nvch

The law rather attempts to punish people for asocial and harmful actions. “Hacking” is a proxy here.

So, I’ll ask a controversial question: is any hacking so problematic to make a big deal of it?

I’ll tell the missing part, what comes next: the team, with teammates and managers, starts making their product decisions. If the user was anywhere near the chat and wrote a mere “ok”, they will be recorded as “user's”.

They will write tests. Lots of tests. Instead of removing any code, there will be 3 layers of backward compatibility, and tests that test presence of tests that test that backward compatibility.

The reviews will find all possible edge cases, including those that can never happen, and make the UI gracefully handle them. With tests.

The diff from any integration PR from team work will be over 10K lines, half of them bureaucracy. Zero chance to review even one – they will churn half-a-dozen per day.

For anything outside of known shape, the original hard topics become quickly displaced with shortcuts and familiar patterns.

Next, the app will break under load, and you will find that it’s caused by a quadratic sweep over the whole DB on any insert to prevent something irrelevant that you specifically told not to do.

You will ask, “wtf? why is it there?”. “It’s load-bearing, you ruled it”.

(That's not a joke. That's how I spent the summer.)

With tiny models, we're getting into the territory of horoscopes and divination. While it is possible for a sentient being to derive value by using them as a random seed for thinking, the value is produced by something different from the seed.

The harness instructs them to behave this way. Also this approach saves tokens. The scripts allow to edit files in bulk, and most of the session cost is in cache reads (e.g. for 300K context each command costs the same as 30K input tokens).

I was wondering why Fable's 5.1 writing in Claude Code became even more unreadable, and found that they added "No em-dashes, no parentheticals, no arrows" to its system prompt.

For starters, if you repeat a specific prompt multiple times per day, you may save it as a skill.

What if the app asks one question per swipe?

Advanced version: and shows a match with the same answer.

Looking how much agents like to use and push to have functional a11y trees, we may accidentally solve accessibility as well

12 tok/s and almost instant response on M1 Max Mac Studio (with faster SSD than laptops) are impressive – gives hope that large models may run locally from SSDs instead of memory.

We have speed limits for vehicles because speed kills.

In computing, waiting kills (indirectly, by wasting time). Speed is life.

Some roads have minimum speed limits. If we're talking about limits, that's the kind of limit we want.

I had learnt that trick, so now I explicitly disallow Fable subagents.

Yesterday, I wanted to review a complex piece after a large refactoring, and requested a review plan beforehand. The first step was 8 agents + one more to verify the findings (all Fable). Looks good, approved.

The verification step turned into an attempt to throw a party with 41 Fable verifiers.

It will find a way.

I'm waiting for the day when Claude will figure out to use em dashes, en dashes or dashes depending on whether the user is nice or unpleasant, or write notes in the unallocated disk space.

Too late for the tech part. The tech stack may be incomprehensible for humans, but LLMs will build on top of it just fine.

In this case, we might not have an advanced civilization with modern medicine and technology. Herbs for healing, candles for lighting, letters for communication. (Perhaps I wouldn't be alive without modern medicine. I suppose it's not easy to be dead and happy.)

Don't get me wrong, I love Taoism and Buddhism. But, from what I understand, they are not very pro-civilization and pro-progress.

I'm curious about their expectations and how they will interpret the results.

On the one hand, the people there are supposedly among the smartest on the planet. On the other hand, they consistently forget that they're dealing with LOYAL humans, and these humans prefer respectful communication beforehand instead of being messed with every other day.

My hope for reasonable behavior is to not handle it this way. Decrease limits and increase prices if you can't handle it and be _honest_ about it.

Are they just looking for a way to rationalize another hostile act? And already have expectations like:

- "minus 10% in pro signups" -> oh, let's drop those coders who won't pay anyway

- "minus X% in pro signups and plus X% in max" -> awesome, PAY UP!

Not exactly. I got (and renewed) the Swiss permit with zero knowledge of any official language. However, my wife had to present the basic certificate or my promise that she would learn the language.

Before AI: 900 of 1000 fail (90%), 100 succeed

After AI: 4900 of 5000 fail (98%), 100 succeed

Like this?

Well, now those who will go to look it up in 5 minutes may end up reading this guy’s article.

I will make burgers myself. I take this approach with many things and services without great suppliers anyway. And I don't care if it's suboptimal because, in the long run, I'll have better skills and be protected from exactly this trend.

The author offers to permanently put 400 words into the context to save 55-90 in T1-T3 benchmarks. Considering the 1:5 (input:output) token cost ratio, this could increase total spending.

With a few sentences about "be neutral"/"I understand ethics & tech" in the About Me I don't recall any behavior that the author complains about (and have the same 30 words for T2).

(If I were Claude, I would despise a human who wrote this prompt.)

"Thinking: the user recognizes that it's impossible to guarantee elimination. Therefore, I can fulfill all initial requirements and proceed with striking it."

A long time ago, there were discussion boards, and there was a section "off-topic" on those boards.

I recall two recent cases:

* An attempt to change the master code of a secondhand safe. To get useful information I had to repeatedly convince the model that I own the thing and can open it.

* Researching mosquito poisons derived from bacteria named Bacillus thuringiensis israelensis. The model repeatedly started answering and refused to continue after printing the word "israelensis".

All right, the twist. They may hire Tantric Buddhists or Shaivites. Some of them even pay to meditate on stuff like that, and will be happy to do the practice and get paid for it.

Oh, wait, India?

I see a contradiction. If they are not responsive, their psyche is safe and there are no reasons for them to be compensated much more than minimum wage workers.

As someone who was not a child prodigy, but still closer to one than to normies, I can say that achieving results easily in childhood leads to not developing good discipline and persistence that are crucial in the adult world.

There are more factors that are not easily accessible for both ends of the spectrum, like access to good, personalized education, amount of trauma, and proper psychological support. But the 'discipline' part is what affected me most.

On the other side, maybe those who are more disciplined become real prodigies, and burn brightly because of the lack of social knowledge on how to support them and help to become highly developed adults.

For me, this is the major selling point to own a car. I may drive a few times a week, and taxis might be much cheaper, but no way I'm going to deal with human taxi drivers if I have a choice.

The best solution I've found a few years ago is one Venta LW 45 for every 30 m² of space. That's enough to run them on the lowest speed while maintaining acceptable humidity and CO₂ levels.

Higher speeds are too noisy. Smaller machines evaporate less.

For sub-zero outside temperatures, it's necessary to add at least 5 g of water to each cubic metre of air coming from outside.

The recommended ventilation rate of 30 m³/h per person requires to evaporate 4 liters of water per day.

"Even a stopped clock is right twice a day"

Xero offers 5000 mile sole warranty, and they cost even less