Ditto Creates Shared Memory for AI
markjeffrey · x · 2026-07-16
Ditto is described as a "shared memory" for AI: even after switching models, the AI retains the full context without losing historical information.
The author notes using Ditto to hot-swap models from OpenClaw / Opus 4.8 to Hermes + GLM 5.2 seamlessly and instantly.
Quoted content adds details on Ditto's network competition progress:
- The subnet competition is live and running
- Emissions are expected to resume that day
- The top miner scored 0.883 on DittoBench, nearly double the initial internal score
- 94 miners have come online within 24 hours, adding 164 new evaluations
More from coding & agent
- Codex helps build Valdiluce, an open-world game with climbing, gliding and gondolas — Dimillian · 2026-07-22
- HeyGen adds a media-sourcing skill for coding agents with 75k images and 10k tracks — HeyGen · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- LangSmith adds tracing for Pipecat, LiveKit, OpenAI Realtime, and Gemini Live — LangChain · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Annotated transcript of a Claude Code team interview is now available — trq212 · 2026-07-22