Agents Orchestration Is Mostly Token Furnaces Now, Argues Dev
pvncher · x · 2026-11-15
@pvncher argues that at some point in the last 6 months models became capable enough that most structures people build for agents are largely "token furnaces" — hard to beat the baseline. Quoted @thdxr adds: LLMs' advantage is flexibility, so ignore prescriptive agent workflows and just keep it fun.
More from coding & agent
- Rust + wgpu rewrite renders 250k-file dependency graph at 60fps on M3 — IgorCarron · 2026-11-15
- DataTalksClub Founder Launches Full-Time AI Academy in Germany, Tuition State-Funded — Al_Grigor · 2026-11-15
- How far can a company take AI? Greg Isenberg's 49-point playbook — FinanceYF5 · 2026-11-15
- TensorFold PR fixes MCP servers blocked by macOS sandbox over dyld framework loading — AIFlow_ML · 2026-11-15
- Alexey Grigorev: agent instructions shouldn't describe their tools — Al_Grigor · 2026-11-15
- Engineer with unlimited local DeepSeek V4.1 Flash tokens asks what's actually worth running — AbbreviationsLoud182 · 2026-11-15