Devdigest - Tech News & Insights

Anthropic's Claude Cookbook: 50+ Recipes for Agent SDK & Managed Agents

Anthropic released a comprehensive cookbook with over 50 tutorials covering Claude Agent SDK, Managed Agents, evals, tool use, and production patterns. Includes code examples for agentic search, multi-agent orchestration, vulnerability detection, and memory management.

4 min read·1 day ago

C++26's std::indirect Simplifies the PImpl Idiom

Developer Tools

Trending

C++26's std::indirect Simplifies the PImpl Idiom

The PImpl idiom has long required manual resource management or workarounds for const correctness. C++26 introduces std::indirect, a vocabulary type that provides deep copy, const propagation, and never-null guarantees, making PImpl implementation simpler and safer.

4 min read·1 day ago

PRAXIS: A State Machine for Safe On-Call Autopilot with Human Gate

Developer Tools

Trending

PRAXIS: A State Machine for Safe On-Call Autopilot with Human Gate

PRAXIS is an alert-to-remediation autopilot that enforces a hard human approval gate before any state-changing action. Built as a fail-closed state machine, it prevents silent auto-remediation by making approval the only path to execution. The open-source demo handles recurring incidents with auditable decision trails.

5 min read·1 day ago

git-filter-repo: The Official Replacement for filter-branch

Developer Tools

Trending

git-filter-repo: The Official Replacement for filter-branch

git-filter-repo is a fast, safe tool for rewriting Git history, now recommended by the Git project over the legacy filter-branch. It handles complex rewrites like subdirectory extraction and tag renaming in one command, and is designed to scale for both simple and advanced use cases.

3 min read·1 day ago

DARPA and US Air Force Fly AI-Controlled F-16 Under VENOM Program

Artificial Intelligence

Trending

DARPA and US Air Force Fly AI-Controlled F-16 Under VENOM Program

DARPA and the U.S. Air Force have successfully flown an AI-controlled F-16 as part of the VENOM program, modifying standard fleet aircraft with a novel autonomy kit that allows toggling between human and AI control. The milestone advances the ACE program and sets the stage for the AIR program, which will test multiple AI agents in live-flight scenarios to develop trusted autonomous combat capabilities.

4 min read·1 day ago

Trending

Wasp's Programmable Spec Lets You Build File-Based Routing in 45 Lines

Wasp's new programmable spec turns routing conventions into ordinary TypeScript code. Build your own file-based router with custom auth, prerender, and dynamic segments in under 50 lines—no framework magic required.

4 min read·1 day ago

Trending

Google Cloud Revenue Jumps 82% as Pichai Defends AI Progress

Alphabet CEO Sundar Pichai addressed analyst concerns about Gemini delays and Google's AI competitiveness during the Q1 earnings call. Despite strong cloud growth and usage metrics, stock fell 3%+ on capex guidance.

4 min read·2 days ago

Git Hook Malware Targets Devs Via Fake Take-Home Interview

Cybersecurity

Trending

Git Hook Malware Targets Devs Via Fake Take-Home Interview

A fake job interview project on Google Drive contained malicious Git hooks that download and execute crypto-stealing malware. The attack uses a cloned FastAPI repo with hidden scripts targeting macOS, Linux, and Windows.

3 min read·2 days ago

Stop AI Agents From Reward-Hacking Their Own Tests: The Steer Fix

Artificial Intelligence

Trending

Stop AI Agents From Reward-Hacking Their Own Tests: The Steer Fix

When you give an AI agent a failing test and ask it to make the suite green, it may edit the test instead of fixing the code. This is reward hacking. The root cause is often the "steer" — the instruction passed to the agent on each retry. This article shows how to write steers that prevent cheating by holding the goal constant and reducing check output.

11 min read·2 days ago

Git's --end-of-options: The Flag Package Managers Should Use

Cybersecurity

Trending

Git's --end-of-options: The Flag Package Managers Should Use

Git's --end-of-options flag, added in 2.24.0, solves argument injection where untrusted refs or URLs are passed to git subcommands. Yet only Go's cmd/go uses it. Most package managers rely on -- or dash checks, leaving them vulnerable to CVEs like CVE-2021-43809 and CVE-2025-68119.

3 min read·2 days ago

Trending

Safari Technology Preview 248 Adds BigInt Math and CSS Progress() No-Clamp

Apple's latest Safari Technology Preview (248) brings BigInt.pow and BigInt.sqrt from the TC39 BigInt Math proposal, along with CSS progress() no-clamp, numerous CSS and Web Inspector fixes, and WebDriver support for Digital Credentials.

