Seroter's reading list: Gemini Decisions API, agent memory components, enterprise AI adoption
rseroter · x · 2026-11-12
Richard Seroter's Daily Reading List #908 curates several notable pieces:
- Gemini Decisions API: a new "decision model"—send multimodal inputs with independent questions, get back probabilities and calibrated confidence scores
- Components of agent memory: offline compute ("dreaming") on session transcripts lets agents consolidate experiences into structured notes and catch errors
- Mintlify's new CLI command gives coding agents better instructions, greatly reducing hallucinations
- The future of software engineering is boring: a take on keeping humans learning rather than becoming "meat proxies"
- Enterprise AI modernization survey: companies trapped between legacy software investments and AI urgency
- Anthropic and OpenAI coming for the dev workflow: don't pick fundamental infrastructure based on this month's favorite model
- How Salesforce scaled engineering AI adoption without stifling innovation—a rare big-shop experience report
More from coding & agent
- Agent burns through 5x Max plan's 5-hour limit in 17 minutes by launching 30 parallel researchers — teortaxesTex · 2026-11-12
- Fable Ultracode burns a 5-hour Max limit in 17 minutes by spawning 30 parallel researchers — teortaxesTex · 2026-11-12
- vLLM team open-sources OpenDirector, an agent-driven AI video creation workflow — vllm_project · 2026-11-12
- Leak: xAI Working on a Selection Box for Grok Bot to Comment on Files — nima_owji · 2026-11-12
- Coding Agent Tooling Layers: One Agent vs Many, Personal vs Org-Wide — jiayuan_jy · 2026-11-12
- MobAI: Rotate Driver/Navigator Roles in AI Group Work to Boost Team Autonomy — JoeJustice · 2026-11-12