No it’s more like - because AI can’t know every endpoint and what it does, so MCP allows for injecting the endpoints and a description into context so the ai can choose the right tool without additions steps

Agents can't write bash correctly so... I wonder about your claim

They cannot? We have a client from 25 years ago and all the devops for them are massive bash scripts; 1000s of them. Not written by us (well some parts as maintenance) and really the only 'thing' that almost always flawlessly fixes and updates them is claude code. Even with insane bash in bash in bash escaping and all kinds of not well known constructs. It works. So we habe no incentive to refactor or rewrite. We did 5 years ago and postponed as we first had to rewrite their enormous and equally badly written ERP for their factory. Maybe that would not have happened either now...

It can. Not sure what AI you're using, but Gemini outputs great bash. Of course you need to test it.

You do have to make sure to tell it what platform you're using, because things like MacOS have different CLIs than Linux.

In Japanese websites this is pretty much the norm. Govt, bank, marketplace, you name it. fills the address until the block, where you'll need to fill the rest of the numbers until your house address / room number

The whole point about having an open platform from boot is you don't have to trust it. You run your own code from first power on.

Is it possible that it's backdoored, have a secret opcode / management engine? Probably, but that goes to everyone, as it's not practical to analyze what's in the chip (unless you're decapping them and all)

I don't know what secure environments you're talking about, if it's an airgapped system then you should be secure even when what's inside 'tries to get out'.

Korean and western made stuff guarantee to have such thing. CNC devices in Russia stopped working. Even NVIDIA gpu has back door according to China and NVIDIA had to settle this matter behind the scene with China government. At this point, your phone is 100% backdoorable by western government. The only thing protect you is you are non-threat and too small to be bother with.

>Even NVIDIA gpu has back door according to China and NVIDIA

They never said or claimed that. They rised concerns and asked about _possible_ backdoors the same way the west does about china e.g. Huawei.

Is there documentation that GrapheneOS Pixels or iPhones are backdoored by governments to the extent that any person can be targeted?

No? Okay.

I think if Blender can do UI change, GIMP should too.

I'm doubting the 29-ish percent of people submitting 'walk' are actually human.

Is it not obvious that you need a car to wash?

Are they using LLM to answer?

A lot of people will literally answer incorrectly for a laugh as well on surveys.

it is surprising, but give this question to some random people on the street without context and you would be surprised

In reverse engineering we often use Graph View to see execution flow as well. Glad to see it being used elsewhere

Do you automate that? If so what tooling do you use?

IDA does it by default, for example.

I’m not trying to make any claims about consciousness. For us, the practical question is: does the interaction feel supportive and useful, while staying transparent that it’s a model. The rest is philosophy, and I’m happy to read more perspectives.

Give it access to a terminal and see what it does, unprompted. Does it explore? Does it develop interests? Does it change when exposed to new information?

We’re not giving it unconstrained tool access. In-product, actions are either not available or gated behind explicit user intent and strict allowlists. The interesting part for us is the real-time conversational loop and memory personalization, not autonomous exploration.

>Does it change when exposed to new information?

By this metric most humans are not conscious.

Not putting strings on GPU looks very much like how some system approaches semihosting

I'm working on a game for pocketstation (essentially Dreamcast VMU, but Playstation). It has the same cpu architecture as GBA but there are some unfortunate circumstances that requires me to modify LLVM for rust to use. Forces me to learn I guess

Looks really cool but I'm wondering if the whole Docker setup was necessary just to get onnx?

Thank you! Yes, I use Docker to get ONNX DLLs and cross-compile the main DLL using the MSVC toolchain (which is required for game engines)