grep -r "Code" /news · home›search
grep -rli "Code" /news

Code

Full-text search across 69509 articles. Combine with topic and date filters; results sorted by relevance.

results 69509 page 1235/3476 follow RSS for this search
22:57
2026-10-31
ziggit.dev
developer-tools

`dabeob`: a simple TUI lib for Zig

Developer `dabeob` released version 0.17.0 of its namesake TUI library for Zig, a first presentable alpha that wraps low-level terminal setup, column/row grid filling and a double-buffer grid for efficient writing, witho…

20:15
2026-10-31
forum.level1techs.com
ai-infrastructure

Gorgon Halo Arrives in gmkTek.. do you need 192gb of LPDDR5?!?

A first-look test of GMKtec's Gorgon Halo unified-memory mini-PC compared it against an Nvidia-based Spark system, with 184 GiB usable versus 121 GiB usable, serving the same models across engines including vLLM 0.32.0+s…

17:07
2026-10-31
morkeeth.substack.com
artificial-intelligence

Exploring taste graphs and where we can beat frontier models

A developer testing Qloo's taste graph against frontier models found the data gave no measurable improvement on recommendation and long-tail naming tasks, but sharply improved results on a location task where models lack…

11:00
2026-10-31
julin.ai
ai-agents

Adding Metering to Small Python

Developer soasme is adding a metering feature to Small Python, an embeddable Python-like language intended to be run by agents, so a host application can halt code that consumes too many resources. The metering documenta…

04:11
2026-10-31
overbring.com
large-language-models

How to run flint NVFP4 on 2× RTX 5060 Ti 16 GB

A 39.8B mixture-of-experts model with 2.5B active parameters, flint-nvfp4, served at its full 262,144-token native window across two RTX 5060 Ti 16 GB cards, retrieved a planted needle in 18 of 18 attempts through 157,28…

00:00
2026-10-31
runagentrun.co.uk
large-language-models

DeepSeek updates V4.1 Flash after outage

DeepSeek released an updated V4.1 Flash model on Saturday, 17 October, claiming faster task completion, shorter outputs and stronger performance on reasoning, coding, tool-use and visual tasks, with the update live on De…

20:18
2026-10-30
byteiota.com
ai-infrastructure

llm-d 1.0: The Inference Layer vLLM Was Missing

Llm-d, the Kubernetes-native fleet coordination layer for LLM inference built jointly by Red Hat, IBM, Google, CoreWeave and NVIDIA, reached version 1.0 on October 20 at PyTorch Conference North America, adding multi-ten…

← prev page 1235 / 3476 next →