it all comes down to sensors and actions. With proper data on what is occurring and proper ways to act upon that data, everything in between is just an optimization problem
Christian Eilers retweeted
Hope you'll find this useful, on the only platform that does not charge a revenue sharing fee for paywalled content 💪.
Nice work @saurinx @YanhuaLiu2n @allegrajacchia on top of the XChat foundations laid by @cambridgemike @skunichi @antonlikespizza @TatanDev @twericz.
getting gold is not even the exciting part here. It's the potential to generate rare metals that are useful in engineering at a low cost
Last month, we demonstrated high-rate alchemy: turning mercury into real, stable gold, beating CERN’s record by a factor of 10.
Last week, we enriched isotopes in the world’s most powerful plasma centrifuge, beating the Soviet record that stood for 40 years.
Now, we’re building a fusion reactor in San Francisco to achieve record power density.
"Oh you use AI so you dont have to think?"
No bro I use it to parallelize 20x and be 10x faster at building stuff
From the past months of experimenting with being fast with agents I've learned the following:
- Your agent must be able to navigate and control the app the same way any human would
- Your agent must be able to debug everything the way a human would. This means every feature must have proper metrics, proper tracing and proper logging.
- Once you start parallelizing enough you ideally want a global overview of all the features that its building in parallel and what stage they are in (implement, review, babysit)
- The best way of getting review is with a bot that will isolate an environment to test everything in
Christian Eilers retweeted
If you're a software developer with AI-induced depression, you should know that we're entering a golden age of programming. Lean is the cure.
Types as specifications
Any type system expresses some properties — even int vs string rules out a class of errors. Richer type systems express richer properties: generics constrain relationships between types, linear types track resource ownership, refinement types attach predicates to base types. But dependent types go further: types can depend on values, which makes the type language expressive enough to state arbitrary logical propositions. Not just "this is a list" but "this is a list of length n." Not just "this function returns a list" but "this function returns a list and here is a machine-checked proof that it is sorted."
This is not speculative. This is Lean 4 today.
The theoretical foundation is the Curry-Howard correspondence: types are propositions, and programs are proofs. A function of type A → B is not merely a piece of code that transforms A into B — it is a constructive proof that "if A, then B." When one writes List α → SortedList α, one is simultaneously defining a function and stating a theorem: "for every list, there exists a sorted version, and here is the evidence." The compiler does not merely check that the code runs — it checks that the proof is valid.
The thesis follows directly: if the specification can be expressed as a type, the compiler becomes the verifier. The AI can produce whatever implementation it wants — insertion sort, merge sort, something entirely novel — and the compiler will reject it unless it comes with a valid proof that the output satisfies the specification. The proof is the guarantee.
There is good reason to believe we are entering a golden age of type-driven development. Not despite AI, but because of it. AI is effective at generating code and filling in proof obligations. Humans are effective at stating what they want. Dependent types are the bridge.
ngrislain.github.io/projects…
