Seroter's reading list: WebMCP saves tokens vs DOM, Meta courts MongoDB CEO for enterprise AI
rseroter · x · 2026-09-29
Richard Seroter's daily reading list (#876) rounds up notable AI and software engineering pieces:
- WebMCP test: an AI agent can work a web page from the DOM alone, but it costs more time and tokens than using tools exposed via WebMCP
- Antigravity agent skills, part 4: built-in options for subagent-to-subagent messaging
- Meta's enterprise AI platform: Meta announces the effort and recruits MongoDB's CEO to lead it
- Nine unlikely trends shaping software development
- DiffusionGemma on vLLM/Red Hat AI as a Jev-style decision model
- Coherent long-form video generation: "today is the least realistic AI video will ever be"
- Memorystore for Valkey 9.1: 3x QPS and microsecond latency, more than a Redis alternative
- Plus takes on experts managing experts and the apps/agents/aggregation trend
More from coding & agent
- Claude refuses to speed up tests, says 'Running tests will take 35 hours' to respect rate-limit spec — julianharris · 2026-09-29
- Claude Opus 5.5 runs an AI game studio: builders, critics, revisers, verifiers — chrisfirst · 2026-09-29
- 45 parallel modules, ~580 agent runs: engineering details of an AI game studio — chrisfirst · 2026-09-29
- After a week with Claude Sonnet 5.5: 6 tips, from effort settings to surprise bills — every · 2026-09-29
- Re-enable Ultracode in Claude Code's VS Code extension with one settings. line — AdLow1228 · 2026-09-29
- Dave Morin: No Single Super Agent — Every App Will Become an Agent — nbaschez · 2026-09-29