accessibility on S Anand

Is all AI content slop?

Wed, 05 Nov 2025 00:00:00 +0000

Is all AI content slop?

I asked Claude to:

Analyze this thread. Then explain it like a Malcolm Gladwell New Yorker article. https://news.ycombinator.com/item?id=45820872

It gave me a beautiful, engaging and insightful essay about a 300+ message debate about AI vs humans on routine tasks. https://claude.ai/share/60c5810f-5c81-4970-8026-a24bf89c3392

Is this slop?

One phrase stood out:

There’s an irony here that the commenter doesn’t quite state but implies beautifully: we’ve spent so long celebrating automation because humans are imperfect that we’ve forgotten we also value humans because they’re imperfect.

Note: it’s something “the commenter doesn’t quite state” and yet Claude inferred it. “Beautifully”.

Is this slop?

Another paper, The Hidden Curriculum, is quite readable as papers go. https://mgcuna.github.io/website/JMP_latest.pdf

But look at how it begins:

Despite dramatically expanded access to selective U.S. colleges, first-generation students persistently trail continuing-generation peers in GPA, internship attainment, and early-career outcomes.

Here’s how Claude’s Malcolm Gladwell essay begins: https://claude.ai/share/81d7ff3c-db89-4c9f-8423-82358fb660a3

When Sara Martinez arrived at UC Berkeley as a freshman, she did everything right. She showed up to every class. She completed every reading assignment. She took detailed notes. She studied harder than most of her peers. By every visible measure, she was the model student.

I read every word of the essay. The paper has value, but the essay has accessibility.

Is this slop?

History repeats this pattern.

The printing press displaced calligraphers.
But typography emerged as an art.
Film displaced theater but gave us montage, screenplay, and editing.
CAD displaced drafting but birthed parametric design.
3D printers are displacing workshops, creating toolpath sculpture and generative objects.

Maybe AI slop is the start of new arts?

Things I Learned - 24 Nov 2024

Sun, 24 Nov 2024 00:00:00 +0000

This week, I learned:

