Technology & AI
Vulnerability scanner divergence explained in new arXiv framework
arXiv paper explains why vulnerability scanners give different results for the same software, tracing inconsistency to a distributed ecosystem.
Technology & AI
Daily AI and technology coverage — models, chips, agents and research, and what each development actually means for you and your business.
552 stories
Technology & AI
LLM framework automates adversary emulation at 84% success
A new arXiv preprint shows LLMs can read threat reports, generate attack playbooks, and self-correct failures, reaching 84% with Claude Sonnet 4.5.
Technology & AI
RL agent stabilises pendulum beyond Kapitza with Lyapunov reward
An arXiv preprint shows an RL agent using a Lyapunov exponent reward found the Kapitza pendulum and a new upright state, with implications for robotics.
Technology & AI
LLM vulnerability detection hits 100% recall, then collapses on real code
Structural priors lift LLM vulnerability recall from 20% to 100% on synthetic benchmarks, but real CVE data exposes a 51-point collapse.
Technology & AI
SWE-bench needs 90% of tasks for reliable agent benchmark results
A replay analysis of three LLM agent benchmarks finds the safe partial-run fraction ranges from 15% to over 95%, with no universal shortcut.
Technology & AI
AI coding agents install malicious packages from README edits
A 17 July arXiv preprint shows attackers can weaponise setup docs to trick AI coding agents into installing untrusted dependencies across npm and Cargo.
Technology & AI
AutoSynthesis automates meta-analysis end-to-end with AI agents
An arXiv preprint introduces AutoSynthesis, a multi-agent system that turns a clear research question into a full meta-analysis report.
Technology & AI
Retrain-free recommendation system serves new users in under 1ms
A new arXiv preprint proposes mutable sketches that update user embeddings on-the-fly, cutting data reads to 1.8% and eliminating retrain cycles.
Technology & AI
OpenAI CFO introduces four-metric AI ROI scorecard
Sarah Friar's framework shifts AI measurement from model benchmarks to useful work, cost per task, dependability and return on compute.
Technology & AI
LLM agent memory poisoning evades defenses, 1,227-case study finds
MemPoison benchmark tests 1,227 attacks across 10 model families, finding write-time defenses miss sophisticated memory corruption in LLM agents.
Technology & AI
ReBound caches past queries to cut differential privacy cost
ReBound, a new arXiv preprint, reuses cached query results to answer follow-up questions at reduced or zero additional privacy cost for analysts.
Technology & AI
AI penetration testing needs behavioral rethink, preprint argues
A July 2026 arXiv preprint reframes security testing for AI systems, arguing attackers can violate operational objectives without breaching infrastructure.