GLM Evals Reinforcement Learning Interpretability Agent runtime infrastructure Security

Silico

Automated interpretability and RL experimentation platform

Interpretability-first AI research platform that automates experiments, including causal interpretability replications and reinforcement-learning workflows, to inspect, debug, and shape model behavior.

Recent stories

3 linked stories

workflowPRIMARY2026-09-09

Goodfire publishes probe-based agent-monitoring guide with a reported 99% catch rate in a GLM 5.3 test

Goodfire describes probes that inspect model internals for prohibited intent, reward hacking, and risky tool calls. Goodfire reports that a probe for a GLM 5.3 coding agent caught 99% of prohibited actions in its test.

releasePRIMARY2026-07-14

Goodfire opens Silico private beta for automated interpretability and RL experiments

Goodfire opened a private beta for Silico, which it says can run automated interpretability and RL experiments. Reported examples include a GLM-5.2 J-space replication and a Qwen3-8B RLFR run that reduced hallucinations by 37%.

releasePRIMARY2026-06-11

Goodfire introduces predictive data debugging with R² 0.9 DPO forecasts

Goodfire said its predictive debugging can forecast DPO-driven behavior shifts with R² 0.9 before training and trace them to individual preference pairs. Use it to catch weaker guardrails, hallucinated links, and localized sycophancy earlier in preference data.