AI, three at a time · read · watch · listen

Tag

context-management

3 reads

Meta Engineering 2026-10-23-3

The Thin Orchestrator: How We Made Our AI Agents More Reliable by Giving the Router Less to Do

Meta's orchestrator is 1,300 lines, routes 20+ workflows to 14 subagents and does no domain work; only step 6 of its fixed 7-step protocol involves an LLM. A single agent hit 70-80% success with per-task manual prompts and 10-20% without, and column config prep fell from 3-4 days to under an hour (self-reported). It is the same move as 1Password's, applied to routing: the model gets isolated context to be creative in, and nothing deterministic is left for it to hallucinate.

# tags
multi-agent-orchestrationagent-architectureagent-orchestrationcontext-managemententerprise-ai-reliabilitymetaproduction-readinessharness
◆ entities
Harness-as-moatContext managementMulti-agent orchestrationProduction-readinessAgentic AI viability
→ threads
agent-orchestrationenterprise-ai-reliability
⟷ links
2026-03-13-w32026-04-05-12026-05-01-w32026-03-17-12026-05-01-w22026-03-30-32026-04-09-22026-04-15-12026-04-20-3
permalink
The Atlantic 2026-05-18-1

AI Has Broken Containment

Wong's piece isn't a structural update — every event he cites is recycled public record from the past six months. What's new is that The Atlantic, NYT, Economist, Bloomberg, and Hard Fork have consolidated a unified "AI is no longer compartmentalizable" frame inside 30 days. The Cold War metaphor migration — containment, arms race, geopolitical actors — imports a specific policy menu (export controls, pre-release licensing, technology denial), and Anthropic and OpenAI will IPO into that frame, not the prior permissive one.

# tags
ai-political-economyai-regulationai-regulatory-riskconsensus-migrationnarrative-arbitragemythosdata-centersai-infrastructure-financecircular-financingai-displacementpre-ipothe-atlanticai-geopoliticsagentic-coding-skillharnesscontext-managementskillseval-harnessevalrigpickrigagent-architecturescaffold-engineeringai-engineer-conferenceagentic-ai-viabilityai-coding-toolsmcpai-economicsprompt-engineeringai-vendor-governanceevaluation-infrastructureplatform-strategy
◆ entities
The AtlanticMatteo WongAnthropicOpenAIMythosSusie WilesDonald TrumpCiscoJensen HuangElon Musk
→ threads
AI political economyFrame canonization velocityRegulatory window compressionPre-IPO Anthropic OpenAILocal political risk capex
⟷ links
2026-03-13-w32026-05-03-32026-04-14-22026-03-11-22026-04-03-22026-04-24-w22026-04-15-22026-03-18-32026-04-11-22026-04-11-32026-04-15-12026-04-30-22026-05-05-12026-05-09-32026-05-12-22026-05-14-12026-05-17-12026-05-17-32026-05-17-2
permalink
The Typical Set 2026-05-08-2

The bottleneck was never the code

Brooks 1975: software is the residue of human negotiation. For 50 years, tooling investment kept attention on the residue; agents collapsed the residue cost and exposed the substrate. The bottleneck moves from coders to spec-producers, which is to say management. Every AI productivity claim now needs a denominator that is not engineer-coding speed but spec-to-shipped cycle time. If management bandwidth is the bottleneck, individual agent productivity gains compound at zero, and you have just bought yourself the world's most expensive feature-bloat machine.

# tags
coding-agentsagentic-ai-viabilityharness-as-moatcontext-managementorg-designai-and-human-capacitypilot-to-scaleevaluation-infrastructurejevons-paradoxvibe-codingai-strategyagentic-coding-skillevalrigpickrigturanuadvisorypractitioner-grounding
◆ entities
.txtdottxt-aiCodexFred BrooksGerald WeinbergMichael PolanyiSteve JobsAppleAnthropicIntercomWorkOSCursorBloombergGoogleKarpathy
→ threads
agentic-ai-viabilityharness-as-moatevaluation-infrastructurepilot-to-scaleai-1.0-defensibility
⟷ links
2026-04-17-w22026-04-05-12026-04-07-12026-03-27-w32026-04-07-22026-04-05-22026-04-25-32026-04-15-22026-03-13-12026-04-28-22026-04-22-12026-04-27-32026-04-30-22026-05-02-12026-05-03-32026-05-05-3
permalink