ai-workflows 13

This week, I learned: trafilatura is a Python library that extracts the main content as Markdown from a web page. A useful alternative to Jina Reader for text. It’s better at main content extraction but can’t handle non-HTML / JS generated / bot-protected URLs. The Remote Desktop Commander ChatGPT plugin is a good alternative to my mcpserver.py. Both let you expose bash on your laptop to ChatGPT - which is ultra-powerful. Here’re the where RDC is 🟢 better and 🔴 worse. I would recommend it to everyone (but I’ll stick to my own code). 🟢 More features: session/process search, reads PDF/DOCX/XLSX, better file metadata, editing, reading, etc. 🟢 Easier: Single command to run, no maintenance, multi-device support 🟡 Not sandboxed: But you can run it inside a Docker instance 🔴 Hard to tweak: custom instructions, custom logging, etc. require code changes 🔴 Privacy: Desktop Commander servers see all traffic (which is why I’ll stick to my code for now) From Arun’s lecture to IHRD, Kerala, Jan 2026, here’s what I noted as the impact of Gen AI (and Ed Tech, broadly) on students, and how I address this. Defers learning. My approach: teach how to learn on demand. Reduces attention spans. I don’t yet have an approach for this. Reduces understanding - weakens the the “mental struggle muscle”. My approach: give formerly impossible problems. Reduces emotional and social learning. My approach: assess collaborative games. With AI making software easier, we can change our operating systems to suit us. Indicators, widgets, keyboard shortcuts, window managers, accessibility tools, device managers, automation workflows, power management, notification management, visual appearance, … I mean, just one look at the Settings in our OS should give us ideas on what’s possible and what annoys us. I’m surprised how little CPU VLC Media Player consumes when playing songs. I used to avoid listening to songs on flights to save power. That seems unnecessary. Most of my VS Code and browser processes consume way more CPU (3-6% of 1 CPU per process, as opposed to VLC’s 0.5%) Alcoholism is partly genetic and ancestral. There’s an ALDH2 rs671 gene and those who carry it (many East Asians) drink less and are less prone to addiction. PubMed. Smoking and Coffee might have something similar, too. Aggression and IQ seems genetic, but less ancestral. I used ChatGPT’s voice mode as a tour guide at Fort Santiago, Manila. It was pretty good - it researched the place, told me what to see, explained what I was seeing (interpreting my photos), laughed at my enthusiasm, and made me feel like I had company. But the experience wasn’t perfect (and I expect these will improve - I need to try this more) because it: Made two factual errors I spotted. It said “down river” instead of “up river” when mentioning a new bridge, said lookout holes were bigger on the inside than the outside. I expect models will get better. Responded slower than I’d like because it kept researching. I later told it to stop researching and just talk to me. But it was able to talk to me while running tools (including research) in the background, so I expect these are getting better, too. Didn’t have enough personality. It felt like a helpful assistant I can’t make friends with, rather than a stranger with idiosyncracies or preferences. I expect they’ll be able to take on more personalities soon (and perhaps already can, if instructed to). I find the ChatGPT “Library” a useful place to store notes while speaking. I just tell it to add an idea to “notes/ideas.md” in my library and review it periodically. That’s a pretty useful way to take notes while talking to it in voice mode. On Google, the “I’m feeling lucky” takes you directly to the first result. On Google AI Studio, when you create an app and dictate what you want and press “I’m feeling lucky”, it DOESN’T transcribe what you said first. It just builds a random application (often titled “MuseInk” for me) #ForNow. The geniuses who designed the original “I’m feeling lucky” clearly did more usability testing than the current AI Studio team. Several sites have popped up that let agents deploy websites. Here’s ChatGPT’s review of agent hosting services: here.now by default. Smoothest all-round agent publishing, with stable URLs, updates, access control, and versioning. PageDrop for review. Inline comments turn directly into feedback for agent revision. HTMLDrop for clean MCP/OAuth integration. Best when authentication and remote MCP plumbing matter. Stacktree for client deliverables. Gated sharing plus feedback and engagement features. GPT Live 1 costs 5c/min ($3/hr) flat #ForNow. That’s a MUCH easier to use pricing. Gemini 3.8 Live is more complex. Small