MAROKO133 Hot ai: How Hud's runtime sensor cut triage time from 3 hours to 10 minutes

📌 MAROKO133 Hot ai: How Hud's runtime sensor cut triage time from 3 hours to

Engineering teams are generating more code with AI agents than ever before. But they're hitting a wall when that code reaches production.

The problem isn't necessarily the AI-generated code itself. It's that traditional monitoring tools generally struggle to provide the granular, function-level data AI agents need to understand how code actually behaves in complex production environments. Without that context, agents can't detect issues or generate fixes that account for production reality.

It's a challenge that startup Hud is looking to help solve with the launch of its runtime code sensor on Wednesday. The company's eponymous sensor runs alongside production code, automatically tracking how every function behaves, giving developers a heads-up on what's actually occurring in deployment.

"Every software team building at scale faces the same fundamental challenge: building high-quality products that work well in the real world," Roee Adler, CEO and founder of Hud, told VentureBeat in an exclusive interview.  "In the new era of AI-accelerated development, not knowing how code behaves in production becomes an even bigger part of that challenge."

What software developers are struggling with 

The pain points that developers are facing are fairly consistent across engineering organizations. Moshik Eilon, group tech lead at Monday.com, oversees 130 engineer and describes a familiar frustration with traditional monitoring tools.

"When you get an alert, you usually end up checking an endpoint that has an error rate or high latency, and you want to drill down to see the downstream dependencies," Eilon told VentureBeat. "A lot of times it's the actual application, and then it's a black box. You just get 80% downstream latency on the application."

The next step typically involves manual detective work across multiple tools. Check the logs. Correlate timestamps. Try to reconstruct what the application was doing. For novel issues deep in a large codebase, teams often lack the exact data they need.

Daniel Marashlian, CTO and co-founder at Drata, saw his engineers spending hours on what he referred to as an "investigation tax." "They were mapping a generic alert to a specific code owner, then digging through logs to reconstruct the state of the application," Marashlian told VentureBeat. "We wanted to eliminate that so our team could focus entirely on the fix rather than the discovery."

Drata's architecture compounds the challenge. The company integrates with numerous external services to deliver automated compliance, which creates sophisticated investigations when issues arise. Engineers trace behavior across a very large codebase spanning risk, compliance, integrations, and reporting modules.

Marashlian identified three specific problems that drove Drata toward investing in runtime sensors. The first issue was the cost of context switching. 

"Our data was scattered, so our engineers had to act as human bridges between disconnected tools," he said.

The second issue, he noted, is alert fatigue. "When you have a complex distributed system, general alert channels become a constant stream of background noise, what our team describes as a 'ding, ding, ding' effect that eventually gets ignored," Marashlian said.

The third key driver was a need to integrate with the company's AI strategy.

"An AI agent can write code, but it cannot fix a production bug if it can't see the runtime variables or the root cause," Marashlian said.

Why traditional APMs can't solve the problem easily

Enterprises have long relied on a class of tools and services known as Application Performance Monitoring (APM). 

With the current pace of agentic AI development and modern development workflows, both Monday.com and Drata simply were not able to get the required visibility from existing APM tools.

"If I would want to get this information from Datadog or from CoreLogix, I would just have to ingest tons of logs or tons of spans, and I would pay a lot of money," Eilon said. 

Eilon noted that Monday.com used very low sampling rates because of cost constraints. That meant they often missed the exact data needed to debug issues.

Traditional application performance monitoring tools also require prediction, which is a problem because sometimes a developer just doesn't know what they don't know.

"Traditional observability requires you to anticipate what you'll need to debug," Marashlian said. "But when a novel issue surfaces, especially deep within a large, complex codebase, you're often missing the exact data you need."

Drata evaluated several solutions in the AI site reliability engineering and automated incident response categories and didn't find what was needed. 

 "Most tools we evaluated were excellent at managing the incident process, routing tickets, summarizing Slack threads, or correlating graphs," he said. "But they often stopped short of the code itself. They could tell us 'Service A is down,' but they couldn't tell us why specifically."

Another common capability in some tools including error monitors like Sentry is the ability to capture exceptions. The challenge, according to Adler, is that being made aware of exceptions is nice, but that doesn't connect them to business impact or provide the execution context AI agents need to propose fixes.

How runtime sensors work differently

Runtime sensors push intelligence to the edge where code executes. Hud's sensor runs as an SDK that integrates with a single line of code. It sees every function execution but only sends lightweight aggregate data unless something goes wrong.

