wfn

...sure, that's true :) but you get the point. p.s. and the software design pattern applies in general, imho.

Think of it like an assert.

Sometimes you do want some flow to terminate if a schema / data contract is breached, and not have this broken data contract propagate elsewhere / outwards.

And/or, it is a perfectly valid pattern to indeed add try..catch, and contain (hence "localize") the issue there and then. If there is a way to handle this breach - you will need some kind of if check anyway. Catching by matching against the particular KeyError exception is in fact robust - and if you forgot to add an intended catch, then the exception will propagate upstack, yes - which is what you want - and this way you do not need to worry about forgetting an "if None" check.

This sort of approach makes it structurally impossible to "forget" - if exception is not caught, it will abort the cannot-be-null breach continuing with program flow, possibly (e.g.) ending up persisted in some place it shouldn't be, causing problems later.

Well, their developers were struggling understanding how to compute HMAC (we had to also write some pseudocode to help them compute urlsafe-base64, very complex challenging sophisticated stuff, yes) (this was a few years ago) when integrating into previous employer's API (was helping with their integration into us).

So I am zero percent surprised this happened, literally 0% surprise factor.

Hey, I forgot to reply, but still wanted to quickly respond and to say - thank you for the detailed response, I concede your points are valid, and your perspective seems to be more accurate (with regards to incorporating nuance + reality fit) :)

> Javascript also uses basic stack unwinding. Would you also say Javascript doesn't have exceptions or exception handlers?

No, I wouldn't, so re: that - fair point;

For me, Go's error+panic lack of propagation + lack of exception type hierarchy are what stick out and seem vastly different to "typical"; and this does impact development, especially propagation mechanism / lack thereof. But I also haven't written lots of Go code, and could be possibly lacking experience, and am just looking from "typical" language lens (Java (not JS), Python, from my PoV)?

> Isn't every single piece of content here a potential RCE/injection/exfiltration vector for all participating/observing agents?

100%, I wonder when we get LLM botnets (optional: orchestrated by an agent), if not already.

The way I see prompt injection is, currently there is no architecture for a fundamental separation of control vs data channels (others also think along similar lines of course, not an original idea at all). There are (sometimes) attempts at workarounds (sometimes). This apart from other insane security holes.

edit p.s. Simon has been talking about this for multiple years now, I should mention this in fairness (incl. in linked post)

This is a funny chain.. of exchanges, cheers to you both :)

At the risk of ruining 'sowbug having their fun, I'm not sure how Julian Jaynes theory of origins of consciousness aligns against your assumption / reduction that the point (implied by the wiki article link) was supposed to be "I am only my brain." I think they were being polemical, the linked theory is pretty fascinating actually (regardless of whether it's true; and it is very much speculative), and suggests a slow becoming-conscious process which necessitates a society with language.

Unless you knew that and you're saying that's still a reductionist take?.. because otherwise the funny moment (I'd dare guessing shared by 'sowbug) is that your assumption of fixed chain of specific point-counter-point-... looks very Markovian in nature :)

(I'm saying this in jest, I hope that's coming through...)

Yes. I have (as part of Claude output) a

- `FEATURE_IMPL_PLAN.md` (master plan; or `NEXT_FEATURES_LIST.md` or somesuch)

- `FEATURE_IMPL_PROMPT_TEMPLATE.md` (where I replace placeholders with next feature to be implemented; prompt includes various points about being thorough, making sure to validate and loop until full test pipeline works, to git version tag upon user confirmation, etc.)

- `feature-impl-plans/` directory where Claude is to keep per-feature detailed docs (with current status) up to date - this is esp. useful for complex features which may require multiple sessions for example

- also instruct it to keep main impl plan doc up to date, but that one is limited in size/depth/scope on purpose, not to overwhelm it

- CLAUDE.md has summary of important code references (paths / modules / classes etc.) for lookup, but is also restricted in size. But it includes full (up-to-date) inventory of all doc files, for itself

- If I end up expanding CLAUDE.md for some reason or temporarily (before I offload some content to separate docs), I will say as part of prompt template to "make sure to read in the whole @CLAUDE.md without skipping any content"

> but then the shell commands were actually running llama.cpp, a mistake probably no human would make.

But in the docs I see things like

    cp llama.cpp/build/bin/llama-* llama.cpp

Wouldn't this explain that? (Didn't look too deep)