Goodfire Challenges the Black Box; Agent Safety Tests Challenge Oversight
Thursday, November 12, 2026 · 6 min
Goodfire reports interpretable neuron structure in Qwen3.6-35B-A3B, challenging assumptions about how to inspect models. Research on multi-agent safety tests and proposed reasoning-monitor disclosures probes what oversight can actually establish—and where the evidence remains limited.
Listen
Show notes
Goodfire reports interpretable neuron structure in Qwen3.6-35B-A3B, challenging assumptions about how to inspect models. Research on multi-agent safety tests and proposed reasoning-monitor disclosures probes what oversight can actually establish—and where the evidence remains limited.
In this episode
- Neurons as an Interpretable Basis - Goodfire — Goodfire
“Building on a growing body of literature, our work suggests that neurons are more interpretable than previously assumed. We study the neurons of Qwen3.6-35B-A3B using sparsification methods, attribution tools, and research agents, and find three properties that make neurons…”
- ErosionBench: defences refuse up to 92% of real work — Aivio
“Enterprises are handing consequential work to systems of language-model agents that pass state and messages between each other. A benchmark posted to arXiv on 8 November targets a failure mode those systems create and single-agent testing cannot see: a benign-looking request…”
- Policy paper proposes five chain-of-thought disclosures for AI labs and finds none of the three it audits covers the full set — On The Wire — On The Wire
“An updated version of a paper on chain-of-thought (CoT) monitoring, posted to arXiv on Tuesday 10 November 2026, proposes five indicators that frontier AI developers should disclose so that threats to monitoring a model's written reasoning can be tracked. Its audit of Anthropic,…”