bruce343434

Won't this harm SEO? What about agentic software suites where authorized users should be able to drop an app passkey into grokbot or such?

Took the words out of my mouth. The trajectory indicator isn't predictive either, making it pointless. A single playtest would have made this obvious and maybe even a single prompt would have solved it.

So really there are 2 orthogonal axes:

- A: can I change the value

- B: can something else change the value (can I depend on a predictable stable value)

Because the axes are orthogonal, hierarchical based subtyping (inheritance) breaks, but type classes (interfaces), ad hoc polymorphism, would work.

In C, const answers A

In rust, due to pointer aliasing restrictions (either one mut pointer xor any amount of read only pointers), (lack of) mut answers both A and B

Alternatively build a searchable inventory app with claude

I feel like this article does a depth first search on what swiss tables are, jumping head first into the tiniest implementation details, but I'm missing the breadth first search. What is the top level `struct` of a swiss table? An array of groups? Why not simplify all of it into linear open addressing, with a stride of 8 for simd? Why the triangular jumps? What problems does this design solve?

Tis not shared

Perhaps they just used the exact same random seed everywhere?

> last month I spent almost 10k USD on tokens. It sounds so insane

It is. That kind of money would change my life and this guy spends it on prompts that "really force him to think".

I use LLMs. So far, 20 bucks per month has me covered. I hit the limit sometimes. I just take a walk. Forces me to think.

C++ compilers do this too, thats why so many to-be-linked symbols start with "Z"

addressing any of the points would require locking the AI down and making it less general and less "agentic". Your concerns make sense if you look at the AI as an information retrieval engine.

   - why is single URL crawl with 20+ redirects not flagged as problematic and/or aborted?

There could be legitimate use cases for interacting with a website like this that could serve the user.

   - why is a query about a coffee place based on its public URL even seeded with the users' context and confidential information? 

Because it provides context in how the agent interacts with the site (in this case to detrimental effect)

   - why dont they just look up the coffee place on a trusted source like google maps and continue from there?

The ai was explicitly instructed to check the given url

   - why is the basic "social" engineering style attack working?

because ai can not separate prompt from information, they share the same input channel. state of the art ai has some amount of "common sense" as to when it is being prompt injected or engineered, but this isn't exhaustive

   - why is the cloudflare impersonation not challenged if the website is clearly not from cloudflare and there are zero references from cloudflare to this website in the training corpus?

because the ai didn't think to check if the website is truly behind some sort of cloudflare product or not

Prompt injection (or llm social engineering" is fundamentally unsolvable, though with training its effectiveness can be reduced

the optimal crime rate is non zero and the same goes for traffic death rate, because to bring them to zero would imply a dystopia where personal freedom is seriously limited

    :set {:job "Engineer"}
    :where |(= ($ :job) "Developer")

What is going on there in that where syntax?

Is there a nautical map equivalent of osm or organic maps? One that emphasizes waterways by drawing them thicker when zoomed out like regular maps draw roads thicker? Plan routes over the water? Even google maps lacks a nautical layer.