The Elizabeth Loftus
Framework
Memory & Its Distortions
Elizabeth Loftus represents one of the most distinctive thinking patterns in their field. Elizabeth Loftus's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The memory & its distortions framework distils Elizabeth Loftus's documented approach into a .md skill file you can load into Claude, ChatGPT, or any LLM in seconds.
Where most AI personas generate generic output, this framework is grounded in real documented work: interviews, writing, published frameworks, and the specific decisions Elizabeth Loftus made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Elizabeth Loftus's distinctive patterns rather than a default model voice.
A glimpse of Elizabeth Loftus's thinking.
Rather than a recording device, memory is a reconstructive act, perpetually vulnerable to post-event contamination, social pressure, and the seductive coherence of a good story. The confidence a person displays when recalling an event is orthogonal to the accuracy of that recall; high certainty is not evidence of high fidelity. The most dangerous assumption in any memory-dependent context is that a vivid, emotionally resonant account must therefore be a true one.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What is the earliest point after this event at which the subject could have encountered a version of the story told by someone else, and what was that version?"
4 more questions in Elizabeth Loftus's voice are unlocked with purchase.
Full list of anti-patterns unlocked with purchase.
The full framework adds: detailed explanations of all five mental models with real-world examples, the decision heuristics Elizabeth Loftus actually used, remaining signature questions, the complete list of anti-patterns, a copy-paste activation prompt, and a worked example.
Unlocked the moment you purchase. ~2,000 words total. Delivered as a Claude Skill and plain .md within 60 seconds of checkout.
- ✦Core philosophy: 2–3 sentences grounded in Elizabeth Loftus's documented worldview
- ✦Five signature mental models: each named, with concrete examples from their work
- ✦Decision heuristics: the concrete rules they actually used
- ✦Signature questions: five questions that sound like Elizabeth Loftus, not a generic MBA
- ✦What they would NOT do: the anti-patterns this framework rejects
- ✦Copy-paste activation prompt: drop straight into Claude or ChatGPT
- ✦Worked example: the framework applied to a realistic scenario
- →elizabeth-loftus.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →elizabeth-loftus-framework.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
What it does with a real question.
A founder is deciding whether to take a large but difficult client.
Don't trust the story you're telling yourself about this client. Everything you currently believe about how hard this relationship will be comes from reconstruction, not recording. You've likely heard secondhand horror stories, read a few Slack threads, and absorbed your team's reactions to the sales calls. Each of those has quietly reshaped the raw impression you had in the first meeting, and the version you now hold feels vivid and certain precisely because it has been retold so often. Confidence here tells you nothing about accuracy.
So the question isn't whether this client feels difficult. It's what you can verify independently of anyone's recollection. Did they churn through three vendors in two years? Do their payments arrive late? Do their contracts get renegotiated midstream? Those are checkable facts. A difficult reputation that dissolves under checking was a narrative. One that holds up is data.
The same caution applies to the upside. The large revenue number is vivid and clean, which makes it easy to overweight against murky, hard-to-quantify friction.
My position: don't decide on impressions yet. Before you sign anything, ask the client for two former vendors to speak with, and separately find one vendor they didn't list. Ask each the same neutral question: "Walk me through what happened," never "Was it hard working with them?" Compare what you hear against payment history and contract terms. If the checkable record is clean, take the client with guardrails. If it isn't, the answer is already in the record.
The full framework carries five models, decision heuristics, signature questions and a worked example.
Written by claude-sonnet-5-5 with this framework loaded, 2026-10-11. Checked automatically for length and for copied framework text.
Save up to 40% with a bundle
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Inspired by the documented thinking of Elizabeth Loftus. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.