Oaica Researchhttps://research.oaica.com/2026-10-04T00:00:00ZOaica ResearchAI Safety Evaluation in a Regional Language: A Case Study with a Fine-Tuned Malay Model and an Indonesian Cross-Language Probehttps://research.oaica.com/2026/10/regional-language-llm-safety-malay-indonesian/2026-10-04T00:00:00Z2026-10-02T00:00:00ZOne changed prediction can move a Malay LLM safety subtask by up to 9 points. A study of the SEA-HELM Malay safety track, an Indonesian cross-language probe, and a checklist for any language.Malay AI Safety Evaluation: A Case Study with Oaica’s Fine-Tuned 35B-A3B Model, and an Indonesian Cross-Language Probehttps://research.oaica.com/2026/10/malay-llm-safety-score/2026-10-04T00:00:00Z2026-10-01T00:00:00ZHow far a Malay AI safety score can be trusted. One changed prediction can move a Malay LLM safety subtask by up to 9 points. What the SEA-HELM Malay safety benchmark can and cannot resolve, with an Indonesian cross-language probe, by Oaica.Malay AI Safety Scores Measure Less Than You Thinkhttps://research.oaica.com/2026/10/malay-ai-safety-brief/2026-10-04T00:00:00Z2026-10-01T00:00:00ZOaica, a safety-focused AI company: one changed answer can move a Malay AI safety sub-score by up to 9 points. On-premises Malay AI and safety audits.Oaica 35B-A3B Malay v1.0 260923 model family noteshttps://research.oaica.com/2026/10/malay-model-family-notes/2026-10-04T00:00:00Z2026-10-02T00:00:00ZThe Oaica 35B-A3B Malay model, its safety-tuned variant and two experimental specialists: what we measured, the trade we report, and what the copy may say.A Malay AI You Can Run Yourselfhttps://research.oaica.com/2026/10/malay-on-premises-ai/2026-10-04T00:00:00Z2026-10-02T00:00:00ZOaica's 35B-A3B Malay model runs on your own hardware, from small GPUs to datacenter servers, with our .oqm format and a statement of what we do not claim.Measuring the Measure: Evidence and Limitshttps://research.oaica.com/2026/10/evaluation-supplement/2026-10-04T00:00:00Z2026-10-04T00:00:00ZText-free outcome counts, recomputation code and provenance limits for our Malay LLM safety case study, stating what the published evidence can and cannot establish.