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

Code

Full-text search across 70332 articles. Combine with topic and date filters; results sorted by relevance.

results 70332 page 1383/3517 follow RSS for this search
11:00
2026-10-27
julin.ai
ai-agents

Building a Single-File Python Interpreter

Developer soasme is building small-python, a QuickJS-style single C11 source file implementation of the Python language core without the standard library, intended as a possible sandbox for agents to run untrusted code. …

10:16
2026-10-27
byteiota.com
developer-tools

Pylance + Pyrefly: Python Type Checker Is Now Swappable

Microsoft has decoupled Pylance from Pyright via the Type Server Protocol (TSP), a new open standard that lets Pylance accept any compliant type checker as its backend, with Meta's Rust-powered Pyrefly the first to plug …

08:53
2026-10-27
news.ycombinator.com
ai-infrastructure

Show HN: AMD EPYC Windows developer rigs in the UK/EU in ~10 minutes

Developer Mick launched Whitehirst, an early-access service that provisions ephemeral Windows Server 2022 developer workstations on AMD EPYC hardware in UK/EU datacenters in about 10 minutes, priced at £12 for 8 hours or…

04:00
2026-10-27
machinebrief.com
ai-agents

FlexA-Mem: Budget-Adaptive Agentic Memory for LLM Agents

Researchers behind the arXiv paper FlexA-Mem introduced a budget-adaptive memory system for LLM agents that writes each unit of history once into an immutable store and renders a fresh memory per call, outperforming the …

04:00
2026-10-27
arxiv.org
natural-language-processing

AdaptTok-Indic: Script-Aware Adaptive Tokenization for Indic Languages

A new arXiv paper (2610.33017v1) reports that AdaptTok-Indic, an Indic-specialized adaptive tokenizer, achieved mean token fertility of 1.432 for Bengali and 1.388 for Hindi across five recorded seeds, versus 2.156 and 2…

04:00
2026-10-27
arxiv.org
machine-learning

Nested Sparsity for Scalable Pretraining and Continual Learning

Researchers at the Ma Lab at Berkeley introduced Nestor, a transformer architecture that adds a conditional-computation mechanism generalizing the attention operator, and reported it outperforms a conventional mixture-of…

04:00
2026-10-27
arxiv.org
ai-agents

AOS-Bench: Can LLM Agents Manage Dynamic Workloads?

A new benchmark, AOS-Bench, shows that LLM coding agents' success on isolated tasks does not carry over to managing dynamic workloads, with every system losing 13 to 23 points on heavy workloads across five model-harness…

03:39
2026-10-27
zenmux.ai
artificial-intelligence

New Model Available: GPT-6.1 Terra

OpenAI added GPT-6.1 Terra, the mid-tier model in its GPT-6.1 series, priced below GPT-6.1 Sol, according to the model listing. OpenAI positions GPT-6.1 Terra for everyday agentic, coding and writing work, with particula…

01:56
2026-10-27
psi.inc
artificial-intelligence

Five Results on Open Quantum Problems

PSI researchers working with an AI research system reported new results on five open problems in quantum information theory, each released with a paper, a Lean formalization and verification code in a public repository (…

00:22
2026-10-27
cyberscoop.com
ai-safety

Experts temper emergency-level alarms over critical Brotli defect

A buffer overflow in Google's Brotli decompression library, tracked as CVE-2026-111497 and discovered by OpenAI Codex Security, allows system crashes and remote code execution, and Node.js disclosed it in an October 21 s…

← prev page 1383 / 3517 next →