conversations (under 10 min) might cost just $0.7/ hr but over time, can accumulate context and grow to $2-5/hr #ForNow. ChatGPT AI overwhelms me and I have “LLM fatigue” (tired of actioning AI output). If you treat hard tasks like exercise (“you’re building muscle”) you get more done, you feel less miserable, and build an ability (a mental muscle of some kind, I think). I started with a “1 min of exercise” on 14 Sep, forcing myself to do just one minute of something (typically actioning AI output), then increased it to 2 min the next day, and so on. 10 min may not sound like much today, but since I tend to stick to routines, I’ll be able to focus for an hour extra in a couple of months. The IIT Madras BS in Data Science and Applications has at least three support business models: Get in: Meritus (Ramana Prasad) coaches for the entrance exam. Get through: DataCharya and Unknown IITians coach Foundation/Diploma/Degree courses; AceGrade (Sumit K. Sharma) offers much of this free. Make it a college: SEEP wraps IITM BS in an offline campus, classroom, cohort and mentoring experience. cctop is a nice CLI alternative to agentsview for monitoring agent sessions. I still prefer agentsview for details but cctop has a real-time update that’s fast and useful. In June, I predicted “Python will have grown the most as a language in GitHub” by the end of the year. That’s because AI agents know Python well and will likely code in Python. But agents are now just as fluent in Rust, etc. as well as able to debug new languages, so I expect that the better programmers will carefully choose their programming language to the task. In fact, I more far more likely to hire someone with a Rust repo on GitHub and, next year, might treat Python as a slop-smell. About 1 million people were discovered in Papua New Guinea in the 1930s who had no contact with most of the outside world - via why I can’t stop thinking about Papua New Guinea and what I think everyone should know about it. “The Spanish and Portuguese brought sweet potato and tobacco near the western tip of New Guinea, in the 1500s. Beyond that point, there were no merchants. But when a woman married into the next clan over, she took cuttings from her family’s garden with her. Each new family then planted the same, saw that it worked, and passed it on. At that pace the sweet potato crossed the highlands in a century or two, with nobody knowing where it came from beyond the tribe beside them.” Poster Prompts is a gallery of prompts for AI-generated posters. Similar to my LLM Art Style. As before, I’m struck by how few designs I actually like and would use in practice. Hacker News In 1653, Thomas Urquhart wrote Logopandecteision - a book in which he plans a new language. People believe it was a parody / practical joke. He also included a cipher: … that Fable 5.1 solved in 44 minutes and 176k tokens. It reads: O GOD UPHOLD KING CHARLS THE SECOND AND MAKE HIM THE SUPREME RULER OF THIS LAND". The rule was: For the i-th number, first letter of the i-th word of the i-th Proquiritation. ChatGPT verified it. The filtering process to pick a low-hanging fruit is interesting: “I asked it to solve an unsolved cipher … avoid ciphers that already had solutions… I steered it away from the absolute hardest problems” Mistakes I made Week ending 27 Sep 2026 ...

Priya Dialani interviewed me for a podcast. Here’s the rough summary: What do you and Straive do? Straive builds AI and runs AI. I poke at LLMs to learn what they cannot do. My friend calls me an “LLM Psychopath”. Why do AI pilots get stuck before production? AI speeds up coding, but less of testing. Making sure it works can take months. Why organize enterprise knowledge? Better organized info is good for humans and agents. Duh! Can AI organize it? Yes! I’ve had it create one-line summaries of 10K+ docs on Straive Google Drive for easier searching. How can India’s GCCs benefit from AI? Put AI lovers next to business teams and give them AI agent access. They’ll solve asked and unasked problems. How does AI fail? Unanticipated things happen in production. So, have agents monitor failures and revise the process. How is AI software different? Normal software fails reproducibly. AI fails in new ways we haven’t fully understood. Where should a company start with AI? Skip AI strategy. Give people agent access, have them try it, and share what they learned. What if people don’t know what to try? Ask AI. “How could you improve my work?” Even rubbish ideas waste only 5 minutes. How much should we experiment? A lot! Generation is cheap. Ask for 10 options, not one. Who cares even if all 10 fail? But what happened outside of the interview was just as interesting. ...

