Plausible Reality

AI Is Cheap. Good Ideas Still Aren't.
The useful question is not whether AI saves hours. It is whether it lets teams buy more serious attempts without lowering the bar.
 • Eloi Tay
Your Agent Isn't Tired. It's Drowning in Context
The useful analogy between humans and LLMs is not consciousness. It is that both fall apart when active memory, compression, and management are sloppy.
 • Eloi Tay
Your Org Chart Is Not Your Operating Model
Why healthy software teams keep accountability close to the product, centralize leverage, and design for knowledge resilience
 • Eloi Tay
You Are Probably Rebuilding DSPy Already
Why prompt tables, eval scripts, and model wrappers keep turning into the same architecture.
 • Eloi Tay
The New Senior Engineer Knows What to Trust
In the AI era, the real edge is not writing more code. It is deciding what counts as evidence before the code ships.
 • Eloi Tay
Mythos Is Not Unreleased. It’s Gated.
OpenAI is forcing Anthropic to move faster, but the likeliest move between late May and mid-June is controlled expansion, not a public Mythos launch.
 • Eloi Tay
Even the Handcrafted-Code Purists Are Using Agents
When the engineers most associated with software craft start teaching agentic workflows, the lazy "tech bros vibe coding" dismissal stops working.
 • Eloi Tay
XXX + Claude Code Is Not 99% Cheaper
You can cut the visible token bill hard. You can also quietly swap out the model, the API semantics, and the operating costs that made Claude Code feel…
 • Eloi Tay

March 2026

© 2026 Eloi Tay · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture