CONTEXT JAMMING

Field notes from inside the context window.

Stupid LLM Tricks™
Context Jamming  /  Vol. 26

Context Jamming · ACRA Insight LLC

Dispatches

Polemics and long-form essays on cross-model orchestration, AI safety, and the economics of the new cognitive stack.

Issue №005·Meta × Playbook · The CMO’s Guide·11 min

Production Collapsed. Now What?

Claude Design launched April 17, 2026. A live analyst read for CMOs on what it commoditizes, what survives, and why cross-model orchestration is the durable competitive advantage for brands in 2026.

Bret Kerr  ·  19 April 2026Read

Issue №004·Meta · The Determinism Test · Live·14 min

Two Labs. One Prompt. Different Architectures, Different Answers.

Gemini 3.1 Pro and Claude Opus 4.7 were handed the same prompt on AI interpretability. Gemini produced a 43-source synthesis in taxonomic voice. Claude spent 48 minutes, cited 2,501 sources, and named the Architectural Determinism thesis by name. A live, side-by-side test of whether model architecture determines the shape of the answer.

Bret Kerr  ·  18 April 2026Read

Issue №003·Playbook · Generative Engine Optimization·8 min

For the Weights, Not the Algorithm.

Five moves that matter for AI crawlers — most of them free, most of them uncrowded, all of them shippable this weekend. Plus a forecast: LLM recommendations are going to eat organic search alive inside 24 months, and the agencies that see it are already repositioning.

Bret Kerr  ·  18 April 2026Read

Issue №002·Strategic Briefing · The C-Suite Bifurcation·14 min

The Architect or the Casualty.

A board-level briefing on the existential repositioning of the CMO role, 2026–2027. Two archetypes will still be called 'CMO' in 2027. Only one will still be holding the title in 2028.

Bret Kerr  ·  17 April 2026Read

Issue №001·Polemic · The Double Standard·9 min

Vibe Coding Good. Vibe Writing Bad?

Silicon Valley will lionize a founder who ships a production app he barely understands — then call a writer a fraud for using the same tools to think. The double standard isn't about craft. It's about which priesthood still believes in its own robes.

Bret Kerr  ·  17 April 2026Read

Context Jamming is a dispatch from ACRA Insight LLC

Subscribe at contextjamming.substack.com

§ · Invoice No. 001 · The Build Ledger

The Ledger.

Filed · contextjamming.com

What a conservative mid-market digital agency would have quoted for the same scope, itemized against what this site actually cost. Agency numbers are the floor — not the premium brand-studio tier.

TIME

12 weeks

2 days

~42× faster

COST

~$150,000

~$300

~500× cheaper

TEAM

5-person agency

1 human + 3 models

Same deliverable

§ Itemized — what a mid-market agency SOW would have billed

Discovery · brand positioning · workshops40–80 hr$10,000
Design system · Figma tokens · 3 rounds60–120 hr$18,000
Wavesurfer audio carousel · single-track context60–100 hr$16,000
Dual lightbox systems · focus trap · keyboard30–50 hr$8,000
LLM product flows · streaming · state machine80–160 hr$26,000
Stripe · checkout · webhooks · env hardening40–80 hr$10,000
Editorial routes · 6 sub-pages · templates60–100 hr$14,000
Accessibility pass · aria · reduced-motion40–80 hr$10,000
QA · cross-browser · mobile matrix60–100 hr$14,000
Cross-publication rebrand · masthead + IA · 2026-04-2820–40 hr$6,000
Subtotal~700 hr$126,000
Project management · 18% overhead—$24,000
Agency total — conservative floor~700 hr~$150,000
Actually spent · Claude + Gemini stack~20 hr~$300

Agency figure assumes ~700 billable hours at $200/hr blended, plus ~18% PM overhead — the conservative floor of a mid-market SOW. Premium brand studios would have quoted 2–3× that. Stack: Claude Code 4.7 Max, Claude Opus 4.6, Gemini 3.1 Pro, Vercel Pro.

§   Colophon

How this site is made.

Vol. 26 · build log

Every page on contextjamming.com is the output of a real-time, three-body Mixture-of-Experts loop. One model orchestrates. Two consult. The human holds the thesis. No single model commits alone.

Orchestrator

Claude Code 4.7

1M context · Max tier

  • Primary author
  • Terminal-native, direct push to Vercel
  • Audit trail to GitHub on every commit
  • Adaptive thinking · effort: extra-high

Auditor

Claude Opus 4.6

1M context

  • Editorial critic
  • Code review before merge
  • Backup-of-record
  • Co-signs every commit

Adversary

Gemini 3.1 Pro

Cross-model MoE

  • Factual adjudication
  • Structural dissent
  • Deep Research → semantic triples
  • Caught the Donelan incident

Stack

Next.js
16.2 · App Router
React
19.2
TypeScript
5
Tailwind
v4 · @theme inline
framer-motion
transitions
wavesurfer.js
audio waveforms
marked
MD → HTML at build
fast-xml-parser
RSS + Atom

Typeset in

Fraunces
variable · opsz + SOFT
Playfair Display
debate display
IBM Plex Mono
editorial metadata
Geist Mono
utility mono
Caveat
grease-pencil marginalia
All via
next/font/google
Palette
single @theme block
No dupe tokens
ever

Infrastructure

Deploy
Vercel Edge Network
ISR
30-min revalidate · wire + notebook
Repo
github.com/BretKerrAI/founderfile
Branch
hero-redesign-library
Analytics
Google Tag Manager
Apex
contextjamming.com
Runtime
Node 24
Build tool
Turbopack
       human intent
            │
            ▼
   ┌────────────────────┐         ┌─────────────────┐
   │  Claude Code 4.7   │  ◄────► │  Claude Opus 4.6 │      ← auditor loop
   │    (orchestrator)  │         │     (auditor)   │
   └─────────┬──────────┘         └─────────────────┘
             │  ◄───────────┐
             ▼              │
       ┌──────────┐    ┌────┴───────┐
       │  Vercel  │    │ Gemini 3.1 │          ← adversarial loop
       │  (edge)  │    │    Pro     │
       └─────┬────┘    └────────────┘
             │
             ▼
       contextjamming.com
             │
             ▼
       ┌──────────────┐
       │   Git push   │         ← audit trail
       └──────────────┘
Assembled on Mac in Terminal · Filed from Franklin, MAContext Jamming · ACRA Insight LLC · MIT License · FounderFile.ai · RelationalIntelligence.xyz · Commission a Dispatch →