blog/videos/ep01-the-cure-for-ai-slop at main · woosal1337/blog · GitHub
//files/disambiguate" data-turbo-transient="true" />
Skip to content
Search or jump to...
Search code, repositories, users, issues, pull requests...
-->
Search
Clear
Search syntax tips
Provide feedback
--><br>We read every piece of feedback, and take your input very seriously.
Include my email address so I can be contacted
Cancel
Submit feedback
Saved searches
Use saved searches to filter your results more quickly
-->
Name
Query
To see all available qualifiers, see our documentation.
Cancel
Create saved search
Sign in
//files/disambiguate;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up
Appearance settings
Resetting focus
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
woosal1337
blog
Public
Notifications<br>You must be signed in to change notification settings
Fork
Star<br>52
FilesExpand file tree
main
/ep01-the-cure-for-ai-slop<br>Copy path
Directory actions
More options<br>More options
Directory actions
More options<br>More options
Latest commit
History<br>History<br>History
main
/ep01-the-cure-for-ai-slop<br>Copy path
Top
Folders and files<br>NameNameLast commit message<br>Last commit date<br>parent directory<br>..<br>README.md
README.md
before-after-samples.md
before-after-samples.md
experiment-results-openai.md
experiment-results-openai.md
experiment-results.md
experiment-results.md
run-openai.py
run-openai.py
ste-lint.py
ste-lint.py
ste-writing-skill.md
ste-writing-skill.md
View all files
README.md<br>Outline<br>The cure for AI slop is a 1986 aircraft manual - the kit
Everything the episode promises "in the description": the distilled STE skill,<br>the linter, and the full first-party test data. Self-contained - no external<br>dependencies beyond Python 3.
Files
File<br>What it is
ste-writing-skill.md<br>The distilled ASD-STE100 agent skill, two modes: strict (procedures, error messages) and flavored (prose, no dictionary lockdown)
ste-lint.py<br>The heuristic anti-slop linter - the machine-checkable subset of STE. Deterministic; the score delta between two texts is the signal
experiment-results.md<br>The cross-model test: 6 writing tasks x 4 conditions on Claude and gpt-5.5
experiment-results-openai.md<br>Per-category detail for the gpt-5.5 run
before-after-samples.md<br>The real baseline-vs-STE outputs quoted in the episode
run-openai.py<br>Reproduction script for the OpenAI side of the experiment
Run the linter
python3 ste-lint.py your-draft.md
Score is violations per 100 words - lower is cleaner. Lint a draft, apply the<br>skill, then lint it again - the delta between the two scores is the signal.
The headline numbers
Condition<br>Claude sonnet<br>gpt-5.5
baseline<br>4.36<br>3.54
banned-words list<br>4.21 (-3%)<br>2.14 (-40%)
Orwell's 6 rules<br>2.48 (-43%)<br>1.69 (-52%)
STE skill<br>1.12 (-74%)<br>1.76 (-50%)
Give the model a writing system and slop drops by half or more, on every model<br>tested. STE was best or tied-best. A banned-words list is the least reliable fix.
Not a certified STE checker. The judgment rules of ASD-STE100 need a human;<br>this covers the mechanical subset - which is where the slop lives.
Spec: ASD-STE100 Issue 9, free at asd-ste100.org
You can’t perform that action at this time.