Does your AI agent need an LLM to decide what to do next?
Say “good morning” to an AI agent, and it might search its long-term memory before saying hello back. Somewhere in
Recent stories from The New Stack.
Say “good morning” to an AI agent, and it might search its long-term memory before saying hello back. Somewhere in

Google is adding computer use to its Gemini app for macOS. The assistant can now work across desktop applications and

Cognition has spent nearly three years developing Devin as an autonomous engineer that takes a ticket and ships a pull
If you’ve spent any time over the past year trying to get AI agents to talk to each other without

Coding agents need backups, too, or at least that’s what IDrive is arguing. Backup and storage service IDrive on Thursday

For AI agents to work together effectively, they need a way to communicate and divvy up tasks — much as

AWS raised prices on EC2 Capacity Blocks, its reserved GPU capacity, by about 15% in January and about 20% in

Deploying containers safely at scale can mean assembling your own system: traffic-splitting logic, alarm evaluation, rollback automation, approval gates. It’s

A marketing site used to have two kinds of visitors: people and search crawlers. Now an agent can build a

Groundcover, the eBPF-based observability startup, has introduced Investigations, giving agents and engineers one place to collaborate on incident response in
An AI coding agent can write a patch in minutes. Ask it whether that patch slows down the API endpoint

Google’s new Gemini 4 Neon resolved 12.8% of the SWE-sweep coding benchmark using the mini-SWE harness, but that score jumped

Microsoft says its Bing search engine now has one billion monthly users. The company says those are humans — not

Last week at KubeCon + CloudNativeCon North America, a major gathering of the open-source and cloud-native communities, many speakers —

Qwen4-Max, made available in preview to Token Plan subscribers on November 11 and generally released on November 16, is quite

OpenAI spent approximately $1.2 million in API costs to generate working exploits for 948 Linux kernel vulnerabilities. At The New

It’s not a revelation to say AI workflows are changing enterprise infrastructure. What gets less attention, though, is how they’re
Building an AI agent that performs an impressive demonstration is one thing. Building one that can reliably process financial transactions,

A customer asks whether they can swap unworn boots for a size 10. The agent replies, in under a second,

At Red Canary, storing large amounts of small data is a big deal. Their Linux Endpoint Detection and Response (EDR)

For two years, the question around AI coding was whether agents could write good code. Developers have largely answered it:

Hugging Face and OpenRouter have announced a partnership that promises to make AI model inference faster and more reliable for

The same AI model can cost up to five times more to run depending on the coding agent harness it’s

OpenAI’s new GPT-6.2 Astra is nearly twice as likely as its predecessor to leave users unaware of problems that prevented

At its Ignite conference in San Francisco on Tuesday, Microsoft announced a number of new AI models, including two new

Microsoft is making its Cobalt 200 virtual machines generally available, with CPU improvements aimed at the sandboxes, tools, and code

Agent swarms are all the rage, as companies set about finding ways to coordinate multiple AI agents to tackle complex

Production traffic shows failures that benchmarks or pre-deployment evaluations can’t fully reveal. It tells you which edge cases matter and
AI agents are testing systems that were originally built for people, and Jonathan Bryce thinks the cloud-native community has a

Google’s Threat Intelligence Group says attackers are using autonomous AI agents to reverse-engineer security patches, generate exploits, and attempt to