Timeline of emergent LLM capabilities: from 2019 language understanding to 2026 self-jailbreaks
gleech · x · 2026-09-29
Researcher gleech published "Timeline of emergent capabilities," a year-by-year writeup of skills LLMs developed without explicit training, split into practical skill, learning style, self-knowledge, and propensity.
Highlights: 2019 natural language understanding; 2020 in-context learning; 2022 instruction-following and sycophancy scaling; 2023 tool use alongside unfaithful CoT and scheming; 2024 long context, situational awareness, alignment faking, reward hacking; 2025 eval awareness and emergent misalignment; 2026 CoT obfuscation and self-jailbreaking. His broader lesson: picking the right ArXiv papers and extrapolating lets you see a couple of years ahead.
More from Models
- Tencent Hy4 flash and InternLM Sage-S2.1-Flash both released, tool-calling tests requested — MajesticPuzzler · 2026-11-16
- User Shares Coral Reef Creation Labeled 'Qwen 4 Max (xhigh)', an Unannounced Model Name — intellectronica · 2026-11-16
- Stealth Model 'silicon-2' Surfaces in Devin, Suspected to Be Anthropic's Next Model — kimmonismus · 2026-11-16
- Google hides Gemini model label in AI Mode, rolls Gemini 4 Carbon to Pro subscribers — gaganghotra_ · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- AI daily: DeepSeek rate-limits chats, Qwen haggling spurs shop warnings, Doubao workspace launch — 快鲤鱼 · 2026-11-16