I think this language is fascinating, but immediately reached a similar conclusion: it might trip up an LLM consuming the text directly but once an interpreter/compiler/decompiler has been written for the language it's trivial for an agent to consume these programs and produce them.
Now on the other hand, as a class of techniques - "anti-LLM languages" - it might be a useful method of emitting code that some agents with the correct tools can consume and others cannot, by design. Evolving such techniques with differing specifications might make for an interesting line of investigation.
Indeed, and an interpreter has been written[1]. As part of the benchmarks, in some cases the models receive a binary of the interpreter and indeed some of them attempt to reverse engineer it. So that already helps the models a bunch.
I do think this will also eventually make it into the training data, but that will in itself be interesting to see. It's also possible for KillSwitch to evolve and gain/remove features over time to constantly evade the LLMs.
also I believe it helps you track save games. I have multiple Linux boxes I play GOG games on using Heroic launcher and save game tracking is a big issue (maybe there's a way to do this with Heroic, idk). But I think Galaxy would help here.
I haven’t done any objective tests but I frequently run Windows 11 on ARM via Parallels on macOS and - it’s kinda insane (subjectively) how fast it is. Emulated x86 code is pretty fast there as well - I can easily get a solid 60 FPS on some x86 steam games as well.
Isn't the point of electron to be cross platform? (I get a company may have not released an ARM build or wherever, but seems an odd choice for emulated performance comparison)
I don’t have a good list of which games I validated in parallels and which I didn’t (since I’ve stopped gaming for the last 6 months or so).
And I do heavily play boomer shooters so it’s likely I was impressed by performance of less demanding games.
Doom Eternal is one AAA game I definitely would want to play in Parallels but can’t because the Vulkan version is not new enough. I’m confident though that Microsoft could bring these APIs up-to-date on an “ARM PC” though, if it has capable 3D hardware.
This appears to be an architectural vulnerability where a speculative execution side channel similar to Spectre can be utilized within Safari or any other browser. The specifics of which environment is exploitable comes down to the specifics of the JavaScript-based gadget they use to trigger/measure this side channel. It may be in the linked paper which I haven’t read yet.
From a cursory review of the FAQs on the page it appears one mitigation might be to only keep one browser tab open at a time? They appear to be using timers and a cache eviction gadget to infer the state of other browser tabs/processes so it’s unclear what they can recover if you are not concurrently having a session to a particular site outside the gadget execution context. ???
They use window.open on a mouseover event listener to open another page. Even if you close it, they still are able to read from it as that memory isn't immediately zeroed or returned to the OS.
Besides windows.open I'd wonder if iframes could also be vulnerable if they launch in the same process.
Chrome and Firefox both support Out-Of-Process Iframes as part of their security setup; though I'm not sure if Firefox has it enabled by default yet. Firefox even drew some lovely pictures about it here: https://hacks.mozilla.org/2021/05/introducing-firefox-new-si...
Now on the other hand, as a class of techniques - "anti-LLM languages" - it might be a useful method of emitting code that some agents with the correct tools can consume and others cannot, by design. Evolving such techniques with differing specifications might make for an interesting line of investigation.
reply