OpenAI lets you download GPT instructions and execute arbitrary code in their containerized environment. This is not a bug. Ref
BM25 works as follows: Ref
- For each query term in the query, sum up the product of:
  - Inverse document frequency = LN(% of docs without the query term + 1) – with a small tweak
  - Term frequency = freq / (freq + k) – where k is usually between 1.2 to 2. Returns 0-1 with diminishing frequency benefit
    - k is multiplied by Document length normalization = 1 - b(1- DocLength/AvgDocLength). Longer documents have larger k, dampening frequency benefits.
- Some implications:
  - The actual BM25 score has no meaning. It’s just useful for ordering
  - BM25 scores for 2 queries can be compared ONLY IF the document sets don’t change
A list of Markdown to Website converters on this thread:
- Jekyll - Ruby - 2008
- MkDocs - Python - 2014
- GitBook - JavaScript (Node.js) - 2014
- MkDocs Material - Python (MkDocs-based) - 2016
- Docsify - JavaScript - 2016
- MdBook - Rust - 2017
- Antora - JavaScript (Node.js) - 2017
- Docusaurus - JavaScript (React) - 2017
- JupyterBook - Python - 2019
- Keenwrite - Java - ~2019
- Honkit - JavaScript (GitBook fork) - 2019
- Nextra - JavaScript (Next.js) - 2020
- Astro - JavaScript/TypeScript - 2021
- Hugo Book - Go (Hugo-based) - ~2020
- Clowncar - JavaScript/Node.js - ~2021
- Quarto - R and Python - 2022
- Starlight - JavaScript/TypeScript - 2023
DuckDB has an LLMs.txt. Today, 38 repos on GitHub support it
When identifying LLM use cases, it helps to tell LLMs what they can do. I use one or more of a list like below:
- Core capabilities:
  - Text Generation: Produce coherent and contextually relevant text across various domains.
  - Image Generation: Create realistic images that match the style and content of a given reference image.
  - Text to Speech: Convert text into natural-sounding speech with appropriate intonation and rhythm.
  - Speech to Text: Transcribe and interpret spoken language.
  - Vision: Analyze and describe visual content from images.
  - Video Analysis: Summarize and extract information from video content.
  - Text to Video: Generate realistic (and surrealistic) videos from text descriptions.
  - Function Calling: Execute predefined functions or access external tools to perform specific tasks.
  - Structured Output: Generate structured outputs like JSON, XML, HTML, YAML, DSLs, etc.
  - Tool Use: Utilize external applications or APIs to enhance functionality.
  - Code Generation: Write and debug code snippets in various programming languages.
- Cross-domain use cases:
  - Summarization: Understand and condense lengthy documents into concise summaries.
  - Translation: Convert text between multiple languages with high accuracy.
  - Question Answering: Provide precise answers to user queries based on provided information.
  - Reasoning and Planning: Solve complex problems and develop step-by-step plans.
  - Personalization: Tailor responses based on user preferences and historical interactions.
  - Dialogue Management: Engage in context-aware, multi-turn conversations.
  - Data Analysis: Interpret and generate insights from structured data.
  - Content Moderation: Identify and filter inappropriate or harmful content.
  - Sentiment Analysis: Detect and interpret emotions and opinions in text.
  - Robotics Integration: Interface with robotic systems for control and decision-making.
  - Knowledge Retrieval: Access and present information from vast datasets or knowledge bases.
  - Creative Writing: Generate poetry, stories, and other creative content.
  - Educational Assistance: Provide explanations and tutoring across various subjects.
  - Ethical Reasoning: Assess scenarios for ethical considerations and implications.
  - Accessibility Support: Assist users with disabilities through tailored interactions.
  - Simulation and Modeling: Create predictive models and simulate scenarios.
- Domain-specific use cases:
  - Legal and Medical Assistance: Offer information and guidance within legal and medical domains.
  - Gaming: Generate narratives, dialogues, and scenarios for interactive entertainment.
  - Scientific Research: Aid in literature reviews, hypothesis generation, and data interpretation.
  - Financial Analysis: Analyze market trends and provide investment insights.
  - Cultural Competence: Understand and respect diverse cultural contexts in interactions.
  - Security Applications: Detect and respond to potential cybersecurity threats.
  - Environmental Monitoring: Analyze data related to environmental changes and sustainability.
  - Healthcare Support: Assist in patient monitoring, diagnostics, and personalized treatment plans.
  - Supply Chain Optimization: Enhance logistics and inventory management through predictive analysis.
  - Customer Service: Provide automated support and resolve customer inquiries.
  - Market Research: Analyze consumer behavior and market trends for business insights.
  - Content Creation: Generate articles, blogs, and marketing materials.
  - Virtual Assistance: Manage schedules, reminders, and personal tasks.
  - Social Media Management: Craft posts and engage with audiences across platforms.
  - Human Resources: Assist in recruitment, training, and employee engagement strategies.
  - Event Planning: Organize and coordinate events, including logistics and communication.
  - Travel Planning: Provide itineraries, booking assistance, and destination information.
  - Real Estate: Analyze property markets and assist in buying or selling decisions.
  - Agriculture: Monitor crop health and optimize farming practices through data analysis.
  - Energy Management: Optimize energy consumption and monitor renewable energy sources.
  - Transportation: Enhance route planning and traffic management systems.
  - Urban Planning: Assist in designing sustainable and efficient urban infrastructures.
  - Disaster Response: Provide real-time information and coordination during emergencies.
  - Public Policy: Analyze data to inform policy decisions and predict societal impacts.
  - Art and Design: Generate visual art concepts and assist in creative design processes.
  - Music Composition: Create original music pieces and assist in songwriting.
  - Language Learning: Facilitate language acquisition through interactive exercises and feedback.
  - Historical Analysis: Interpret historical data and provide insights into past events.
  - Philanthropy: Identify charitable opportunities and assess the impact of donations.
  - Sports Analytics: Analyze player performance and game strategies.
  - Fashion: Predict trends and assist in clothing design and merchandising.
  - Culinary Arts: Generate recipes and provide cooking guidance.
  - Astronomy: Analyze celestial data and assist in space exploration research.
  - Psychology: Offer insights into human behavior and mental health support.
  - Linguistics: Analyze language patterns and assist in translation studies.
  - Archaeology: Assist in artifact analysis and historical site interpretations.
  - Literature Analysis: Interpret literary works and provide critical analyses.
  - Philosophy: Engage in discussions on ethical dilemmas and existential questions.
  - Mathematics: Solve complex equations and assist in theoretical research.
  - Physics: Model physical phenomena and assist in experimental design.
  - Chemistry: Analyze chemical compounds and predict reactions.
  - Biology: Assist in genetic research and ecological studies.
  - Geology: Analyze geological data and assist in natural resource exploration.
  - Meteorology: Predict weather patterns and analyze climate data.
  - Oceanography: Study marine ecosystems and assist in ocean exploration.
  - Anthropology: Analyze cultural data and assist in ethnographic research.
Style of writing impacts output style a lot. E.g. Adding an evil laugh makes Claude more creative. Ethan Mollick
For good structured mode output, we need good prompting.
- Mentioning examples and schema and “JSON” helps. When providing examples, using (user, assistant) message pairs helps (I think it’s because it’s easier for the LLM to parse).
- Using a {reasoning, answer} schema (with reasoning first) helps. Make reasoning concise and relevant Ref Arxiv
- We already know code in JSON is not a great idea. Ref
Just adding 3 real examples and regurgitation helped GPT 4o play chess much better. Both techniques may have more general use in prompting. Simon Willison
With Deno 2.0, the same .js file can run in Node.js as well as Deno. Example
jspm lets you generate import maps against any CDN.
You can click on htop columns on the terminal to sort by that column! Mouse events work on command line apps. Julia Evans
Alt Text will very likely be a browser feature. It’s important for the Alt text to flow as part of the content when listening to the page. Perhaps even become a part of the browser APIs like speechRecognition.
Langchain suggests multiple levels of agentic behaviour. LLM Call < LLM Chain < LLM Rounter < State Machine < Autonomous Langchain
A HTML quine: A page that, when rendered as HTML, shows the HTML source code of the page!
You can enable syntax highlighting just using fonts. Ref
HTML is all you need shows examples of using HTML for notebooks instead of Jupyter, Observable, etc.
Straive evaluated Gemini 1.5 Flash 002 and GPT 4o Mini for translation.
- Portugese: Flash is better than GPT 4o Mini. BLEU Word Overlap is 65.5% > 64.6% and METEOR (Semantic) is 84.9% > 78.9%
- Mandarin: Flash is better than GPT 4o Mini. BLEU Word Overlap is 25.0% > 15.9% and METEOR (Semantic) is 54.7% > 51.1%
The problem with Accept headers is that you can’t link to them. Simon Willison
Recraft v3 supports vector (SVG) generation Simon Willison. The output is 100% <path> elements (even for text). You get 50 free credits daily. Creating 1 image is ~2 credits. The API costs $1 per 1K credits. Some things I can create with it are:
- Base data visualizations that I can animate with code
- Icons in a specific style
- Comic strips
- Explainers for talks or student material
- Featured images for blog posts
- Architecture diagrams?

