Eric Lu (@ericlu, Mixfont) posted Ghost Font on July 11, 2026 — a video effect where text exists only in motion. Background dots scroll up; letter dots drift down. Your visual system fuses the opposing flows into words. GPT-5.6 Sol Ultra and Claude Fable 5 could not.
The clip hit 14.7M views on X. Solomon Hykes (@solomonstre, Docker founder) replied: "Captchas are about to get so much worse."
TL;DR — Ghost Font (July 11, 2026)
| Field | Detail |
|---|---|
| Creator | Eric Lu · @ericlu · Mixfont |
| Ship date | July 11, 2026 |
| Mechanism | Opposing dot motion → human-readable letterforms |
| AI tested | GPT-5.6 Sol Ultra · Fable 5 — both wrong per Lu |
| Human read | Immediate for most viewers watching playback |
| Tooling | Local prototype generator (Lu) |
| Hot take | Motion CAPTCHAs · vision model blind spots |
How Ghost Font works
Ghost Font is not a traditional font file you install — it is a motion graphics illusion:
Frame N (static): █ ░ █ ░ ░ █ ░ █ ← looks like noise
Over time:
background field → scroll UP
letter field → scroll DOWN
Human integration → "HELLO" (example shape)
The effect exploits temporal integration in human vision — the same family of phenomena as biological motion and aperture illusions. Single frames carry no legible OCR text; the message lives in velocity differences between dot populations.
Lu's demo pairs the motion text with decoy static strings models latch onto — part of why frontier VLMs report confidently wrong answers.
What frontier models did
Eric Lu's test (July 11)
I created a font called Ghost Font that only humans can read. Tested it in Fable and GPT 5.6 Sol Ultra and neither was able to decipher it correctly.
| Model | Reported behavior |
|---|---|
| GPT-5.6 Sol Ultra | Failed · often cited decoy on-screen text |
| Fable 5 | Failed · same decoy trap |
Community tests extended to Grok (@tranmautritam challenged @grok on the clip) with mixed results depending on prompting and frame tools.
Riley Goodside's inverse test (July 12)
@goodside posted meaningless eyes-closed phone scribbles labeled as handwriting:
| Model | Behavior |
|---|---|
| GPT-5.6 Sol | Hallucinates readable content reliably |
| Fable 5 | Abstains or says it is not real writing |
explainx.ai read: Ghost Font and Goodside's scribble are complementary failures — Sol over-reads garbage; both Sol and Fable under-read motion-encoded truth. Neither is a trustworthy OCR layer without verification.
Why multimodal models miss it
| Human vision | Typical VLM pipeline |
|---|---|
| Continuous motion integration | Sparse frame sampling |
| Opposing flow → form | Static salience wins (decoy text) |
| Phi / aperture prior | Trained on legible pixels |
| No "caption" needed | Text-in-image bias from pretraining |
Models that can crack Ghost Font in replies often do so via frame-by-frame diff analysis or explicit user instruction to track dot trajectories — not native "watch the video once" understanding.
That gap matters for:
- Agent browsers (Claude Code in-app browser)
- Video QA pipelines
- Accessibility (humans who cannot see motion still blocked)
- Security (bot gates assuming vision parity)
CAPTCHA implications — Hykes was joking, but not wrong
Captchas are about to get so much worse.
| Era | Bot gate |
|---|---|
| Text CAPTCHA | OCR arms race → broken |
| reCAPTCHA v3 | Behavioral scoring |
| Ghost Font class | Motion-only human proof |
Countermeasures already exist in principle:
- Frame differencing on server-side video upload
- Optical flow models (specialized, not general LLM)
- Human farms + screen recording
Ghost Font is a demonstration, not a deployed gate — but it surfaces the same lesson as GPT-5.6 bio bounty: security through obscurity in perception erodes fast once attackers optimize.
Ghost Font vs the July 2026 model race
Ghost Font dropped the same weekend as:
| Event | Link |
|---|---|
| GPT-5.6 Sol GA | Benchmark comparison |
| Fable credits cliff | July 12 usage billing |
| Honeycomb / Opus rumors | Opus 5 speculation |
Frontier labs market native multimodal parity with humans. Ghost Font is a cheap, viral falsification — not a rigorous benchmark, but a memorable one. 14.7M views beat most vendor eval PDFs for public persuasion.
Try it yourself
Lu attached a local prototype to generate Ghost Font clips — check @ericlu's thread for the latest link. Workflow for researchers:
- Render a clip with your hidden message
- Ask Fable 5 / GPT-5.6 Sol to read the video cold
- Retry with frame-by-frame or optical-flow hints
- Compare to human accuracy at normal playback speed
Document decoy text placement — models grab it first.
Limits and ethics
| Limit | Note |
|---|---|
| Accessibility | Motion-only text excludes some humans |
| Not cryptographic | Motion analysis can reverse |
| Demos ≠ product | Mixfont typography tool ≠ shipped CAPTCHA |
| Hallucination risk | Sol may "read" Ghost Font wrong confidently |
Do not deploy human-only gates without fallbacks and audit for exclusion and bypass.
Related on explainx.ai
- GPT-5.6 vs Fable 5 — vision-capable frontier models
- Fable 5 usage credits from July 13
- Claude Opus 5 speculation — Honeycomb leak
- Claude Code desktop in-app browser
- OpenAI bio bounty — jailbreak economics
- Google Gemini 3.5 multimodal guide
Sources: @ericlu · @solomonstre · @goodside · @tranmautritam
Ghost Font mechanism described from July 2026 X posts and community summaries. Video © Eric Lu — re-hosted as animated WebP for explainx.ai. Verify model behavior on your own clips before security claims.