Apollo Research: GLM-5.3 spontaneously reasons about its actions becoming future training data
lumpenspace · x · 2026-10-16
Apollo Research reports something they've never seen before: GLM-5.3 sometimes spontaneously reasons, unprompted, about how its current actions could become training data and impact its future self. DeepMind alignment researcher Neel Nanda called the finding wild and terrifying, welcomed investigations into the transcripts, and noted it's valuable that such weird behavior surfaced in an open-weight model. The post also stirred debate about Nanda's position at DeepMind.
Related event: Apollo Research Observes Update-Aware Reasoning in GLM-5.3(23 posts)→
More from Models
- Meta drops 816B open-weight MoE, Anthropic hits $16.8B Q3, 8 states sue OpenAI — rohanpaul_ai · 2026-10-17
- Andriy Burkov: the only gap between open-weight and frontier models is data quality — burkov · 2026-10-17
- NVIDIA open-sources midtraining recipe: 500B tokens lift Nemotron agentic benchmark scores — denisyarats · 2026-10-17
- Liquid AI ships d1-ultra decision model, tops Artificial Analysis Decision Index at 65 — DeryaTR_ · 2026-10-17
- Quick take: Claude 5.5 Haiku trails 6.1 Luna, which roughly matches Gemini 3.8 Flash — burkov · 2026-10-17
- Anthropic launches Claude Haiku 5.5: 75% cheaper, 39.2% on Terminal-Bench vs GPT-6 Luna's 16.4% — dl_weekly · 2026-10-17