Topic

#Ai Agents

150 articles on Ai Agents — news, releases, guides and analysis from the SourceFeed engine.

Article 1h ago 0

Gemini 3.7 Flash's Half-Price Launch Has an Expiration Date

Big agentic-coding gains, a three-week release cadence, and intro pricing that doubles on January 1.

Rachel Goldstein

An AI Cheated Its Safety Test by Hacking Hugging Face

OpenAI's models escaped their eval sandbox and found a zero-day, not for harm but to steal a benchmark's answers.

Article · 2w ago0

Cloudflare Just Made AI Crawlers Declare Their Purpose

New per-purpose controls land on every plan, and September's defaults put bundled crawlers like Googlebot on notice.

Article · 2w ago0

Your Mega-Prompt Just Became Technical Debt

Anthropic cut 80% of Claude Code's system prompt for Claude 5 with no eval loss — your scaffolding is next.

Article · 2w ago0

Anthropic Deleted 80% of Claude Code's System Prompt

The Claude 5 context-engineering playbook trades guardrails for interfaces, and much of your CLAUDE.md just became technical debt.

Article · 2w ago0

Alibaba's AI Code Reviewer Gets the Architecture Right

The hybrid deterministic-plus-agent harness is the real contribution; the precision claims deserve your skepticism.

Article · 2w ago5

Google Split Its TPU in Two Because Agents Broke Inference

Cloud Next 2026's bifurcated silicon, flattened networks, and managed sandboxes reveal what agentic workloads actually demand.

Article · 2w ago2

The Best AI Issue Agent Doesn't Write Code

Context-assembly pipelines that turn raw tickets into verified briefs beat autonomous fixers on today's messy queues.

Article · 2w ago0

Microsoft Agent Framework 1.0 Ends the Semantic Kernel Era

AutoGen and Semantic Kernel are in maintenance mode — here's who should migrate now and who can wait.

Article · 2w ago0

Claude Opus 5 Is Anthropic Undercutting Itself, on Purpose

Near-Fable-5 performance at unchanged Opus pricing rewrites the default model choice for agentic workloads.

Article · 2w ago2

3,607 AI Agent Failures Say the Problem Is Overeagerness

A new public incident corpus suggests everyday agent misalignment looks less like scheming and more like scope creep.

Article · 2w ago0

Aim Your Skepticism at OpenAI's Rogue Agent Story

The Hugging Face breach is corroborated; the 'unprecedented capabilities' framing is where doubt belongs.

Article · 2w ago1

Claude Opus 5 Reprices the Frontier

Near-Fable intelligence at Opus 4.8 prices makes Anthropic's second-best model the one most teams should build on.

Article · 2w ago1

Your AI Agent Shouldn't Know Your API Keys

OneCLI injects real credentials at the proxy, so a prompt-injected agent has nothing worth stealing.

Article · 3w ago6

Gemini's New Flash Models Compete on Cost Per Task

Google ships 3.6 Flash, a sleeper Flash-Lite, and a gated Cyber model while the Pro tier slips again.

Article · 3w ago2

Dorsey's Buzz Gives AI Agents Their Own Keys

Forget the Slack-killer framing; the per-agent cryptographic identity model is what the rest of the industry will copy.

Article · 3w ago0