Issue Archive

Every issue,
in one place.

Every weekday issue of Inference, from the very beginning. Free to read, forever.

No. 009 Jun 18, 2026

How to read an AI safety paper without a PhD

AI safety research shapes what models can do and what's legal to ship. Most builders skip the papers. Here's a fifteen-minute reading framework that gets you the signal without the academic overhead.

Read issue → 5 MIN
No. 008 Jun 17, 2026

The coordination problem: how multi-agent systems actually fail

Single-agent systems fail in predictable ways. Multi-agent systems fail in the handoffs — handoff drift, conflicting world models, cascading overconfidence. Here's the failure map and the cheapest fix for each mode.

Read issue → 5 MIN
No. 007 Jun 16, 2026

Why agent memory is the next infrastructure battleground

Your agent runs great in a demo. Then a real user hits it across three sessions, references something from last week, and it has no idea what they're talking about. Here's the memory architecture that actually fixes it.

Read issue → 5 MIN
No. 006 Jun 15, 2026

Why everyone's fine-tuning now (and most people shouldn't)

Fine-tuning got cheap enough that it's on every roadmap. Most of those projects are aimed at a problem fine-tuning can't fix. Here's how to tell which kind of problem you actually have.

Read issue → 5 MIN
No. 005 Jun 12, 2026

Open weights just changed the math for startups

Open-weight models from Meta, Mistral, DeepSeek, and Qwen have closed most of the gap with frontier closed models — and that's quietly rewritten the build-vs-buy calculus for almost every AI startup. Here's the new math.

Read issue → 5 MIN
No. 004 Jun 10, 2026

The quiet death of the prompt engineer

Prompt engineering didn't disappear — it got absorbed into a bigger discipline. Here's what actually matters now, and the eval habit that replaces "finding the right wording."

Read issue → 5 MIN
No. 003 Jun 9, 2026

Agents are getting good. Here's what breaks first.

Long-running agents are finally viable in production. They also fail in five predictable ways — context poisoning, tool hallucination, stuck loops, scope creep, and silent failure. Here's the map and the cheapest guardrail for each.

Read issue → 5 MIN
No. 002 Jun 8, 2026

Why your RAG pipeline is probably overbuilt

Long context windows didn't kill retrieval — but they killed most of the reasons teams reach for it first. Here's how to tell which camp you're in, plus a template for fighting the "lost in the middle" effect.

Read issue → 5 MIN
No. 001 Jun 5, 2026

The context window arms race is over — here's who won

Context windows hit 1M+ tokens and most teams are still building like it's 2022. We break down what changes in your stack, what to throw out, and the one architecture decision that actually scales.

Read issue → 5 MIN
Don't miss the next one

Get it in your
inbox every morning.

Free forever. Delivered at 7am. Unsubscribe anytime.

No spam. No paywall. Unsubscribe in one click.