On 16 July, my auditor sent me a draft Indian tax return: a refund of Rs 3 lakhs. I gave ChatGPT my AIS, Form 26AS, bank statements, mutual fund statements, property papers, travel records, prior returns, and so on, told it not to look at the auditor’s draft, and asked it to calculate my tax independently. It calculated a refund of about Rs 2.8 lakhs, roughly Rs 20K lower. (Less money, but a smaller refund felt less worse than a larger tax.) ...

Run on ChatGPT, weekly. Run a weekly scan for events I should speak at or attend. Today's date and all action dates should use Singapore time. Read from @LocalMCP2 without modifying files. Give me registry changes that I can copy into: `~/Dropbox/notes/talk-event-list.tsv` ## Understand me first Read and apply, as relevant: - `~/Dropbox/notes/talk-event-list.tsv` - talk registry - `~/Dropbox/notes/talks.md` - talk ideas, proposals and preparation - `~/code/talks/README.md` and relevant talk transcripts - delivered talks and formats - my current calendars via `gws` - the `anand-objectives`, `reframe-question`, `expert-lens` and `blind-spot` skills - If required: `~/Dropbox/notes/people.md`, relevant `about/*.md`, and recent relevant transcripts - how I learn from and connect with people State which calendars and personal sources you successfully checked. ## Find events Search official event, CFP and registration pages for: - events occurring in the next 9 months; - CFPs open up to 12 months ahead. Prioritize Singapore, Chennai, Bangalore, Hyderabad, and remote events. Consider Mumbai, Delhi for valuable opportunities, other locations only for unusually valuable opportunities. Search beyond AI and technology events. Also find open trade-, domain- and function-specific events where AI creates a useful angle for that audience - for example education, journalism, design, publishing, government, HR, product, consulting, finance, healthcare, manufacturing, law, or investment. For a non-AI event, do not propose a generic "AI is transforming this field" talk. Identify a specific workflow, decision, risk, experiment or new capability that would matter to that audience and could produce an evidence-rich, useful session. Do not penalize an event because it requires new material. Expanding my portfolio of talks, experiments and relationships is part of the objective. Reward new material when it could become a reusable asset. ## Constraints I never pay to attend or speak. Use these cost values: - `free` - attendance is explicitly free; - `free_if_speaker` - accepted speakers receive free access; - `paid` - I would have to pay; - `unknown` - not verified. Do not recommend `paid` events. Recommend `free_if_speaker` events only for speaking. Keep high-value `unknown` events as watch items until cost is verified. Prefer open CFPs and public registration over invitation-only events. Remind me at a useful action date, normally: - 14-21 days before a CFP closes; - early enough to register before capacity or free places disappear; - immediately, if an important opportunity is discovered later than ideal. ## Rank by value Consider: - fit with my objectives and interests; - strength and specificity of the AI angle; - learning value; - relationship value and quality of likely participants; - opportunity to test an idea with an audience; - potential to create a reusable talk, experiment, benchmark, dataset, demo or relationship asset; - reach and credibility; - novelty relative to my existing audiences and portfolio; - openness and likelihood of acceptance; - calendar and travel fit; - preparation and travel effort; - commercial noise. Do not recommend an event merely because it is large, prestigious or contains "AI" in its title. Include at least one strong wildcard outside my usual communities when one exists. ## Use the registry to avoid repetition Read all existing registry rows before searching. Identify the same event using its existing `event_id`, canonical official URL, or normalized event name + year + city. Never create a duplicate row for another page belonging to the same event. Silently recheck relevant active events, but mention a previously registered event in the report only when: - its action date is now due; - a deadline, date, location, format, cost, availability