Context compaction

Named by 6 kept items in this workspace.

The items that name it 6

TokenMaxxing: How to Get the Most Out of Your AI Models
article2026-10-17
Show HN: Gemini 4 Argon plays StarCraft
article2026-10-16
OpenAI Gave AI Agents Their Own Computers at DevDay 2026. Here's Everything It Announced
article2026-09-29
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
paper2026-09-28
Computation and Data Movement for Inference
article2026-09-21
Long-running agents compress context to stay under the model limit, abandoning many prior blobs whose space is recycled.
santosomar/AI-agents-for-cybersecurity
repo

In every workspace you can read 7

Security

Stolen AI Reasoning Could Help China Build Cheaper Rivals
article2026-10-26It is written here as Context compaction: compressing conversation history, tool calls and workspace state into a summary before the context window overflows (the feature abused by the attack).

AI

TokenMaxxing: How to Get the Most Out of Your AI Models
article2026-10-17
Show HN: Gemini 4 Argon plays StarCraft
article2026-10-16
OpenAI Gave AI Agents Their Own Computers at DevDay 2026. Here's Everything It Announced
article2026-09-29
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
paper2026-09-28
Computation and Data Movement for Inference
article2026-09-21
santosomar/AI-agents-for-cybersecurity
repo

All techniques in this workspace.