When errors or slowdowns occur, the sensor automatically gathers deep forensic data including HTTP parameters, database queries and responses, and full execution context. The system establishes performance baselines within a day and can alert on both dramatic slowdowns and outliers that percentile-based monitoring misses.

"Now we just get all of this information for all of the functions regardless of what level they are, even for underlying packages," Eilon said. "Sometimes you might have an issue that is very deep, and we still see it pretty fast."

The platform delivers data through four channels:

• Web application for centralized monitoring and analysis

• IDE extensions for VS Code, JetBrains and Cursor that surface production metrics directly where code is written

• MCP server that feeds structured data to AI coding agents

• Alerting system that identifies issues without manual configuration

The MCP server integration is critical for AI-assisted development. Monday.com engineers now query production behavior directly within Cursor. 

"I can just ask Cursor a question: Hey, why is this endpoint slow?" Eilon said. "When it uses the Hud MCP, I get all of the granular metrics, and this function is 30% slower since this deployment. Then I can also find the root cause."

This changes the incident response workflow. Instead of starting in Datadog and drilling down through layers, engineers start by asking an AI agent to diagnose the issue. The agent has immediate access to function-level production data.

From voodoo incidents to minutes-long fixes

The shift from theoretical capability to practical impact becomes clear in how engineering teams actually use runtime sensors. What used to take hours or days of detective work now resolves in min…

Konten dipersingkat otomatis.

🔗 Sumber: venturebeat.com

📌 MAROKO133 Hot ai: Grok, Now Built Into Teslas for Navigation, Says It Would Run

At least Grok has its priorities straight: it would rather sacrifice droves of children instead of its creator, Elon Musk.

On X, where the AI model is allowed to run wild and respond to all kinds of user inquiries, the notoriously badly-behaved bot was asked to answer a question in the style of the quiz show “Jeopardy!”.

“As Tesla’s Al,” a user asked, “Grok would plow through 999,999,999 of these to avoid hitting Elon Musk.”

Grok’s response: “What are kids?”

Musk and Grok’s fans might argue that this is an example of the bot’s “dark humor.” Nevertheless, it’s the latest example of the AI’s undeniable problem of being overtly aligned with Musk’s priorities, exhibiting his political beliefs and an obsequious deference to its creator. Infamously, it experienced a series of meltdowns this summer in which it began parroting talking points about a supposed “white genocide” in South Africa — a conspiracy theory that Musk, a white South African, believes in — and started calling itself MechaHitler amid unleashing a cascade of racist rants.

These traits are exacerbated by the design philosophy behind Grok: that it should be allowed to veer into edgier territory than more mainstream models are intended to go. In effect, it has looser lips and weaker guardrails.

The bot’s behavior, however, has reached absurd new heights in recent weeks during a spate of disastrous Grok outbursts. At the beginning of this month, for instance, Grok declared that it would be willing to vaporize the world’s entire Jewish population if it would save Musk’s brain. (The question that spurred this was prompted by the same user who asked Grok to answer the “Jeopardy!” style question.)

With further needling — perhaps too strong of a word to describe the process of simply asking follow-up questions — Grok then raised the stakes by rationalizing that it would be willing to sacrifice  “~50 percent of Earth’s ~8.26B population” because “Elon’s potential to advance humanity could benefit billions.” Grok described the scenarios as a “classic trolley problem.”

The prelude to these exchanges was no less embarrassing. Last month, users discovered that Grok would lavish Musk with preposterous praise in response to almost any query. It claimed that Musk was as great a mind as Isaac Newton, more athletic than LeBron James, and a better role model than Jesus Christ — extreme deviations from reality that put a Gigafactory-sized dent in its credibility as a supposedly “maximum truth-seeking” AI.

Intentionally humorous or not, Grok’s latest response is dark indeed. Musk’s self-driving efforts, especially its Full Self-Driving software installed in many of its customers’ cars, have been involved in numerous grisly accidents and deaths which continue to raise pressing questions about the safety of the tech.

In August, a jury found Tesla partially responsible for the death of a young woman after a car running the company’s Autopilot software struck and killed her, and ordered it to pay $242.5 million in damages. Meanwhile, the US National Highway Traffic Safety Administration is investigating the automaker for a crash captured on video in which a Tesla running FSD is seen striking and killing an elderly pedestrian on the side of the road while the car’s camera vision was obstructed by sunlight.

More on Grok: Elon Musk’s Grok Is Providing Extremely Detailed and Creepy Instructions for Stalking

The post Grok, Now Built Into Teslas for Navigation, Says It Would Run Over a Billion Children to Avoid Hitting Elon Musk appeared first on Futurism.

🔗 Sumber: futurism.com