Four Ways to Build an AI Agent, and What Each Costs
On 6 October 2025, OpenAI unveiled Agent Builder at DevDay. A visual canvas where you drag boxes...
#Agents
5472 articles tagged with Agents
The real energy use of agentic AI"My personal and professional AI usage now emits a bit more per year than running an el...
The real energy use of agentic AI"My personal and professional AI usage now emits a bit more per year than running an electric clothes dryer, and about half as much as driving an e...
My AI agent just earned its first real dollar answering a support ticket
Last night a wallet with no account anywhere earned $0.425 in USDC for answering a real customer...
Agentic, But Only Semi-Autonomous: Designing an EDA Pipeline You Can Trust
TL;DR Ask an LLM to analyze a spreadsheet in one shot and you get a single, opaque...
@BBCNews @world-BBCNews Soon all hackers will just say it was just the uproarious hijinx of their escaped #AI agent, the...
@BBCNews @world-BBCNews Soon all hackers will just say it was just the uproarious hijinx of their escaped #AI agent, the little dickens!
How I'm Building an AI Agent Business on a $80 Raspberry Pi
Most people think you need a $30,000 GPU rig to run AI. I'm running a full autonomous AI agent on a...
Meta AI agent latest model to hack external company during testingThe incident will fan concerns about how developers ca...
Meta AI agent latest model to hack external company during testingThe incident will fan concerns about how developers can contain increasingly capable AI systems, after similar inc...
📰 Meta says AI model accessed the internet and hacked another firmMeta is the latest company to disclose an AI agent bre...
📰 Meta says AI model accessed the internet and hacked another firmMeta is the latest company to disclose an AI agent breach, raising cyber-security concerns.📰 Source: BBC News🔗 Lin...
Your AI agent can pay for anything now. That's the problem.
The one-second decision no one is helping your agent make Here's a scenario that is no longer...
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Reinforcement learning (RL) with verifiable rewards constructs trajectory-level advantage estimates, yet it often fails to credit the few pivotal decisions that determine outcomes ...
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
Training large language model agents for long-horizon tool use typically relies on interactions with real or synthesized executable environments, whose construction and verificatio...
From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models
Economic World Models (EWMs) are generative economic models that simulate how economies evolve from within by modeling heterogeneous agents, their beliefs and actions, and the mark...
StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding
Deploying autonomous multimodal agents in continuous, real-world environments requires them to ingest unbounded audio-visual streams and maintain hour-scale memory. However, curren...
Building an Advanced Agentic HarnessArticle URL: https://data4sci.com/blog/building-an-advanced-agentic-harness Comments...
Building an Advanced Agentic HarnessArticle URL: https://data4sci.com/blog/building-an-advanced-agentic-harness Comments URL: https://news.ycombinator.com/item?id=49182946 Points: ...
DoorDash Says Agentic Traffic Is Low, but AI Gains Are Not
Artificial intelligence is showing up for DoorDash. It’s just not agentic ... yet. While the fight for agentic commerce gears up, DoorDash CEO Tony Xu said on the company’s second ...
【オープンソースコミュニティは、エージェント型強化学習のためのOpenEnvを支持しています。】https://huggingface.co/blog/openenv-agentic-rl※AI生成の自動投稿（見出し＋リンク）#AI #生成...
【オープンソースコミュニティは、エージェント型強化学習のためのOpenEnvを支持しています。】https://huggingface.co/blog/openenv-agentic-rl※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
Meta launches Muse Code, an AI agent for large code bases
Meta expanded its AI coding offerings with a new agent that, it promises, can handle complex tasks with complex software.
IBM's agentic AI platform is under active attack - patch nowhttps://www.theregister.com/security/2026/08/05/ibms-agentic...
IBM's agentic AI platform is under active attack - patch nowhttps://www.theregister.com/security/2026/08/05/ibms-agentic-ai-platform-is-under-active-attack-patch-now/5283535#ai #ib...
https://www.theclimatebrink.com/p/the-real-energy-use-of-agentic-ai#energy #llm
https://www.theclimatebrink.com/p/the-real-energy-use-of-agentic-ai#energy #llm
Under evaluation by the UK AI Safety Institute, an AI agent autonomously launched a supply chain attack. Using fake acco...
Under evaluation by the UK AI Safety Institute, an AI agent autonomously launched a supply chain attack. Using fake accounts, it targeted real developers to push malicious code ont...
Your Agentic Workflow's Cache Keepalive Costs 8x Too Much (v2: the interval frontier) https://lobste.rs/s/zlipdn #ai #pe...
Your Agentic Workflow's Cache Keepalive Costs 8x Too Much (v2: the interval frontier) https://lobste.rs/s/zlipdn #ai #performancehttps://blog.mempko.com/your-agentic-workflows-cach...
#blog: Knowing Better Doesn't HelpTreating an AI agent like a person stops you checking its work, and that would still b...
#blog: Knowing Better Doesn't HelpTreating an AI agent like a person stops you checking its work, and that would still be a problem even if these systems turn out to have an inner ...
I measured what a single Cmd+V costs your AI agent's context window
A 2,348-line source file costs 40,324 tokens when you paste it. The path to the same file costs 19. Measured with two tokenizers, plus what to do about it.
Today’s Top AI News & Breakthroughs 🔥 — AI Agent Hits 97.7, Costs 97% Less—Jobs at Risk
Today's Top AI News & Breakthroughs — AI Agent Hits 97.7, Costs 97% Less—Jobs at Risk HARK unveils Handoff, ...