autonomous-vehicle-technology-and-safety

We have all hit the "monolithic LLM wall." You design an incredibly capable AI agent, arm it with a suite of tools, and give it a complex, multi-step task—like writing a comprehensive technical paper complete with data analysis, web research, and code verification. At first, it works beautifully. But as the steps accumulate, the context window fills up. The agent begins to experience "attention d…

AI Agents: The Future of Autonomous Intelligence What is an AI Agent? An AI Agent is a system that perceives its environment, makes decisions, and takes actions to reach a goal with minimal human involvement. A chatbot answers questions. An AI Agent goes further. It can: Search the web for up-to-date information Write and run code Read and write files Call external APIs Plan tasks across multiple…

I built a fully autonomous AI agent that costs $0/month to run. Here is exactly how. The Problem: API Bills Add Up When you build an AI agent, the first thing you reach for is an API: OpenAI, DeepSeek, Groq. They work great — until you check the bill. Even at $0.14/million tokens, a moderately active agent burns through $30-50/month. That is a GPU you will never save up for. The second problem: m…

TL;DR Same task, same infrastructure, different harness: cost went from $3.41 to $0.03. Zero model changes. Prompt caching on the inner browser loop (~120 lines of wrapper code): −29% cost. The 8K of repeated system prompt + tools was being billed at full price 59× per run. Convergence rules in the prompt (three sentences): −54% cost on the desktop path, −75% wall time. The default behavior acros…

We have all been there. You spend hours meticulously crafting the perfect system prompt or tool description for your AI agent. It performs beautifully in your initial tests. But a week later, production data throws a curveball. The team's coding standards shift, edge cases emerge, or the underlying LLM updates, and suddenly your agent's performance degrades. To fix it, you have to manually inspec…

Hey HN, Guanming and Bill here from General Instinct ( https://general-instinct.com/). After years of working in robotics, we kept running into the same problem: the best models never fit the hardware we actually had available. The models that performed best were usually designed around datacenter assumptions: large GPUs, lots of memory bandwidth, and reliable network access. But most physical sy…

Startups are looking to install smaller, quieter AI data software in people’s houses

Every AI agent ships with the same bottleneck: it can only reason over what it can reach. MCP servers dissolve that boundary. They expose tools, resources, and prompts to any compliant client over a JSON-RPC wire format so lean you can implement it in an afternoon. Yet most developers grab a framework, copy a template, and ship something they can barely debug. Forge starts differently. You will b…

For Yu Wang, Ph.D., engineering has always been about more than technology. It’s about people. Long before receiving one of the nation’s most prestigious honors for early-career faculty, the National Science Foundation CAREER Award, Wang was fascinated by a simple question: How can we teach autonomous systems to be safer, more reliable, and more beneficial […]

Imagine deploying an autonomous AI agent to handle your production database migrations, customer support, or code reviews. On day one, it performs beautifully. On day two, it encounters a novel edge case, misinterprets its instructions, and fails. In a traditional software engineering workflow, this failure triggers a frantic manual patch. An engineer opens a prompt file, manually rewrites the in…

SOUTHFIELD, Mich.—The Lawrence Technological University Self-Drive 2026 team “rACTor” from the university’s Department of Mathematics and Computer Science won first place in the 33rd annual Intelligent Ground Vehicle Competition’s Self-Drive Challenge, hosted May 29-June 1 on the campus of Oakland University. This year, 24 college teams registered in two performance challenges—Self-Drive for auto…

For most of AI’s history, humans drove every step in its development cycle. But at Anthropic, we are delegating a growing share of AI development to AI systems themselves, which is speeding up our work. Taken far enough, and given enough compute, that trend points to an AI system capable of fully autonomously designing and developing its own successor. This is called recursive self-improvement. W…

MODUS and IRON WAVE aim to help military forces counter drone threats and deploy robotic systems ahead of frontline troop Ondas Holdings has unveiled two new autonomous defense systems designed to address some of the most significant challenges facing modern military forces: the rapid growth of drone threats and the increasing use of robotic systems […] The post Ondas Unveils New Autonomous Count…

SpaceX is seeking to raise $75 billion in an initial public offering that would be the biggest of all time, as Elon Musk’s rocket, satellite and artificial intelligence company targets a historic debut that could clear a path for more mega-listings.

Proposed legislation would require national security review of certain foreign-made humanoid and quadruped robots A bipartisan group of lawmakers has introduced legislation that would apply a familiar national security review process to humanoid and quadruped robots, signaling a broader U.S. approach to evaluating connected autonomous systems. The Guarding the U.S. against Adversarial Robotics Do…

It wasn’t that long ago that the state of the art in AI was generating you an image that sort of looked like the thing you’d asked for. In the interceding years, we’ve seen a Cambrian explosion of capabilities, with AI that can now generate flawless text, run mission-critical enterprise workflows, or orchestrate agents to run entire apps autonomously. But even with all these advances, the ways we…

Hurricane season is expected to be milder than usual this year. But that's not stopping cell phone companies from pulling out all the stops.

Stop Blocking Virtual Threads: Building Asynchronous Human-in-the-Loop AI Agents with Spring AI In 2026, letting autonomous AI agents execute high-risk enterprise tools without human oversight is a production liability, but blocking platform threads—or even Project Loom’s virtual threads—for hours waiting for a manager's Slack approval is absolute architectural malpractice. We must transition fro…

Abstract The growing deployment of vehicles equipped with driver assistance and automated driving systems presents new challenges for crash record classification, as existing police-reported databases vary considerably in the completeness and consistency of automation-level metadata. This study benchmarks five tabular machine learning and deep learning models: random forest, XGBoost, MambaAttenti…