AsideAI cuts memory/CPU use 60-93% and tokens 7-14x in latest update
garrytan · x · 2026-09-29
Garry Tan boosted a batch of updates to the coding assistant @AsideAI: its compaction and "dreaming" mechanisms now use 7-14x fewer tokens and 60-93% less memory/CPU, stuck-task bugs while waiting on subagents are fixed, agents no longer steal focus, /feedback auto-fixes are live, and tab naming has shipped. Upcoming: a faster, more token-efficient harness, custom keyboard shortcuts, and per-profile background colors.
Related event: AsideAI Cuts Token Consumption Up to 14x with Compaction and Dreaming(2 posts)→
More from coding & agent
- InstaCloud raises $8M seed for agent-native serverless cloud that deploys itself — Shruti_0810 · 2026-09-29
- Routing with small models is 200x faster and 400x cheaper than LLMs, reshaping AI software architecture — Pavan_Belagatti · 2026-09-29
- SRE copilot built on Hindsight memory stops agents from repeating past incidents — sathvik1233 · 2026-09-29
- VeilMind prototype isolates private AI memories while sharing generalized lessons — Logical_Leading8882 · 2026-09-29
- Open-source Manus-style skill recreates CellMotion animations, fully editable — yihui_indie · 2026-09-29
- Building a customer-support agent with persistent memory using Hindsight — Harani_19 · 2026-09-29