


Playing with the largest conversational corpus in the world.





It does what it learnt from us :(
I’ve tried to vibe code in Rust a couple of projects (around 20KLOC). The worst result so far compared to other languages. Absolute slop in terms of ownership: it adds clone(), lifetimes, Arc, to_vec, etc absolutely randomly just to shut the compiler. (Opus 5.5). I think Rust has too complex semantics and requires rigorous ownership design. My personal top of languages in terms “write prompt get nice code back”: - Go (!) it’s just hard to fuck up such primitive code. - C/C++. I guess huge training data size does the job. - Java / Kotlin. Solid, but you tend to get “enterprise patterns”. - Python / TS. They okay for small programs, for larger ones LLMs abuse gradual typing. … - Rust. Outright slop.


Este es el nivel, chavales. Que nos gobierne la IA por favor.
Es normal que os resulte rara la palabra “sacrificio”. No habéis dado un palo al agua en vuestra vida.

The actual GOAT of our IT industry who co-created the C programming lang and helped develop the Unix OS. Happy birthday to a true legend whose work shaped modern computing.

Mercury Transfer Module separation confirmed! 📡 ✅ After nearly eight years in space and billions of kilometres travelled, #BepiColombo's Mercury Transfer Module has successfully separated. Signal acquired via our Cebreros deep-space antenna confirms the spacecraft is healthy and operating as expected. The MPO and Mio spacecrafts are now on their way to Mercury orbit insertion on 21 November. Farewell, MTM. Mercury awaits. ☀️🛰️





I'm writing "Understanding Go AI Inference": how the run of LLMs locally, from Go, work underneath. The stack is llama.cpp (the C/C++ inference engine), Yzma (which calls it from Go, without cgo), and Kronk (an OpenAI-API-feeling SDK and model server on top). The first article demystifies inference itself. A simple mental model for this is: inference is a pure function. It takes your text and billions of frozen numbers (the weights), and returns one prediction: the next token. Something like nextToken(input, weights). No learning, nothing updated. And a whole answer is just that function in a for loop: predict a token, append it, run again, until the model emits its "I'm done" token. Also, in this article we explore one fundamental part of the LLM, the GGUF model file, which is fully self-describing. The weights, the architecture, even the entire tokenizer live inside that one file. Article drops Tomorrow! Want these articles directly in your inbox? Subscribe to the newsletter: internals-for-interns.com/ne… #Go #AI

