Hacker Timesnew | past | comments | ask | show | jobs | submit | est's commentslogin

> just plain HTML and some basic CSS

Or even better. XML + XLST.

True separation of representation and data.

Is thousands of nested <div> really a good idea?


MCP is based on a lie: Machines are good at read/generate machine-parsable procotols.

Turns LLMs are shit with JSON. Especially those JSON str embeded inside another JSON key-value pairs.

Why do smart ppl design a schema like escape JSON into str embeded into another?

It's based on another lie: AIs favor static typed languages.


> I'm going to feed all of my business's data to it

Your business data is probably worthless, even considered harmful for the pretrain corpus.

Your interactions and decision making process are most valuable parts of the whole business.


I assure you my business's data is not remotely worthless which is why there are pretty strict laws and regulations about what we can do with it

>Your business data is probably worthless

please tell me you are not in charge of the data of any business I'm a client of


Could be! Let's check. I just need your name and address, your SSN, a list of businesses you are a client of, and a DNA sample.

to clarify, probably worthless to AI vendors, but might be useful for third-parties.

Third parties that can be clients of the AI vendor...

If it's worthless to AI vendors, they won't include it in the training corpus, so third parties won't have access to it.

But it isn't worthless because the user is paying for that, and third parties are paying for that as well. Unless the input output is completely different, which it's not because you are human, and I bet you have a profession which other humans have, and many other qualities which you share with other humans.

In any case, relying on the chance that the LLM inference won't train on your data because of it's presumably low value is as good a strategy as crossing your fingers or venerating the god of rain. You should be relying on contractual clauses at least when including professional and client data.


They're alluding to something more like espionage of just selling the interesting stuff you put in the text box.

Wow I thought this was quite obvious, apparently not, so I'll explain.

Llm provider sells usage of their model. You use it to write code. Other clients use it to write code as well. If the llm provider trains with user data, then the usage benefits other users. If you pay the company to generate code,then by definition it is useful, and highly likely that other customers care about it.

Replace writing code with anything, a lawyer, a psychologist, a confessional. The IO is inherently useful to users of the same category.

That is to say nothing of adversarial use, that is, being useful because a counterparty might find it useful, so an attacker might find common code patterns, a lawyer might see what the opposition might be advised, a boy might see what a girl asks or gets advised, etc..

If this sounds too complex to you, just think of training on data as exfiltration with added steps, because that's what it is


Oh well this is a bad argument. I made a mistake by assuming you made a good argument instead.

The worry is direct exfiltration, not training

There are basically two kinds of people in the world, ones that create stuff, and ones that destroys stuff.

Defense is a toally different game, and requires a complete new mindset than creativity. Security is something that you miss one then you lose all.

AIs are good at choosing a good candidate based on a reward model, but it sucks hard at enumerating mundane attack surfaces and make combinations to exploit through.


Good engineering is good engineering. Belief that someone else uniquely possesses the skill to engineer some critical part of a system you built is, for me, just abdicating responsibility. It's a learned helplessness.

Someone else blindly operating an llm on a corpus you created with an llm is comical.


Are you the best choice to engineer everything your system does? There is no one in your company that might do a better job than you for a specific part of the system?

There is nothing wrong with asking for help or bouncing ideas of people with stronger skills.

I still have the responsibility to code XYZ well. But I don’t have to do it in a clean room.


sounds like a Monty Python sketch ...

> The founding tenet of AI, “saving us” from all sorts of difficult things: climate, disease, poverty, conflict is falling, fast

No those are just marketing slogans. The founding tenet of AI is to best match next token according to a reward model.


I am almost certain this layout is generated by AI, because I vibe coded the exact same newspaper-like style weeks ago.

Yes ! Building a news website with Claude design give me the same design, background color, text size …

Somehow, Claude seems to have developed a default nostalgic newspaper aesthetic despite being so young.

me too… this felt awkward: https://duobook.co/explore-stories

Your DNS config 5-7 rows are the culprit.

Don't point a wildcard domain to Github. It's a wildcard and dangerous.


Yep! Fixed it already!

clickbait.

Nope, HN changed the title.

https://imgur.com/a/UgJqWEh


Why can't you use a web page instead ?


Came here to ask the same question. This could be a static HTML web page with a table.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: