Agent researcher: LLM agents still lack a sense of time, two years on
akbirthko · x · 2026-11-07
Revisiting a two-year-old take: LLM-based agents ought to have a sense of time, but they are not real-time systems. The upside is they can be treated like any other API to build software on; the downside is this likely limits how general they can become. The author notes the problem remains unsolved, arguing the world is severely compute-poor — otherwise everything would run in real time.
More from AGI Musings
- AI Exposes the Economy's Inefficiency: The Real Threat Is Getting Paid for Mediocrity — TinfoilTricorn · 2026-11-07
- basedjensen: recursive self-improvement is already here and bans are unenforceable — basedjensen · 2026-11-07
- Musing: Much of ML's progress may just be rediscovering good discipline — yunta_tsai · 2026-11-07
- Geoffrey Hinton's 47-minute AI masterclass promises to reshape how you think about AI — HeyAmit_ · 2026-11-07
- AI video characters may feel conscious sooner than LLMs, argues viral post — flowersslop · 2026-11-07
- WIRED archive analysis: 60.5% of AI stories use harm framing vs 18.6% in early internet era — emollick · 2026-11-07