> It is a new programming language that blocks AI mistakes via proof checking - the same technique big AI labs used to >solve open math problems, like Navier-Stokes.
Ideally something like IPNS to have a mutable ref based on (repo, pubkey, branch) to resolve a commit hash, a DHT for who has what commit hashes, and then just p2p transfers. You could still have a github or gitlab for issues and CI, but code (and maybe issues) could all be p2p like git is already designed for. Your forge could also act as a peer for code cloning, of course.
The complexity is in locating what is already a distributed database item (git is fundamentally already designed that way), just using a protocol meant for that. Basically just support `git clone` with e.g. IPFS URIs.
I think the clear reason is even with their unreliability, the cost of migrating off of GitHub for _most_ places is not worth it, and so companies don't / won't (yet)
This bugs me so much. Management decides what is reasonable cost of service and the employees have to deal with all bullshit coming from that product. And you can't really escape it. Maybe the real moat was enterprise deals we made along the way.
The company I work for just did a huge and expensive study that was showing LLMs are much better at exploiting than securing code. So ya, that's kind of problematic.
Last stage is moving everyone to their cloud platforms, they deploy everything for you, you don't even get to see the code, just the deployed end product.
Because letting you look at the code would be too dangerous, you could reverse engineer an exploit to another product! Or distill their internet-distilled model!
But don't worry, at least it will be very convenient.
The name "Engram" (n-gram) says it all - this is just another type of statistical word association, not a factual knowledge store.
While DeepSeek describe this as "knowledge lookup", what Engram is really trying to do is separate dynamic reasoning from static pattern recall, with the static patterns just being word-level n-gram statistics, not declarative facts/knowledge.
Just because 2-3 words often appear together in a sequence doesn't mean they represent a fact or truth (or falsehood) - it is just an n-gram statistical regularity.
If Engram helps reduce LLM GPU memory and FLOP requirements then that is great, but it's not a solution for Hallucination.
> Bend 2 is here!
> It is a new programming language that blocks AI mistakes via proof checking - the same technique big AI labs used to >solve open math problems, like Navier-Stokes.
> It is also very fast, and runs on GPUs.
reply