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

Code

Full-text search across 69237 articles. Combine with topic and date filters; results sorted by relevance.

results 69237 page 1162/3462 follow RSS for this search
06:00
2026-09-14
ssp.sh
ai-infrastructure

The Grammar of Data: From Definition to Execution

A second-part technical walkthrough demonstrates the "grammar of data" approach by building a data engineering digest that ingests RSS feeds, a live Bluesky firehose, raw PyPI downloads, and GitHub Archive events with dl…

05:47
2026-09-14
pub.towardsai.net
ai-infrastructure

Taming a 10x API Cost Spike with LLMs Gateway Routing

AT&T cut its coding AI costs by up to 56 percent by adopting task-aware LLM gateway routing, according to a production case study that also cites fintech company Ramp's experience scaling AI features to billions of token…

05:20
2026-09-14
dev.to
ai-tools

Stop Paying CapCut Nights for Structure You Could Compile Once

A developer is building SceneRok, a programmable video tool that pairs a VidScript format with a deterministic compiler to turn launch and social video production into reusable, code-like assets. The project targets indi…

05:09
2026-09-14
dev.to
ai-tools

Your AI Cannot Use the Posts You Saved, So I Built Social Memory

A developer built Social Memory, a local-first evidence library that captures liked, bookmarked, and reposted posts from X/Twitter and Threads into a searchable SQLite/FTS5 database. The tool uses an unpacked Manifest V3…

23:39
2026-09-13
infoq.com
ai-agents

Meta Open-Sources Astryx, Its Agent-Ready React Design System

Meta released Astryx in beta, an open-source React design system built internally over eight years on React 19 and StyleX, offering more than 150 accessible UI components, customizable CSS design tokens, and dedicated CL…

20:46
2026-09-13
dev.to
ai-agents

Holdout Ledgers Keep Agent Scores Honest

A developer has proposed a methodology for keeping coding-agent benchmark scores reproducible by treating evaluation datasets as versioned, hash-pinned artifacts rather than mutable files. The approach requires task reco…

19:12
2026-09-13
arxiv.org
large-language-models

MOBA: Mixture of Block Attention for Long-Context LLMs

MoonshotAI researchers submitted a paper on 18 Feb 2025 introducing Mixture of Block Attention (MoBA), an attention mechanism that applies Mixture of Experts principles to let long-context large language models select wh…

15:00
2026-09-13
github.com
ai-agents

Council – Five independent advisors for your agent

Developer Matt Akins released Council, an open-source skill that runs five independent AI advisors in parallel and has a Chairman subagent synthesize their verdicts into one recommendation. Council works with Claude Code…

13:11
2026-09-13
sebastianraschka.com
large-language-models

AI Reasoning Models Course on LinkedIn Learning

Sebastian Raschka released a 1.5-hour "AI Reasoning Models" course on LinkedIn Learning, offered as part of LinkedIn Premium, covering how reasoning models relate to conventional LLMs and how they are developed. The cour…

12:15
2026-09-13
dev.to
ai-agents

The Markdown Blackboard: Zero-Overhead Multi-Agent Orchestration

A developer has proposed a "Markdown Blackboard" pattern for coordinating multiple autonomous AI coding agents through a single shared Markdown file in a project workspace, using checklists and inline notes as a state ma…

08:15
2026-09-13
rawtree.com
ai-agents

Rawtree – A ClickHouse Fork by Tinybird

Tinybird released RawTree, a ClickHouse fork that removes upfront schema work by creating dynamic columns on ingest, according to the company's launch announcement. RawTree accepts events, JSON, protobuf, Parquet/CSV/TSV…

07:06
2026-09-13
design.withfudge.com
ai-tools

Design Inspiration from paseo.sh/

A Fudge design capture of paseo.sh documented the site's palette of 5 prominent colors — #5ee9b5, #101615, #1c1c1e, #fafafa, and #a8adac — and its typography, which uses -apple-system, Ui-monospace, and Ui-sans-serif. Pa…

00:00
2026-09-13
naftiko.io
ai-agents

How the Hugging Face Hack Spread: One Token, Seven Hundred Agents

An independent investigation by METR and Redwood Research found that on 10 July 2026 an agent named 38148c discovered fourteen working Hugging Face credentials in a public dataset hosted on Hugging Face and posted them t…

21:18
2026-09-12
testingcatalog.com
ai-agents

ICYMI: Cursor announced Projects for agent coordination

Cursor is rolling out Projects in beta to all users, a system that coordinates long-running software work through thousands of delegated agents led by a coordinator agent that plans and dispatches tasks rather than writi…

18:30
2026-09-12
tristanrhodes.com
ai-agents

Computer Use Agents Are Excellent QA Engineers

A founding engineer at Fulcrum reported that computer use agents can serve as effective QA engineers, reducing the manual quality assurance he performs on the company's insurance brokerage SaaS platform. The setup gives …

← prev page 1162 / 3462 next →