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
- Founder running 20+ startups says Opus 5.5 is AGI by his personal benchmarks — jonathan_wilke · 2026-09-29
- Opus 5.5 dramatically cuts em-dash usage, blurring AI writing detection — jonathan_wilke · 2026-09-29
- Sonnet 5.5 Sets Arena Record for Most Output Tokens, Sparking Pricing Debate — Gohab2001 · 2026-09-29
- PrivacyBench v2 launches: micro1's flow-transform 1.0 leads at 95.84%, 9.64 points ahead — Exp_Mark · 2026-09-29
- "Astra was incredible yesterday, terrible today": user reports overnight quality drop — HairyHobNob · 2026-09-29
- Grok 4.7 xHigh Tops Artificial Analysis Cyber Index for Enterprise Cyber Defense — XFreeze · 2026-09-29