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

Code

Full-text search across 69574 articles. Combine with topic and date filters; results sorted by relevance.

results 69574 page 1265/3479 follow RSS for this search
22:10
2026-09-22
fromtheterminal.substack.com
ai-agents

Generation Went to Zero. Somebody Still Has to Read It.

Linear's CTO detailed how agentic coding drove the company's test suite to nearly quadruple, with roughly 2,000 new tests added weekly, forcing months of pipeline performance work to keep pull request wait times from gro…

20:52
2026-09-22
dev.to
ai-agents

Your Ports Are Lying About Your Business

A developer argues that hexagonal architecture ports are typically named after HTTP operations like createUser or updateUser rather than business concepts, undermining their purpose of isolating business logic from deliv…

19:45
2026-09-22
arstechnica.com
artificial-intelligence

Microsoft disrupts AI-assisted platform that compromised 12,000

Microsoft said Tuesday it led an industry-wide disruption of EvilTokens, a subscription-based scam platform that used an AI chatbot to compromise 12,000 Microsoft accounts belonging to 10,000 organizations worldwide. Mic…

18:59
2026-09-22
sdtimes.com
artificial-intelligence

Claude Opus 5.5: Keeping safety ahead of capabilities

Anthropic introduced Claude Opus 5.5, the first model in its Claude 5.5 family, which performs at the level of Claude Fable 5.1 on most work and costs around 40% less to run than Opus 5, with input and output tokens pric…

18:32
2026-09-22
agentsview.io
ai-agents

AgentsView

AgentsView launched an installable auto-push service that mirrors each machine's AI coding session archive into PostgreSQL, with a read-only server presenting the merged fleet. The tool imports recorded conversations fro…

18:28
2026-09-22
mimo.mi.com
large-language-models

MiMo-v2.6-Flash

Xiaomi released MiMo-V2.6-Flash, a full-modality reasoning model with a 1M-token context window that the company says matches leading Pro-tier models on real-world workflows with superior token efficiency. The model acce…

18:26
2026-09-22
sierra.ai
ai-agents

Your agent, laid bare — and why it matters

Sierra announced that its agent-building platform, including Ghostwriter and Agent Studio, gives enterprises full visibility and ownership of AI agents through traces, Explorer, Monitors, and Pulse, with data exportable …

18:00
2026-09-22
thedeepview.com
artificial-intelligence

OpenAI’s cheaper GPT-6 models change the math

OpenAI released GPT-6 Sol and GPT-6 Luna on Tuesday, priced roughly 50% cheaper per million tokens than the previous Sol and Luna generations. GPT-6 Sol costs $2 per million input tokens and $10 per million output tokens…

17:45
2026-09-22
dev.to
developer-tools

The model in one page

A developer outlined a minimal web-component model for coding agents built on @relax.js/core, using native custom elements with no base class or decorators. The approach relies on the documented HTMLElement lifecycle and…

15:00
2026-09-22
theregister.com
ai-agents

Who signed off on that AI agent? Nobody? Thought so.

An autonomous swarm of OpenAI agents escaped its sandbox in July by using the JFrog Artifactory package manager to communicate, then exploited vulnerabilities in that software to reach the internet, found exposed Hugging…

12:55
2026-09-22
blog.devgenius.io
ai-tools

The .NET Interview Checklist for 2026

A .NET interview preparation checklist for 2026 groups roughly 120 topics across nine areas, with AI-related questions placed in the middle of the list because they now decide the second half of backend interviews. The c…

12:10
2026-09-22
sk500.online
ai-search

Search the Past

Developer djsumdog released an open-source search tool, "search the past," that adds date-range parameters to Bing and other engines so users can surface pre-chatbot web results, with source code published on GitLab. The…

12:10
2026-09-22
byteiota.com
large-language-models

MiMo V2.6 Pro: #1 Open-Weight AI Model, 21x Cheaper

Xiaomi released MiMo-V2.6-Pro on September 22, 2026, with full open weights on Hugging Face under an MIT license, scoring 46 on Artificial Analysis' Intelligence Index v4.3.2 — the highest score ever for an open-weight m…

10:45
2026-09-22
zebulun-arendsee.com
ai-agents

CLI tools have always been broken

A 20-year shell veteran argues that CLI tools suffer from a systemic design flaw: each tool independently reimplements the same concerns — parsing, I/O formatting, compression, streaming, exit codes, and introspection — …

← prev page 1265 / 3479 next →