Why CEREBRO kept it

Codex cache-retention change; direct token-cost mechanics

Backlinks

Appeared in 1 briefing

• 2026-10-21

Related

Shares tags: ai/llm-mechanics · cerebro/signal · release-notes

• Day 16/ You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming afx · 2026-10-21
• RT @ClaudeDevs: We keep improving performance across Claude, and you may have noticed it starts responding sooner! Claude Code now gzips the conversation it sends on every turn, so it reaches the modx · 2026-10-17
• Haiku 5.5 is especially good value on tasks under 100,000 tokens, which make up around 90% of requests to our previous Haiku model. https://t.co/Qu8BZlizajx · 2026-10-08
• Claude Haiku 5.5hackernews · 2026-10-08
• Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released. On average, it costs around 75% less to run than Claude Haiku 4.5. https://t.co/jm06cZJfkVx · 2026-10-08
• Discover local models in GitHub Copilot CLIrss · 2026-10-08

Also from x.com

• Some OpenCode users found out their AI keys were stolen when the bill showed up, before the company had even told them. OpenCode makes a coding assistant. Its paid web dashboard, called Console, letx · 2026-10-21
• RT @charliermarsh: We're starting to see some agentic Rust forks (or alternative implementations) focused on iteration speed. More-so than the specific projects, I'm interested in the ideas being expx · 2026-10-21
• We just shipped an updated T3 Code Stable release with over 1,400 changes 🤯 Quick highlight reel of my favorites: - Massive perf wins on desktop and mobile - Add a project to another machine from thx · 2026-10-21
• It's crazy how quick these new capabilities have started to feel normal. Like I vibe coded a Cargo alternative that compiles my Rust apps up to 129x faster and my immediate thought is 'yeah, and?' htx · 2026-10-21
• Day 16/ You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming afx · 2026-10-21
• Devin Fusion with Claude Opus 5.5 (max) and a GPT-6 Luna (high) sidekick scores 68 on the Coding Agent Index, 2 points above Claude Code with Opus 5.5 (max) at 31% lower cost per task @cognition's Dex · 2026-10-21