17,811 karma · joined June 4, 2016
But a lot has changed in those 12 months.
Frontier models and coding agents have advanced so much that I don't really see much value in this anymore.
Not sure the DeltaDB based features really add anything significant compared to the alternatives.
I reckon the game here has to be adding a service that stores the data and runs agent sessions?
The reason they open sourced this is because grok-build uploaded entire directories.
A) You notably don't write a recovery log (WAL/journal) for things not yet flushed, so data can be lost. Do you have plans to add this? I think it would be pretty crucial.
B) the system is single writer. Do you have plans for adding horizontal scalability so a writer can be dynamically selected and routed to, transparent to the client? (Or with client cooperation, but without forcing sharding on the user)
Besides that, Rust code is actually much easier to maintain , thanks to type system guarantees.
That would be very powerful for various use cases.
Right now they want to prevent the US labs from gaining any sort of self-reinforcing oligopoly on the space, and to let the ecosystem in China flourish.
That will all die sooner or later.
Other things don't though.
The per-repo config is in `.git/config`, so that can still not be checked into the repo itself, unless I'm missing something?
So not very useful at all...
I get the security implications, but there could be a checked in `$REPO/.githooks`, and a prompt asking to allow running those hooks , with an approval marker being stored inside `.git/`.
I found it works very well in once-off scenarios, but the specs often drift from the implementation. Even if you let the model update the spec at the end, the next few work items will make parts of it obsolete.
Maybe that's exactly the goal that "codespeak" is trying to solve, but I'm skeptical this will work well without more formal specifications in the mix.
* This isn't a language, it's some tooling to map specs to code and re-generate
* Models aren't deterministic - every time you would try to re-apply you'd likely get different output (without feeding the current code into the re-apply and let it just recommend changes)
* Models are evolving rapidly, this months flavour of Codex/Sonnet/etc would very likely generate different code from last months
* Text specifications are always under-specified, lossy and tend to gloss over a huge amount of details that the code has to make concrete - this is fine in a small example, but in a larger code base?
* Every non-trivial codebase would be made up of of hundreds of specs that interact and influence each other - very hard (and context - heavy) to read all specs that impact functionality and keep it coherent
I do think there are opportunities in this space, but what I'd like to see is:
* write text specifications
* model transforms text into a *formal* specification
* then the formal spec is translated into code which can be verified against the spec
2 and three could be merged into one if there were practical/popular languages that also support verification, in the vain of ADA/Spark.
But you can also get there by generating tests from the formal specification that validate the implementation.
This puts much more work on the compiler development side, but it's a great boon for the ecosystem.
To be fair, zig is pre 1.0, but Zig is also already 8 years old. Rust turned 1.0 at ~ 5 years, I think.
At least 100k context without huge degradation is important for coding tasks. Most "I'm running this locally" reports only cover testing with very small context.
For Tesla it was "electrify transport to end dependence on fossil fuels and save the planet", for SpaceX it was "save humanity by becoming a multi-planetary species".
With how much he talked about it, he did probably actually believe in Mars.
But now both of these ideals have come into conflict with his newfound political affiliations, so they have to be dropped.
It's essentially just an atomic pointer that can be swapped out.
Many things that would only be caught at runtime in other languages are caught at compile time in Rust, making coding agents iterate until things compile and work well.
Rust also has great error messages, which help the agents in fixing compilation errors.
BUT it is not good at all at tool calling and agentic workflows, especially compared to the recent two mini-generations of models (Codex 5.2/5.3, the last two versions of Anthropic models), and also fell behind a bit in reasoning.
I hope they manage to improve things on that front, because then Flash would be great for many tasks.
Codex quite often refuses to do "unsafe/unethical" things that Anthropic models will happily do without question.
Anthropic just raised 30 bn... OpenAI wants to raise 100bn+.
Thinking any of them will actually be restrained by ethics is foolish.
Research and training are the cost sinks.