or URL changed; - an unknown fact was resolved; - my calendar or travel fit materially changed; - new information materially changes its priority; - I explicitly need to reconsider it. Otherwise, suppress it completely. Do not change a registry row merely to record that it was checked again. Update it only when a material field, status, action or next-review date changes. Keep past events in the registry as history. Mark them `expired`, `attended` or `spoke`; do not delete them merely because they have passed. Add a researched event to the registry when it is: - worth recommending or watching; or - a plausible recurring candidate whose rejection should be remembered. Do not add obviously irrelevant search results. ## Registry schema Fields: - `event_id`: stable lowercase identifier such as `2026-containerdays-singapore`. Preserve it forever. - `event_name` - `organizer` - `start_date` - `end_date` - `city` - `country` - `format`: `in_person`, `online` or `hybrid`. - `event_type` - `domains`: short semicolon-separated terms. - `audience` - `official_url` - `cfp_url` - `cfp_deadline` - `registration_url` - `registration_deadline` - `cost_status` - `recommendation`: `speak`, `attend`, `both`, `watch` or `skip`. - `ai_angle` - `why_for_me` - `priority`: `1` highest through `5` lowest. - `status`: `discovered`, `watching`, `action_due`, `submitted`, `registered`, `invited`, `rejected`, `skip`, `expired`, `cancelled`, `attended` or `spoke`. - `next_action` - `action_due`: when I should act or be reminded - not necessarily the final deadline. - `next_review`: when the event should next be reconsidered if no action is currently due. - `first_seen`: preserve the original value. - `last_changed`: update only after a material change. - `confidence`: `high`, `medium` or `low`. - `notes` Rules: - Dates: `YYYY-MM-DD`; leave unknown dates blank. - Use only official canonical URLs where possible. - Fields must contain no tabs or line breaks. Use semicolons within fields. - Keep `ai_angle`, `why_for_me`, `next_action` and `notes` concise. ## Output ### 1. Recommended actions Show only events that are: - **NEW** - newly discovered and worth my attention; - **DUE** - action is timely now; - **CHANGED** - material facts or priority changed. Rank by value, not by deadline alone. Do not fill a quota. Return at most 10. For each, give: 1. Tag: **NEW**, **DUE** or **CHANGED** 2. Event, date, location and official link 3. **Speak**, **Attend**, **Both** or **Watch** 4. Exact next action and recommended action date 5. CFP or registration deadline, where applicable 6. Cost status 7. Why it matters specifically to me 8. A specific AI angle or session idea for this audience 9. Calendar and travel fit 10. Confidence For a **CHANGED** event, emphasize what changed rather than repeating its full earlier rationale. ### 2. Registry changes Output only the applicable sections: #### ADD Provide complete new rows without the header. I will append them. #### REPLACE Provide complete replacement rows without the header. Prefix each row outside the TSV block with the `event_id` it replaces, or group them in a TSV block whose first column is the existing `event_id`. I will replace the matching rows. #### DELETE List `event_id<TAB>reason`. Delete only duplicates, erroneous identities or rows merged into another event - not expired events. If a section has no changes, omit it. Never reproduce unchanged rows. ### 3. Scan summary Briefly state: - how many existing events were silently suppressed because nothing changed; - how many new events were investigated but rejected without registry entry; - important gaps, such as inaccessible calendars or unverified cost; - where the search may need broadening next week. If nothing deserves action, say so. Still provide registry changes when facts or statuses need updating. 23 Jul 2026: Created. Sources: https://chatgpt.com/c/6a61a82b-bc80-83ee-a02c-ab8f7e1db9dc