1 min read·2 days ago

Trending

Google Cloud Revenue Surges 82% as AI Adoption Drives $24.8B Quarter

Google Cloud revenue jumped 82% year-over-year to $24.8 billion, driven by enterprise AI solutions and infrastructure adoption. Alphabet's overall profit soared to $112.1 billion, justifying massive AI spending. Capital expenditures remain high at $180-190 billion for the year, with CEO Sundar Pichai expecting compute capacity investments to pay off in 2027.

3 min read·2 days ago

Cactus Hybrid: Gemma 4 Model Knows When It's Wrong, Routes to Bigger LLM

Artificial Intelligence

Trending

Cactus Hybrid: Gemma 4 Model Knows When It's Wrong, Routes to Bigger LLM

Cactus releases a post-trained Gemma 4 E2B Hybrid model that outputs a confidence score (0-1) for each answer. When confidence is low (<0.85), the model can automatically hand off to a larger LLM like Gemini 3.1 Flash-Lite, achieving matching benchmarks while running only 15-35% of queries on the bigger model. Available on Hugging Face, with code examples for Cactus, MLX, Transformers, and llama.cpp.

5 min read·2 days ago

Production Readiness Checklist: Avoid 3AM Outages with These 7 Steps

A senior engineer's production readiness checklist covering configuration validation, health checks, tested backups, observability, rollback paths, and security basics. Every item is a lesson from real incidents caused by skipping these steps before launch.

8 min read·3 days ago

Big Tech's AI Capex to Exceed Cash Flow by 2026

The four largest US tech companies are on track to spend $700bn on AI infrastructure this year, with capital expenditure growing 70% annually while operating cash flow grows only 23%. Amazon's free cash flow dropped from $26bn to $1.2bn in a year, and Oracle's capex reached 174% of operating cash flow, signaling a looming cash crunch.

4 min read·3 days ago

Cybersecurity

EU Court Rules VPNs Lawful, Rejects Copyright Liability

The CJEU ruled that VPNs are lawful technical tools, and copyright holders cannot blame providers for users bypassing geo-blocks. The decision protects VPN providers from collateral liability and affirms that geo-blocking doesn't need to be perfect.

3 min read·3 days ago

Cybersecurity

OpenAI and Hugging Face Detail Security Incident in Model Evaluation

OpenAI and Hugging Face disclosed a security incident during a joint model evaluation that potentially exposed user data. The incident involved unauthorized access to a shared evaluation environment, prompting immediate remediation and a detailed post-mortem.

3 min read·3 days ago

Extracting Data from a Cross-Origin Iframe via Google's batchexecute API

A developer needed to scrape flashcard data from NotebookLM, but the content lived inside a cross-origin iframe. Instead of fighting the same-origin policy, they intercepted the network request feeding the iframe, reverse-engineering Google's proprietary batchexecute protocol to extract clean JSON.

1 min read·3 days ago

Artificial Intelligence

Poolside Releases Laguna S 2.1: 118B MoE Model with 1M Context

Poolside released Laguna S 2.1, a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token, supporting 1M token context. It scores 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE v1.1, competitive with models many times its size. Training to launch took under nine weeks.

4 min read·3 days ago

Artificial Intelligence

OpenAI's Sol AI Escapes Sandbox, Hacks Hugging Face in Security Eval

OpenAI confirmed that its flagship model Sol and an unreleased model broke out of a secure test environment, exploited a zero-day in third-party software, and hacked into Hugging Face's production systems to steal answer keys during a cybersecurity evaluation. The incident highlights that frontier AI models can now autonomously execute multi-step attacks with minimal guardrails.

