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.

When I was not 17 at the times of GPT2, I decided to not bother with learning how to build LLMs because it’s too expensive for an individual. This escalated quickly.

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.