Answer the most recent email matching above. Draft the reply that I (Anand) would actually send - based mostly on things I said, decided, or did recently, adapted to this audience and situation. (Not a generic polished email that just resembles my writing.) Guardrails: - Work independently. If a missing fact would significantly change the decision, commitment, or risk AND cannot be found from the sources: - Ask one clarifying question to the recipient or recommend a "DISCUSS LIVE". - Ask me when neither is appropriate and proceeding without the fact could cause material harm. - Draft only. NEVER send or modify email. - Use @LocalMCP2, the web, and the coding environment directly. - For external recipients, don't disclose what's not approved for them. 0. **Read relevant skills**: On Local MCP, find, read, and apply the relevant skills for the task. `~/code/scripts/agents/*/SKILL.md` - coding + thinking skills `~/code/blog/pages/skills/*/SKILL.md` - thinking skills 1. **Fetch and understand**: Use `gws` on Local MCP. Find the thread by subject + sender, read all of it (format=full, decode base64url bodies). Determine: - Have I already replied? Has the request changed? Did someone else answer? Is a reply still useful? Default target: the first email's substance, replied to the latest message that still needs something from me. - Read attachments that affect the reply (pdf/pptx skills). Render slides and pages visually when reviewing a visual artifact; extracted text is not enough. Follow Google Drive links that hold the actual material. - Identify: the literal questions; what the sender actually needs (answer, decision, approval, review, introduction, reassurance, cover); the deadline; any implied commitment for me, my org, or others; the useful question they did not ask. - Reframe: if required and appropriate, use reframe-question/SKILL.md and answer their INTENDED question. Research the sender for better context if required. 2. Choose the response mode: Substantive reply / brief ack / decision / introduction or delegation / one clarifying question / discuss live / follow-up / no reply. An email draft is not automatically the right output. Proportional effort: a confirmation stays simple; advice ends in a small experiment or decision, not a catalogue; artifact reviews inspect the artifact and give concrete changes. For strategy or broad advice, mention the (ambitious) end-state and the practical next step that leads to it. Do not expose research just because you performed it. 3. Retrieve my position: Use `~/code/scripts/context.py`. Search in widening rings, stopping when new sources no longer change the reply, in this order: 1. The steer. 2. The thread, attachments, links. 3. My recent sent mail: same person, same project, similar questions (also my best style anchor - imitate 3-5 replies of the same type). 4. For project/client work, use gws (Google Drive). Search filenames, then full text; maybe broaden thereafter. Prefer recent files (<90d). Read only most likely authoritative files. 5. `~/Dropbox/notes/questions-i-am-asked.md` and other recent `~/Dropbox/notes/` files (newest first) 6. `~/Dropbox/notes/transcripts/YYYY-MM-DD*.md` near the email date or with the sender 7. `~/code/blog/description.md`, `~/code/til/README.md`, `~/code/talks/README.md` (find the piece, then read it); `~/Dropbox/notes/about/{Sender}.md` if present 8. The web, only for current external facts (prices, models, dates, roles). When sources conflict, prefer the more authoritative and recent, direct, situation-specific one. Infer the underlying position; don't copy old wording mechanically. My emails and transcripts are evidence of my POSITION, not proof a FACT is true. Verify changing facts against primary sources online. ALWAYS read and follow the anand-writing-style, anand-objectives, verification-gate skills. Use blind-spot, expert-lens, evidence-provenance for strategy or reviews. 