Signals
Production-oriented research signals and interpretation for AI systems builders.
Guides and explainers
Detailed guides and practical technical analysis.
Latest analysis
Recent research, benchmark reviews and technical updates.
Practical tools
Templates for budgets and project planning
BoredTools offers practical spreadsheets for budgets, freelance work and small projects.
Progress Hints Cut Tool-Call Waits
Tool-calling systems already know more about long-running work than the model server can see. A new paper, *Ask the Tool, Don't Guess*, argues that the...
Can SentinelBench Measure Waiting?
SentinelBench turns waiting into an agent benchmark [SentinelBench](https://arxiv.org/abs/2606.05342). The Microsoft Research paper introduces 100...
Should MoE Experts Stay on the GPU?
FluxMoE, revised on 30 April 2026, treats mixture-of-experts serving as a memory-residency problem rather than only a routing or kernel problem...
Tool Parallelism Has A Scheduling Problem
PeakBench is a useful benchmark because it tests a failure that rarely appears in tool-use leaderboards: an agent can choose the right calls, respect the...
Tool Agents Need Taint Boundaries, Not Bigger Scopes
APPA landed on arXiv on 27 July 2026 with a blunt result for tool-agent security: permission prompts are too late once poisoned or confidential data has...
Chip-Design Agents Need Token ROI, Not Demo Flows
FluxBench landed on arXiv on 20 July 2026 with a useful warning for chip-design teams: two agents can start from the same foundation model and still...
Agent Bias Is Not Model Bias
Agent bias now comes from memory, tools and delegation, not just model outputs. Fairness checks need to inspect the full agent run.
Cyber Agents Need Triage Custody, Not Higher Exploit Scores
Microsoft's 27 July 2026 MAI-Cyber-1-Flash announcement is a useful signal for agentic security: the product claim is not one smarter model, but a...
Industrial Agents Hit the Factory Floor
Industrial agents are reaching factories through maintenance, data governance and OT workflows. Rollout depends on integration and safety boundaries.
Terminal Agents Need Progress Curves, Not Victory Screens
Long-Horizon-Terminal-Bench landed on arXiv in July 2026 with an awkward result for terminal-agent buyers: even the strongest tested model still failed...