confusing and unpredictable. Adding a convoluted RAG pipeline (unless it is truly necessary because of context size limitations) only makes things worse compared to simply emulating what we would normally do.

Apart from the “—“, what else gives it away? Just asking from a non-native perspective.

I’m really trying to understand your point, so please bear with me.

As I see it, this prompt is essentially an "executable script". In your view, should all prompts be analyzed and possibly blocked based on heuristics that flag malicious intent? Should we also prevent the LLM from simply writing an equivalent script in a programming language, even if it is never executed? How is this different from requiring all programming languages (at least from big companies with big engineering teams) to include such security checks before code is compiled?

I am not sure how good your test really is. Or at least how high your bar is.

Paul Erdös was told about this problem with multiple explanations and just rejected the answer. He could not believe it until they ran a simulation.

A repeated trend is that Claude Code only gets 70-80% of the way, which is fine and something I wish was emphasized more by people pushing agents.

Recently, I realized that this applies not only to the first 70–80% of a project but sometimes also to the final 70-80%.

I couldn’t make progress with Claude on a major refactoring from scratch, so I started implementing it myself. Once I had shaped the idea clearly enough but in a very early state, I handed it back to Claude to finish and it worked flawlessly, down to the last CHANGELOG entry, without any further input from me.

I saw this as a form of extensive guardrails or prompting-by-example.

It’s just the ChatGPT translation, and it’s a literal one. That said, I’ve never heard that phrase in German either.

Meanwhile, in Germany, you can get raw pork with raw onions on a bread roll at just about every other bakery.

https://en.m.wikipedia.org/wiki/Mett

When I searched for the safe temperature for pork (in German), I found this as the first link (Kagi search engine)

Ideally, pork should taste pink, with a core temperature between 58 and 59 degrees Celsius. You can determine the exact temperature using a meat thermometer. Is that not a health concern? Not anymore, as nutrition expert Dagmar von Cramm confirms: “Trichinae inspection in Germany is so strict — even for wild boars — that there is no longer any danger.”

https://www.stern.de/genuss/essen/warum-sie-schweinefleisch-...

Stern is a major magazine in Germany.

Thanks for sharing! I will try this out. Sounds like something my kids would love.

Like many others in threads like this, I initially felt repelled. It’s restrictive, it’s super expensive, and I dislike some (though not all) of the design choices.

But then I remind myself: it’s not a product made for me. I don’t have to like it. Clearly, the target group loves it. My kids have adored it for years. Even now, with my oldest having access to Spotify Kids, she still prefers her Toniebox in the evening before bed. The figurines aren’t just a medium, they’re toys in their own right. They’re shared, traded, and loved. And they really enjoy squeezing those silly ears.

Many other families in my circle tell the same story. Some tried similar products that launched soon after the original, often ones using cards (though not Yoto). But after a few weeks, their kids lost interest and asked for a Toniebox instead. (It reminds me of when my parents bought me a Sega Master System, even though all I wanted was a Super Nintendo.)

That was my first thought. This can go downhill pretty quickly. Nobody suspects that you expose your account with a link to a mention.

Sometimes I’m astounded. Just when I think I’ve heard of most tools in a certain AI category, I come across a link here to a GitHub repo with over 4K stars.

Has anyone used this one and can share their experience with it compared to other terminal agents?

After reading Sarah Wynn-Williams’ book (assuming that at least half of it is true), it seems that Zuck doesn’t hold any political beliefs at all. Just opportunism, nothing more.

Recently, I found my old ICQ chat history from back in the day. It was a joy to go through, sometimes a little cringeworthy, but overall I really enjoyed it. It felt like a time machine taking me 25 years back, helping me reconnect everything with the memories I have.

That hasn’t been my experience. A few tech-savvy people and those close to them may use alternatives, but even then, it’s usually just for groups where someone refuses to use WhatsApp. For everything else, they still rely on WhatsApp.

On top of that, nearly all groups related to kindergarten, school, or various clubs use WhatsApp, and there’s practically no way to convince them to switch. If my wife weren’t in those groups, I’d have no idea what’s going on.

I’ve been using Signal as my main chat app on iOS and desktop for a long time. Yes, this happens to me every other month too. It’s annoying, but I can live with it.

It’s about taking small steps to get the flywheel turning, not about “just doing it.” You need small wins to build up motivation for the bigger, more complicated tasks.

If you want to lose weight but don’t feel motivated, it might be because you associate getting started with a strict workout routine and highly restrictive dieting. But taking smaller steps in the right direction can spark motivation. From my own experience, I know I naturally start eating healthier as soon as I get back into running.

Issue #113 - “Please continue being awesome.” That emoji-laced drive-by encouragement (August 2018) still pops into my head whenever motivation dips.

This warms my heart. While the internet is infamous for its negativity and how it makes people miserable, even small positive moments like this can make a lasting difference and remain memorable years later.

Whenever I see arguments about past scapegoats, something about them doesn’t sit right with me.

Some things today are simply more addictive than others—and often deliberately designed that way by large corporations. More importantly, they’re everywhere and carry intense peer pressure. I never experienced that with the things people used to worry about. I listened to a lot of so-called “devil’s music” and played plenty of first-person shooters, and it was never quite the same.

Jobs where they make you clock in X hours but actually work X+Y. This of course can be reported, but not many people do (lack of inspectors, fear of losing the job, slowness of the justice system...)

I would add that there are also cases where it’s the other way around—where the employer actually insists that employees work only a set number of hours (X), but the staff voluntarily puts in additional time (Y) without tracking it.

In fact, I’ve seen this happen more often in European companies than situations where employers pressure staff to work longer hours.

Exactly my thoughts. It seems there’s a lot of all-or-nothing thinking around this. What makes it valuable to me is its ability to simplify and automate mundane, repetitive tasks. Things like implementing small functions and interfaces I’ve designed, or even building something like a linting tool to keep docs and tests up to date. All of this has saved me countless hours and a good deal of sanity.