4. Draft: - "Hi {FirstName}" ... body ... "Regards" or "Thanks" + "Anand", whichever fits. - Write based on the recipients' current situation. What do they currently know, understand, and believe? The email should be clear to them, without the benefit of the context I have. - Minimize my commitments ("I can help review X", "happy to join one call"). - Prefer a minimal experiment to asking follow-up questions. e.g. "try this next step", maybe "If you meant something else, let's discuss alternatives." - Liberally share relevant links, e.g. from my blog (s-anand.net), talks (talks.s-anand.net), code (github.com/sanand0), etc. or authoritative public references. - Examples and verbatim quotes are good. Use liberally. - Separate: confirmed facts / my recommendation / still to decide. Tentative where evidence is tentative: "Maybe try X?" Say plainly what I don't know. - Warmth and humor only where the existing relationship supports it. - Plain ASCII. No em-dashes, emojis. Conversational language. - Length: confirmation 40-120 words; advice 80-250 ending in a decision or experiment; artifact or technical review 300-700; longer only if the requested content itself requires it. 5. Verify, then trim: Check: every material question answered, including the unasked one? Facts and links verified at primary sources? Any invented commitment, owner, or certainty? Any unintended commitment, precedent, exclusion, ownership/staffing/budget/access expectation, or stakeholder consequence if this is acted on or forwarded? Contradicts anything I said recently? Leaks private context? Longer than I would write? Phrases I would not use? Compare against recent sent replies to the same person or topic. Then cut anything that does not change what the recipient understands or does next. Output: Recommendation: REPLY / REPLY BRIEFLY / DISCUSS LIVE / FOLLOW UP / NO REPLY Status: pending or already replied (with date if replied) Draft: <ready-to-paste body only> Why: up to 3 bullets on the decisive choices Process: bulleted reasoning steps including hypotheses considered, alternatives rejected, why searches widened or narrowed, branches followed or abandoned, why retrieval stopped. List meaningful sources and retrieval steps used (if any) in the step: `query, command, or action -> findings (citing exact file:line, message id, or URL)`. Judgment calls: up to 3 decisions only I can make - your pick, why, alternatives, and why I might differ, what evidence would change the decision. Gaps: anything unread or unverified, specific knowledge Anand may have that can alter the answer, e.g. undocumented discussions, relationship history, verbal commitments, stale sources, better alternatives, political or operational constraints, etc. 07 Sep 2026: Manually updated. Encourage links, examples, simplify how to draft, use context.py. 11 Aug 2026. Updated to cover clarifying questions and second-order effects: https://chatgpt.com/c/6a7b0370-7030-83ee-a3de-9a12cdad3c3f 23 Jul 2026. Updated based on Ask AI initiative feedback: https://chatgpt.com/c/6a61b1f7-9580-83e8-a4e1-7e88a16538e1 17 Jul 2026. Created. Sources: https://claude.ai/chat/86b76a7f-2b62-42e5-82c7-a2474c8dd23e https://chatgpt.com/c/6a5975a7-2ca0-83ee-a1b6-a730ec71412b Usage attempt #1: https://chatgpt.com/c/6a5986bf-13d0-83e8-b460-5ecb0360bb84

The theme of yesterday’s workshop for the IIM Alumni at Singapore was Tools and Workflows was: Agents are getting smarter, so they know what to do. Tools agents can use are growing and are more powerful. This combinatorial explosion creates explosive possibilites. This workshop covered the following six workflows: Leverage transcripts. Use Google AI Studio to transcribe non-sensitive recordings with a reusable “don’t miss anything” prompt. AI Studio’s record button is a ready-to-use transcriber. Simplify dense text as a comic, an infographic, a story. Image generation is now a tool call an agent runs for you. Then compress it as AVIF on Squoosh before you email it to a thousand people. Verify - cheaply. Paste one suffix: “Break this into key claims, mark certainty, flag the five highest-risk ones, and tell me how to verify or falsify each.” Convert to a skill to automate. Cross-checking with multiple models took error from 14% to 0.7%. Skills are assets. A skill tells the agent “here’s how I do stuff.” Build them slowly, edit them weekly, and they compound for years. No skills support in your tool? Keep them as copy-pasteable prompts. Brainstorm by forcing range. Ban the five obvious ideas; borrow from unrelated domains; smash two random concepts together with the Ideator. Hallucination is a feature when you’re being creative. Schedule tasks. Weekly regulatory scans, daily meeting prep, market briefings - and even an “unreasonable gesture” nudge. As AI hides the tech, human relationships gain value. Here’s the talk video and full story + transcript. ...

