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

Code

Full-text search across 63219 articles. Combine with topic and date filters; results sorted by relevance.

results 63219 page 568/3161 follow RSS for this search
16:49
2026-05-28
anthropic.com
large-language-models

Claude Opus 4.8

Anthropic released Claude Opus 4.8, an upgraded version of its flagship AI model, featuring improvements across coding, reasoning, and agentic benchmarks. The new model launches with user-controlled effort settings on cl…

03:16
2026-05-23
dev.to
developer-tools

A Practical Guide to Designing RESTful APIs

This article provides a practical guide to designing RESTful APIs, emphasizing a resource-oriented approach where endpoints represent nouns and HTTP verbs describe actions, rather than using action-based URLs. It covers …

00:00
2026-05-18
seangoedecke.com
ai-tools

The just-say-no engineer was a ZIRP phenomenon

The just-say-no engineer, a senior developer archetype that thrived during the zero-interest-rate policy (ZIRP) era by blocking unnecessary code and complexity, is now struggling as tech companies shift focus to rapid, p…

00:00
2026-05-09
vexjoy.com
artificial-intelligence

Please Make Mistakes

A team lead at a software company is telling new hires to "please make mistakes" when using AI coding tools like Claude Code, encouraging aggressive experimentation over caution. The manager argues that developers must e…

22:00
2026-03-01
jeffgeerling.com
large-language-models

Expert Beginners and Lone Wolves will dominate this early LLM era

Based on the article, the author, a self-described "AI skeptic," successfully used local LLMs (GPT-OSS 20B and Qwen3 Coder 30B) to migrate blog comments, completing the task in a few evenings. The author notes that while…

10:53
2026-10-23
slack.engineering
ai-agents

Agentic Testing: Where Agents Fit in the E2E Testing Stack

An experiment running more than 200 agentic end-to-end test workflows found that agent-driven tests can be highly reliable but cost $15–30 per run and take over 10 minutes, positioning them as an exploratory layer rather…

18:57
2026-10-21
twitter.com
large-language-models

Flint 40B: Frontier Local LLM (Fast 125 Tps on MacBook)

Recursive SI released Flint, its first model, an open-weights local coding model built with the company's automated research system, the Eureka Machine, CEO Richard Socher announced on X. Recursive SI claims Flint runs a…

07:06
2026-10-21
github.com
ai-agents

Turn any single player PC game into coop instantly

A GitHub project called Co-op Anything lets an AI coding agent such as Claude Code, Codex, Gemini CLI, Cursor or OpenCode add co-op multiplayer to single-player PC games by following the repo's AGENTS.md and skills. The …

21:51
2026-10-20
union.ai
ai-infrastructure

Show HN: Flyte devbox now runs GPU workloads on Apple Silicon

Flyte added an Apple Silicon accelerator to its devbox, letting a task or app that requests gpu="AppleSilicon" run natively on a Mac so torch.device("mps") and MLX work as "cuda" does on a cluster. Because Linux VMs have…

08:00
2026-10-20
spectrocloud.com
ai-infrastructure

Benchmarking GLM 5.3 on AMD Instinct Coder | Spectro Cloud

A Spectro Cloud benchmark of GLM 5.3 running in FP8 on an 8-GPU AMD Instinct Coder appliance with vLLM 0.31.0 supported 60 simulated developers and 15 coding agents over a five-hour window, with a median first token of 4…

00:00
2026-10-20
depot.dev
ai-agents

Now available: Managed Agents and Depot Sandboxes

Depot launched Managed Agents, which runs coding agents from Claude, OpenAI, and Devin on Depot infrastructure, alongside Depot Sandboxes, isolated Linux microVMs created from user code via the Sandbox SDK. Each Managed …

00:00
2026-10-18
mindstudio.ai
ai-agents

Claude's New Projects and /goal Features: A Practical Guide

Claude Code's September redesign turns Projects into an orchestration layer: the main project thread delegates work to independent sub-threads that inherit the project's instructions and memory and keep running after the…

← prev page 568 / 3161 next →