1st Rust for Rustaceans in Bangkok meetup going well 🦀✨Thanks everyone for coming! The topic is Rust FFI Unity and also some ai coding techniques along the ways 😬

I just (let ai) built a latent-space LFU cache where cache keys are BLAKE3(NeuronShard ⊕ region), eviction priority is weighted by emotion (arousal), admission is sigmoid-gated, and the whole thing sits on top of BFCP's O(50) region screening. 🤯 via @zeddotdev @Zai_org GLM5.1

Let's proof this in Rust 🐐✨

Cooking Neuron DB (Neuro-symbolic) in my labs, so GOAT! 🐐

You are not prepare for this 😳 (me too)

✅ SpectralQuant faster than TurboQuant tested on my microgpt-rs

Monthly Rust talk in Bangkok be like 😎

Best place to vibe coding bro 🇹🇭

Did you know that you can let agent burn-rs 🔥 Gemma4 LoRA via @zeddotdev in both Python and Rust simultaneously 👀

Andy really like kaosoy kai lol, so much fun today! 😆

Super excited to finally share CocoIndex v1 ! @cocoindex_io - After 50 releases in v1 alpha, together with 70 contributors since v0 launch. It is a fundamental redesign of how you write incremental data pipelines — built from a year of watching what people actually wanted to do with CocoIndex and building in the space. CocoIndex V1 is built for 𝐀𝐈 𝐞𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐬 𝐚𝐧𝐝 𝐚𝐠𝐞𝐧𝐭 𝐛𝐮𝐢𝐥𝐝𝐞𝐫𝐬 — people building coding intelligence, context, RAG, memory, knowledge-graph that live agents depend on. At GTC 2026, Jeff Dean and Bill Dally named a bottleneck that’s about to reshape every piece of infrastructure around AI. Agents run roughly 50x faster than humans, but the tools they rely on were built for human speed. Data infrastructure is one of those tools, and it matters beyond inference. An agent reasoning over a codebase, a conversation graph, a document corpus, or a stream of events needs that data fresh, organized, and cheap to query — not just on the first call, but throughout the run. That has always been CocoIndex’s vision. V1 makes it the right shape for agent-era workloads: the same incremental, state-driven guarantees, but now expressive enough to cover the pipeline shapes agents actually produce — entity resolution, clustering, multi-phase reduction, per-tenant topologies, conditional targets beyond embeddings and all. Every pattern in the examples gallery is something a long-horizon agent might want to run itself, and have its outputs become fresh source data for the next agent — without a human babysitting the job. Teams that take this on seriously typically allocate 10 – 20 engineers for at least six months to land the first production-worthy version — and then keep paying for maintenance indefinitely as sources, targets, and schemas evolve. CocoIndex ships all of this in the engine, so the code you write is the pipeline itself, not the scaffolding around it. Take a look at the announcement here, and keep us on your feedback!

Feeling lonely? How about monthly Rust event in Bangkok by Rustaceans 🦀😎

Presenting Meridian: a line to connect deterministic compute and language model AI. From Neural Turing Machines and Differentiable Transformers to The Neural Computer, there’s a rich history of trying to combine traditional deterministic computation with the wildly different architecture of Artificial Intelligence. I’ve spent the last 4 weeks creating a single neural network that has the combined capabilities of a 4B param language model and a deterministic computation engine based on Web Assembly. It allows the AI deterministic integer computations up to 2^32, control flow (while loops and if statements) and a basic filesystem - all implemented as part of the transformer neural network, no external tool calls. With this architecture adding fewer than 1 million parameters to an existing 4B param language model I can take it from <20% accuracy on arithmetic with 4-digit numbers to 100% accuracy on 4 digit numbers and 99% accuracy on arithmetic up to 2^32 without adversely affecting the language model’s performance on non-mathematical tasks. The combined model can precisely execute a range of algorithms including checking number for primeness, finding the GCD of two integers and sorting arrays.

RotorQuant - upgraded TurboQuant. > 10x KV cache compression > 28% faster decoding > 5x faster prefill > 44x fewer parameters Same quality as full attention. 1/10th the memory. Ok, another massive VRAM discount for local LLMs. github.com/scrya-com/rotorqu…

I would say they can read my mind!

1/4 Want to build a computer inside a transformer? Given the wide interest in our project, we are releasing the code and the weights so that others can build on our construction.

Gooood

Wait, what?

1/4 LLMs solve research grade math problems but struggle with basic calculations. We bridge this gap by turning them to computers. We built a computer INSIDE a transformer that can run programs for millions of steps in seconds solving even the hardest Sudokus with 100% accuracy