Mobile browsing

Wed, 03 Sep 2008 12:00:00 +0000

When I analysed my HTTP log last week, I had another motive: are there enough people accessing my site on a mobile device? Or is it too small at this stage for me to care about?

Well, have a look at the numbers.

Windows	98.4%
Mobile	0.6%
Linux	0.5%
OS X	0.5%

Yes, there are more people accessing my site through a mobile device than there are using Linux or OS X. That's shocking!

Now, I'm not saying that this is representative of the rest of the world or anything, but at least it tells me a couple of things.

Firstly, the whole mobile browsing thing is bigger than I thought it was. I started worrying about this a couple of months ago and got myself a HTC s620 phone and a BlackBerry (for free, through some innovative social engineering and smooth talking). It really does get pretty useful on the move... which is frankly anywhere outside of the home and the office, and sometimes even within. (It's handier to read recipes off the HTC than a laptop.) Google had caught on to the whole mobile browsing trend a very long time ago, and are rather well positioned to make use of it.

Secondly, it means that rather than worrying about my site working on Linux or OS X (i.e. worrying about what plugins to use), I should worry more about it working on mobile devices (i.e. small screen, no Javascript / CSS).

That's a fairly big shift in my thinking. Earlier, I had been all for shifting all the processing to client-side Javascript. Now it appears I need to design more towards plain HTML pages generated by Perl / PHP.

Comments

Dinakaran 3 Sep 2008 6:23 am: Nice to see that people visit your site your mobile. Mobile browsing is a very upcoming trend . It’s yet to catch up in India for the telecom infrastructure limitations.If there are better band width’s provided by the service providers , mobile browsing will move up to a new level.

A day when I’m able to play 30 minutes of non-interupted podcast through my mobile while travelling down to the office listening to the latest technology discussion is some thing which I dream to come as a reality in the near future.

HTML keyboard shortcuts

Wed, 30 Nov 2005 12:00:00 +0000

HTML keyboard shortcuts using the “accesskey” attribute.

Office 12

Wed, 14 Sep 2005 12:00:00 +0000

A 40-minute video preview of Office 12. I don’t normally watch videos this long. But it was worth it.

Office 12 has a REALLY different user interface (critique). It’s also supposed to have a lot of new features.

What struck me the most in the video is how Powerpoint creates diagrams. You type text, and Powerpoint can automatically convert that into value chains, org charts, etc. Julie mentions that a blind user was able to create graphics using this feature, and that this was the first time she has been able to create graphics in all her life!

Top 10 web design mistakes of 2002

Wed, 25 Dec 2002 12:00:00 +0000

Jakob Nielsen’s top 10 web design mistakes of 2002. Fortunately, I was committing only one of them – fixed font sizes. Now rectified.

Laymen want documentation they understand

Wed, 04 Sep 2002 12:00:00 +0000

Programmers: learn from this. Laymen want documentation they understand. (Wish someone told me 5 years ago.)

Type with your eyes

Thu, 22 Aug 2002 12:00:00 +0000

It’s possible to type with your eyes. Hope this is commercialised soon. The details are available for free.

The deaf use mobile phones

Mon, 11 Feb 2002 12:00:00 +0000

The deaf use mobile phones through SMS. Good idea.