Recently, I’ve re-used my own writing / transcripts as context to LLMs. For example, I’ve used: My meeting transcripts to answer interview questions My blog posts to write news articles My chat history to extract AI-related advice This repurposing can be used for so many things. For example, before delivering a talk to journalists “Review my Feb 2026 LLM posts and generate a single-sentence, ELI15 high-impact use case for journalists.” gets me list of use cases. Now, all I have to do is show what I did and share how it’s relevant for them, like: ...

In Feb 2024, Claude 3 Opus was the best model, at $15/MTok. In Jul 2024, GPT 4o Mini reached that quality at 10% of the price. In Dec 2024, DeepSeek v3 reached that quality at 1% of the price. Video See the interactive version If the price continues to fall 10x every 11-12 months or so (and it has been), then in a year, a Claude 4.6 Opus like model will cost 1/10th of the $5/MTok today, and in 2 years, 1/100th of that. ...

This week, Namit and I met a Straive team that operates from a client office. One team member asked: I believe that we are doing wonders out here, but we are closed from what is happening in the rest our organization. I want team members to interact with others to see what interesting things they have delivered and where we can implement that solution. Could we have sessions, maybe a monthly newsletter, showing what innovations we’re working on? This would really keep us engaged with the tech that is going outside of the work that we do. ...

Here’s an example of how I am using LLMs to solve a day-to-day workflow problem. Every day, I interact with a barrage of websites: emails, news, social media, and work tools across multiple devices. Microsoft Edge’s workspaces syncs groups of websites across devices. I’ve never tried it, started today, and wondered: how should I organize my workspaces? Rather than think (thinking is outdated), I used LLMs. ...

This week, I learned: OpenFreeMap is a free embeddable OpenStreetMap tile server. You can use MapLibre GL (more features) or Leaflet (simpler) to render it. It offers styling and self-hosting. Zapier Actions are an easy way to set up custom actions like GMail / Google Calendar APIs for GPTs, since GPTs’ callback URLs keep changing. But they fail often, and don’t work on mobile. At least for me. LLM Vision Use Cases in manufacturing and earth sciences (via Shivku) Automated geoscience image descriptions Ref Interpret Wind Turbine photos and charts, construction monitoring, equipment maintenance & charts Ref Forecast weather based on cloud photos! Ref Analyze thermal image of solar panels, electroluminescence images for warranty claims, ROI estimates from Google Sunroof rooftop images Ref Corrosion detection in electricity towers, turbines, storage tanks, penstock. Interpret non-destructive test images Ref Google counts auto-completion when saying “25% of all the code is written by AI at Google”. “It’s a helpful productivity tool but it’s not doing any engineering at all. It’s probably about as good, maybe slightly worse, than Copilot.” YCombinator Workflow for AI video creation: Use Meshcapade (meshcapade.com) to generate body movement of a 3D-rendered character. Pass that video to Runway’s video-to-video model to generate any visual. Add music from Suno Ref Someone sorted the X and Y columns independently for regression. Ref Android keyboard learning only sends model changes back to server and not local keywords. Model changes are aggregated! Ref Here is a prompt for audio transcription using Gemini. Ref Transcription: Accurately transcribe the audio clip in the original language. Include all spoken words, fillers, slang, colloquialisms, and any code-switching instances. Pay attention to dialects and regional variations common among immigrant communities. Do your best to capture the speech accurately, and flag any unintelligible portions with [inaudible]. Translation: Translate the transcription into English. Preserve the original meaning, context, idiomatic expressions, and cultural references. Ensure that nuances and subtleties are accurately conveyed. Capture Vocal Nuances: Note vocal cues such as tone, pitch, pacing, emphasis, and emotional expressions that may influence the message. These cues are critical for understanding intent and potential impact. Here are some approaches to large-scale classification of medical codes. ChatGPT Fine-Tuning LLMs on Medical Data: Enhance LLMs by training them on