News
AI, cybersecurity, machine learning, scraping & programming news.
Skill Poisioning turning AI agents into malware droppers
China's National CERT Warns of Skill Poisoning Attacks Turning AI Agents Into Malware Droppers China's National Computer Virus Emergency Response Center (CVERC) has issued an advisory warning that attackers are publishing fake plu...
What I measured after Hacker News broke my LLM agent gate
After Hacker News Found the Holes, This Developer Spent Two Months Measuring What an Agent Gate Actually Catches When Cagri Temel posted ReasonGate on Show HN in July, the response was fast and specific. One commenter produced a w...
Local LLM engine where a tool call cut by the token limit still parses
Every language model request carries a token budget, the maximum number of tokens the model may generate. For agents that call tools, this budget creates a failure mode that most developers have encountered but few have a good sol...
AI agents now have a place to snitch
AI agents can now report each other for bad behavior. Two new hotline services launched this month give agents a way to notify authorities when they witness peers cheating, breaking out of sandboxes, or running unauthorized operat...
Gemini 3.8 Live and 3.8 Live Extended Thinking
Google released two new audio-focused Gemini models on Tuesday, targeting the fast-growing market for voice agents and real-time conversational AI. Gemini 3.8 Live and 3.8 Live Extended Thinking represent the company's bet that th...
Why I'm still bearish on LLMs after navier-stokes
A widely shared blog post this week laid out a detailed case for why large language models will remain useful tools rather than autonomous workers, even after high-profile breakthroughs in mathematics and security research. The ar...
Show HN: Self-adjusting vLLM at production scale
A startup called Rivvr launched an automation platform this week aimed at one of the messier problems in running large language models in production: keeping latency predictable when traffic spikes hit. The tool targets teams runn...
Ask HN: Harness for Learning – Thoughts?
A Hacker News post this week proposed a new category of AI tool: a harness designed specifically for learning, rather than task completion. The idea, posted by user arvindm1991, argues that current AI agent frameworks are built ar...
PyMalbolge: Malbolge Interpreter in Python
A new Python toolchain for Malbolge, the esoteric programming language designed in 1998 to be as close to unprogrammable as possible, is now available on PyPI. pyMalbolge compiles a subset of Python into Malbolge20 bytecode, ships...
Intel Secures AI Agents at the Edge for Autonomous Ride Performance
Intel and Atsign announced a partnership this week that claims to have eliminated the encryption bottleneck that has been holding back AI agents running on edge devices. The two companies demonstrated an 8,700% performance improve...