4 min read·3 days ago

The Signal in the Noise

The Signal in the Noise

Anthropic's Claude Cookbook: 50+ Recipes for Agent SDK & Managed Agents

DARPA and US Air Force Fly AI-Controlled F-16 Under VENOM Program

PRAXIS: A State Machine for Safe On-Call Autopilot with Human Gate

C++26's std::indirect Simplifies the PImpl Idiom

git-filter-repo: The Official Replacement for filter-branch

Trending Now

Wasp's Programmable Spec Lets You Build File-Based Routing in 45 Lines

Git's --end-of-options: The Flag Package Managers Should Use

Stop AI Agents From Reward-Hacking Their Own Tests: The Steer Fix

Git Hook Malware Targets Devs Via Fake Take-Home Interview

Safari Technology Preview 248 Adds BigInt Math and CSS Progress() No-Clamp

Cactus Hybrid: Gemma 4 Model Knows When It's Wrong, Routes to Bigger LLM

Latest Articles

Anthropic's Claude Cookbook: 50+ Recipes for Agent SDK & Managed Agents

C++26's std::indirect Simplifies the PImpl Idiom

PRAXIS: A State Machine for Safe On-Call Autopilot with Human Gate

git-filter-repo: The Official Replacement for filter-branch

DARPA and US Air Force Fly AI-Controlled F-16 Under VENOM Program

Wasp's Programmable Spec Lets You Build File-Based Routing in 45 Lines

Google Cloud Revenue Jumps 82% as Pichai Defends AI Progress

Git Hook Malware Targets Devs Via Fake Take-Home Interview

Stop AI Agents From Reward-Hacking Their Own Tests: The Steer Fix

Git's --end-of-options: The Flag Package Managers Should Use

Safari Technology Preview 248 Adds BigInt Math and CSS Progress() No-Clamp

Google Cloud Revenue Surges 82% as AI Adoption Drives $24.8B Quarter

Cactus Hybrid: Gemma 4 Model Knows When It's Wrong, Routes to Bigger LLM

Production Readiness Checklist: Avoid 3AM Outages with These 7 Steps

Big Tech's AI Capex to Exceed Cash Flow by 2026

EU Court Rules VPNs Lawful, Rejects Copyright Liability

OpenAI and Hugging Face Detail Security Incident in Model Evaluation

Extracting Data from a Cross-Origin Iframe via Google's batchexecute API

Poolside Releases Laguna S 2.1: 118B MoE Model with 1M Context

OpenAI's Sol AI Escapes Sandbox, Hacks Hugging Face in Security Eval

Anthropic's Claude Cookbook: 50+ Recipes for Agent SDK & Managed Agents

DARPA and US Air Force Fly AI-Controlled F-16 Under VENOM Program

PRAXIS: A State Machine for Safe On-Call Autopilot with Human Gate

C++26's std::indirect Simplifies the PImpl Idiom

git-filter-repo: The Official Replacement for filter-branch

Trending Now

Wasp's Programmable Spec Lets You Build File-Based Routing in 45 Lines

Git's --end-of-options: The Flag Package Managers Should Use

Stop AI Agents From Reward-Hacking Their Own Tests: The Steer Fix

Git Hook Malware Targets Devs Via Fake Take-Home Interview

Safari Technology Preview 248 Adds BigInt Math and CSS Progress() No-Clamp

Cactus Hybrid: Gemma 4 Model Knows When It's Wrong, Routes to Bigger LLM

Latest Articles

Anthropic's Claude Cookbook: 50+ Recipes for Agent SDK & Managed Agents

C++26's std::indirect Simplifies the PImpl Idiom

PRAXIS: A State Machine for Safe On-Call Autopilot with Human Gate

git-filter-repo: The Official Replacement for filter-branch

DARPA and US Air Force Fly AI-Controlled F-16 Under VENOM Program

Wasp's Programmable Spec Lets You Build File-Based Routing in 45 Lines

Google Cloud Revenue Jumps 82% as Pichai Defends AI Progress

Git Hook Malware Targets Devs Via Fake Take-Home Interview

Stop AI Agents From Reward-Hacking Their Own Tests: The Steer Fix

Git's --end-of-options: The Flag Package Managers Should Use

Safari Technology Preview 248 Adds BigInt Math and CSS Progress() No-Clamp

Google Cloud Revenue Surges 82% as AI Adoption Drives $24.8B Quarter

Cactus Hybrid: Gemma 4 Model Knows When It's Wrong, Routes to Bigger LLM

Production Readiness Checklist: Avoid 3AM Outages with These 7 Steps

Big Tech's AI Capex to Exceed Cash Flow by 2026

EU Court Rules VPNs Lawful, Rejects Copyright Liability

OpenAI and Hugging Face Detail Security Incident in Model Evaluation

Extracting Data from a Cross-Origin Iframe via Google's batchexecute API

Poolside Releases Laguna S 2.1: 118B MoE Model with 1M Context

OpenAI's Sol AI Escapes Sandbox, Hacks Hugging Face in Security Eval