yet
23 stories and discussions about yet, aggregated from every source we track.
Benchmark for tracking model capability after release. - ninjahawk/livenerf
If you checked my profile recently, you probably noticed my page has been completely quiet since...
Early-stage startups shouldn't run on Kubernetes yet.
<p>A Bloom filter is a simple yet powerful data structure. It allows you to answer the question have you seen this before? in a very fast and memory efficient way. Unlike a regular set, a Bloom filter only needs to store a few bits per item instead of storing the whole thing. The trick is, a Bloom filter will be able to tell you if something is not present in the set with 100% certainty, but if you ask it if something is present in the set, you might get a false positive. That means the response could be true, even if the item was never stored in the set.</p>
This is a submission for the MLH x DEV Writing Challenge What I Built Hey there, my name...
A recap of LDX3 NYC, where the hallway conversations resounded with discussions about AI.
Yet another experiment that checks Jev's talking skills. - zie1ony/jev-talks
One of my biggest hobbies in high school was playing Guitar Hero with my friends.
In the first part of the longest series yet, I'll outline what's coming, and we'll lay a cornerstone for the project.
Real-time status for every stop in the NYC area mass transit systems.
<p>Back in July, inspired by yet another AI integration into firefox, I wrote a <a href="https://mas...
Retatrutide is a triple-hormone obesity drug simulating GLP-1, GIP, and glucagon.
Eleven v4 and v4 Turbo: more emotional nuance, faster responses, stronger voice cloning. Live now in ElevenAgents, ElevenCreative and API.
Aprende Python gestionando tu propio Almacén Digital. Guía visual y práctica para principiantes absolutos, con código ejecutable en el navegador.
SevenDB — reactive,scalable , in-memory database designed for real-time systems with deterministic execution, fine-grained backpressure, and modern hardware optimization. - sevenDatabase/SevenDB
Linux, Devops, Scripting, Cats and various things come to my mind
yass — Yet Another Spec Syntax: a YAML spec language for AI-agent-driven development (specs drive TDD + implementation generation). - shakefu/yass
Your last chat with an AI holds the wreckage of a scorecard. Here’s how to recover it.
Why yet another agent? There are a couple of key assumptions I have: Coding agents are surprisingly simple Especially the agentic part They tend to be while loops with a small number of tools There seems to be very…
Google promised Gemini 3.5 Pro in June, but it spent the summer trotting out smaller Flash models . Now, Google is ready to take on the frontier again with Gemini 4 Argon . The company claims this new AI offers industry-leading performance in coding, knowledge work, and cybersecurity, but you aren't allowed to use it yet. While most of us will have to wait to test Gemini 4, Google says engineers inside the company are already using the new model extensively. Argon reportedly used "fleet-wide telemetry data" to help Google save 300 TiB of memory across its data centers. Meanwhile, Argon agents have been working to migrate C/C++ codebases to Rust across Google, including thousands of lines in the core re2 and libgav1 libraries and more than 800,000 lines in the Fuchsia OS Zircon kernel. Google has also come armed with a raft of benchmarks to back up its claims. On the software engineering DeepSWE v1.1 benchmark, Gemini 4 Argon hits 77.9 percent, which is higher than GPT-6 Astra, Fable 5.1, and Opus 5.5. Google promises similar power across a range of long-horizon tasks, pointing to Argon's industry-leading score in the economic analysis Vals Index test. Read full article Comments