Hyperbob

we're working on merging it into workerd - still very much in progress - but you can see some of it here: github.com/cloudflare/worker… For celld we'll might do some more bug fixes, but the next major release of celld will be workerd

I am working on a map of the secure program synthesis space, in collaboration with @sergeybratus for our NDIST keynote on Tuesday. Here's a sneak-peak. The words "RISC-V" and "Lean" are used here WLOG, and some simplifications are made to fit everything on one page. Did I miss anything? 1. Develop semantics for each language in an interactive theorem prover, and then use these semantics to prove that every program is correct. (@oath_tech has done some work along these lines. See in particular Sam Xifaras' project on Ruby samx.io/blog/topics/devlog/2…) 2. Develop semantics for an architecture, say RISC-V, or perhaps for all possible architectures, and then use this to prove that every compiled program is correct. (@AnthropicAI made headlines recently with their announcement of a very large-scale project along these lines in collaboration with @theoremlabs anthropic.com/research/forma…) 3. Develop semantics for an architecture, say RISC-V, or perhaps for all possible architectures, and then use this to capture a formal model of each existing compiler or interpreter, and then iteratively (provably) refine each such model to an interpretable and easy-to-use formal semantics; then continue as in approach 1. (See foundational work by @kirancodes at BASIS AI basis.ai/blog/ship-your-inte…) 4. Make Lean, or some other such ITP + programming language, fast to run (comparable to Rust or C), and then completely rewrite all software in it, and prove the rewrites are correct. (This is I think, loosely speaking, the idea behind @VictorTaelin 's Bend.) 5. Make implementation-level verification tools, such as Verus, more capable and ergonomic, and then use them to prove all software correct. (This is what @fhuszar and @Craig_Hughes_ are doing at Reasonable, & I'm aware that BASIS and AWS are also working on this.) 6. Design a language in which unsafe states are illegal, and then rewrite everything in that language. Here, what kinds of safety you can express will be much more limited but the problem is, conversely, way more tractable. (This is what @danwallach and @DARPA did with TRACTOR, where the safety property is memory safety.)

Talked to multiple founders yesterday who have been building their products over the last 3 years. Started manual code. They feel behind and slower than companies that started this year with all code written by agents. I have never seen such an order of magnitude difference.

I’ve been watching whole day various talks about AI at the conference I’m at… and I have feeling that people overcomplicate their AI setups so much. You don’t need hundreds of skills or agents definitions.

The trajectory is clear

New on our Frontier Red Team blog: using Claude to formally verify software at large scale. Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time). With AI models, however, this is beginning to change. In collaboration with @theoremlabs, we used Claude to prove security properties in over one hundred real-world open-source libraries over the span of a few weeks. Read our research in full here: anthropic.com/research/forma…

Ok... I see why Bend is pretty radical