Automatic programming dramatically speeds up writing software in certain use cases and in the right hands. In my experience the output does not reach the structural quality and economy of complexity o

High end NVIDIA cards, and the server and power needed to run them, cost a lot of money, especially if you plan to reach enough VRAM to run massive models. The alternative, so far, has been Apple hard

EDIT: of course this was already done in the past! I had little doubts but people just confirmed me about it on Twitter :) But, keep reading: the CRC32 compromise at the end is an interesting tradeoff

I didn’t expect DwarfStar 4 to become so popular so fast. It is clear that there was a need for single-model integration focused local AI experience, and that a few things happened together: the relea

I started working on the new Array data type for Redis in the first days of January. The PR landed the repository only now, so this code was cooked for four months. I worked at the implementation kind

The proof of work is the wrong analogy: finding hash collisions, while exponentially harder with N, is guaranteed to find, with enough work, some S so that H(S) satisfies N, so an asymmetry of resourc

Those who cannot remember the past are condemned to repeat it. A sentence that I never really liked, and what is happening with AI, about software projects reimplementations, shows all the limits of s

Here LLM and coding agents can find: 1. Exhaustive documentation about Redis commands and data types. 2. Patterns commonly used. 3. Configuration hints. 4. Algorithms that can be mounted using Redis

Anthropic recently released a blog post with the description of an experiment in which the last version of Opus, the 4.6, was instructed to write a C compiler in Rust, in a “clean room” setup. The ex

In my YouTube channel, for some time now I started to refer to the process of writing software using AI assistance (soon to become just "the process of writing software", I believe) with the term "Aut

AI will fundamentally change programming despite personal preferences for traditional coding or concerns about economic impacts.

AI researchers now accept LLMs aren't just "stochastic parrots." Chain-of-thought reasoning improves outputs through internal search and RL.

Redis developer shares advanced insights on optimizing HNSW vector search for low-latency performance after a year of implementation work.

AI systems have rapidly achieved abilities once thought impossible, like understanding language and finding code bugs, with future progress uncertain but likely to continue.

LLMs like Gemini 2.5 PRO amplify coding by catching bugs pre-release, rapidly prototyping ideas, and enabling AI pair programming with expert-level knowledge.