The 2026-07-28 Model Context Protocol specification is out, bringing a stateless protocol core, Multi Round-Trip Requests, header-based routing, cacheable list results, authorization hardening, a formal extensions framework, and updated Tier 1 SDKs.
sqlite-backed shell history
This is the fifth model in the ThinkingCap series. We reduced how much Google's gemma-4-26B-A4B-it thinks, without compromising the quality of its answers.
Who is the Assistant? We investigate the character that most modern language models inhabit when interacting with users.
Build an ultra-low-latency voice agent with NVIDIA open models. Learn how Nemotron Speech ASR achieves sub-25ms transcription, how Nemotron 3 Nano LLM and Magpie TTS work together, and how to optimize architecture for real-time voice AI deployment.
Discover the new way to request user location data.
Self-guided agents that think continuously
We're post-tokenmaxxing. What are we pre-? How do we get there?
We are rebuilding Monica from scratch, and this new series will document how.
The craft of engineering is rapidly changing. We built our own coding agent to accelerate faster. Inspect is now open to teams outside Ramp through early access.
Want to follow along with Rust development? Curious how you might get involved? Take a look!
At VectorWare , we are building the first GPU-native software company . Today, we are excited to announce that we can successfully use Rust's std::thread on the GPU. This milestone marks a significant step towards our vision of enabling developers to write complex, high-performance applications that leverage the full…
C3 is the ergonomic, safe evolution of C. Familiar syntax, full ABI compatibility, optionals, slices, contracts and zero-cost abstractions.
With the latest release of corecrypto, we’re publishing our implementations of quantum-secure ML-KEM and ML-DSA algorithms, along with the mathematical proofs we built to assure they are faithful to the FIPS 203 and FIPS 204 specifications. To advance the state of the art for assuring critical software, we're also…
Learn what it means to conform to the Python typing spec, why it matters, and the conformance status of each type checker including Pyrefly, Ty, Pyright and Mypy.
Analysis of millions of human-agent interactions shows agent turns getting longer, with software engineering making up nearly half of tool calls.
A customer's Go application kept crashing on a 32-bit embedded Linux system. We traced the fatal netpoll error to a pointer aliasing bug in the Go runtime.
Rietta patched a government client's Ruby on Rails site within hours of a 9.5 CVSS ActiveStorage CVE. Exploit attempts began before business hours resumed.
One command-line tool to query them all, built with Rust and ADBC
A practical walk-through of a fixed-width uint128 implementation in modern C++.
SAFA details the full exploitation of CVE-2025-13032, turning a double-fetch vulnerability in Avast's kernel driver into a local privilege escalation to SYSTEM on Windows 11.
We get asked about AI a lot. Whether we’re going to add it to Yarn Spinner, whether we use it ourselves, what we think about it. Fair questions. Time to write it all down. Yarn Spinner doesn’t use the technology that’s currently being called AI. We don’t have generative AI features in the product, and we don’t use…
A recap on the work done in NumPy and CPython to make multi-threaded NumPy workloads scale on the free-threaded build of CPython.
Word sizes, strange machines, and why <strong>int</strong> was never meant to mean 32 bits. C's flexible integer types were how the language achieved portability in a world of 12, 18, 36, and 60-bit computers.
It's time for another technical blog post about async Rust on embedded. This time we're going to pitch Embassy/Rust against FreeRTOS/C on an STM32F446 microcontroller.
AI agent misbehavior isn't a sandbox problem—it's a permissions problem.
If you compile your app for AVX2 and it runs on Windows ARM under Prism emulation, is it faster or slower than compiling for SSE2-4.x? I assumed it would be roughly the same — maybe slightly slower due to emulation overhead, but AVX2's wider operations would compensate. The
What makes BEAM and OTP different from async/await, threads, and actors. Process isolation, supervisors, and why Erlang's model keeps winning 40 years later.