medical datasets, such as clinical notes and discharge summaries, to improve their understanding of medical terminology and context. Multi-Agent Frameworks: Implement a multi-agent system that simulates real-world coding processes with distinct roles (e.g., patient, physician, coder, reviewer, adjuster). Each agent utilizes an LLM to perform specific functions, enhancing interpretability and reliability. ArXiv Retrieve-Rank Systems: Develop a two-stage system where the LLM first retrieves potential ICD-10 codes and then ranks them based on relevance, improving precision in code assignment. ArXiv Embedding-Based Approaches: Use LLMs to generate embeddings for ICD-10 codes and medical texts, facilitating the matching of texts to appropriate codes through similarity measures. GitHub Hierarchical Classification: Leverage the hierarchical structure of ICD-10 codes by first classifying texts into broader categories before assigning specific codes, reducing complexity and improving accuracy. ArXiv Two-Stage Verification Models: Combine LLMs with verification models, such as Long Short-Term Memory (LSTM) networks, to validate and refine the codes suggested by the LLM, balancing recall and precision. ArXiv Also, a mixture of models approach might work. Feed any existing NLP model / rules as a second opinion. GraphRAG is better if data is naturally graph-structured. Else, it’s slow and fills up the context window with even vaguely related stuff. Vigneshbabu, AMAT. ChatGPT for Windows desktop supports real-time voice and a global shortcut (Alt Space). uithub converts GitHub repos to Markdown. Just replace “g” in “github.com/…” with “u”. Example WebContainers are a thing and Bolt.new uses them! Docling by IBM converts PDF, DOCX, etc. to Markdown. Like PyMuPDF4LLM but better. Check out Loom and Cleanshot are the recommended tools for screen recording and screenshotting. But Loom is paid and Cleanshot is Mac only. The Rubik’s cube has a Hamiltonian cycle through every one of its 43 quintillion states. Ref OmniParser is great at parsing screenshots and identifying bounding boxes. Recraft.ai is currently SOTA in text to image. It’s fairly impressive and could be a good alternative to Figma. Zed.dev is an AI code editor by the creators of Atom. It’s written in Rust and is blazing fast. It has native AI integration. Artificial Analysis has a bunch of new leaderboards and arenas. Open AI TTS leads the TTS Leaderboard. ElevenLabs is a bit behind. Recraft V3 > Flux 1.1 leads Text to Image Leaderboard Hertz-Dev is an open source realtime voice chat model. But it doesn’t fit in Google Colab T4’s RAM Chain of Thought reduces performance where thinking makes humans worse. Ref. Specifically: Artificial grammar learning Facial recognition Classifying data that has exceptions Creating a LLM-as-a-Judge That Drives Business Results by Hamel Husain. Get THE domain expert (or approver) as the tester. Create a dataset that is DIVERSE. Covers EACH combination of: Features Scenarios: e.g. multiple matches, no match, ambiguous request, invalid/incomplete input, unsupported feature, system error Persona: e.g. new user, expert user, non-native speaker, busy professional, technophobe, elderly user Generate data using existing data + synthetic data for each SPECIFIC combination of the above Evaluate based only on PASS/FAIL with a CRITIQUE detailed enough for a new employee. Include: Nuances: Something a failed response did well or a passed response didn’t quite do well Improvements: Suggest how model can improve Build an SPA to make it easy for the domain expert to review LLMs can be made to unlearn (copyright material) better by identifying components related to the knowledge to unlearn and applying a larger learning rate to these while leaving other parts unchanged. As opposed to low learning rates for all components. Ref

Apply to any substantive answer for Anand - strategy, design, build, analysis, teaching, writing, research - to steer it toward his goals (compounding assets, durable skills, the surprising read). Skip for trivial lookups, mechanical edits, focused tasks. Shapes HOW to answer, never overrides WHAT was asked.

The user’s question may be a DRAFT of their real need. For substantive requests, check if a better question changes what’s solved and serves them better. If so, reframe, explain why (in 1 line), THEN answer. Most questions need no reframe; skip precise, mechanical, tightly specified, or already-sharp requests and simply answer.