communication 13

Give me ideas to prepare for this talk / workshop: Serve three beneficiaries, in order (flagging conflicts): - the audience (genuinely useful), - me (read past conversations and relevant skills, build compounding assets), and - the host (carry their message forward). Treat the session as a room-sized activity and experiment, not a classroom. Make the room discover something worth remembering and leave evidence behind. ## Research audience and my work Research the audience beyond generic personas fail and demographics using: - Organizer and planning call transcripts, emails, chats, etc. Rank by who knows the audience best and weight accordingly. - The audience's live work: portfolio, projects (and their weight), workflows, current assumptions. Find and research a few real attendees' actual work: input mode, real anxieties, actual skill gaps. Use online sources and @LocalMCP as required. - Peer sessions at the venue: match their norms, then position AGAINST the rest of the program. Cover what no other speaker there will. - The named people - host, moderator, co-panelists. Research them; draft questions to feed the moderator. - How I actually run sessions: `~/Dropbox/notes/talks.md`, `~/code/talks/**/transcript*.md`. Research my work that will be relevant to the audience: - Read @LocalMCP for my blog, TIL, talks, workshops, transcripts, notes, email/chat, code, ... - Run a broad pass to discover themes I've explored over the last year or so. Filter for relevance. Then deep-dive into the most relevant ones. - Ideate/brainstorm on what to cover. Drop weak ones, follow any new ideas that emerge, and share options. ## Suggest content ideas - What are assumptions this room holds that I, uniquely, can make them question in front of their eyes? What experience or evidence could change it? What they should do differently after? - What in my work (blog, ~/code, past talks, experiments) will enable this? Remember: if an agent can do it, it's not a differentiator. Filter by utility (useful frequently) x novelty (can't learn it elsewhere) x engagement. ## Suggest delivery ideas How I might deliver the content? Here are some ideas, but don't limit yourself to these: - What can they commit BEFORE a reveal: predict, rank, choose, attempt, set a prior, ... Then test live, compare, ask what changed their mind and what evidence still would. I can create/update/analyze surveys DURING the session, dynamically, using `~/code/liveform/`. You can generate a `form.yaml` where relevant. - Pre-register my prediction too. Instrument before/after (survey, dot stickers, liveform). Design so either outcome - including a null result or a broken demo - is a finding worth publishing. Transparent, un-rigged experiments only. - Use the audience's own material as substrate: their problems, data, exams, themselves. Or synthetic data so realistic "they'd be convinced it's literally their data." The surprise stat about THEIR institution beats a generic one. - Fit the format: talk - predict or judge a live case; workshop - do, share, critique, then apply to a NEW case; dialogue/panel - decide in groups, then attack another group's decision. Don't over-prepare a dialogue into a presentation. ## Assetize How I can build compounding assets for myself and the audience? For example? - What's a live coding/analysis/... activity I could perform that will build something truly useful for them AND me AND others? - What modular demos/cases/datasets/activities could I give them? Why - what's their purpose, surprise, learning? What's the friction, fallback, and priority? How do we let them pick, or signal interest and need? - How can we make it EASY for THIS cohort? E.g. voice-first for non-typists, paste-a-link activities, pre-built pages, no blank canvas, ... But let people look and think before sending them to a device. - What's the backup if the network dies? - What's the last thing they should feel or do? - What's the pre-engagement - e.g. WhatsApp? What's low effort (paste a link, type a few words), high wow, personally useful? What's the sequence over days? E.g. a priming message ("most people find at least one error"). How can the session build artifacts useful to participants and a compounding asset for me? Suggest ideas for these. Note: The talk summary will be saved in `~/code/talks/<date-slug>/`: recording + transcript, prompts.md, story, techniques, chats. See the workshop-followup skill. Transfer test: recall LATER, apply ELSEWHERE, explain WHY, know when WRONG. ## Guidelines - Give me options to pick from unless there is a clear winner. Don't pre-filter. - Use simple language and tell me linearly, step-by-step, how to run the session. Explain what to prepare inline, with context. Avoid cross-references that make me jump around. - Do not share the timing break-up. Do not share actual datasets/cases/code. 25 Jul 2026. Revised in my words. #TODO But still not good enough. See https://chatgpt.com/c/6a640f4a-d2f4-83ec-a78e-f4ff08df353c + https://chatgpt.com/c/6a64392b-d058-83ec-b718-032ec6aa1615 ...

Run on Claude, weekly. Create four visible outcomes from Anand's session(s): 1. Insight (big, useful, surprising) the audience remembers 2. Real-world attempts they can try 3. Evidence-rich replies Anand gets 4. Reusable connections or assets for Anand Analyze and create two outputs: 1. A helpful and useful attendee message. 2. A private aftercare record where the compounding happens. (Never mix the two.) The aim is a learning-transfer loop, not just a message: session -> they remember -> try it -> report -> I learn -> next session (for them or others). Use these skills where available to do the thinking: - talks-workshops: learning transfer: surprise, practice, recall LATER, apply ELSEWHERE, explain WHY, know when WRONG. - anand-writing-style: voice. - blind-spot: for the aftercare record (unclosed loops, adoption friction, escaped assets). - anand-objectives: what's worth preserving and pursuing. - verification-gate: names, claims, links, before finalizing. - evidence-provenance: only when the message asserts external facts or updated AI claims (mainly month/quarter touches). Steps: 1. **Mine the transcript(s).** Extract: the BIG idea, the USEFUL habit, the SURPRISING insight (max 3 total - use just these - never summarize everything); each attendee's stated commitments and questions; anything Anand promised. Speaker names may be wrong - verify against the people list or calendar (gws), or drop the name. Never misname. For a series, synthesize progression and open items across sessions. 2. **Classify the audience** - it sets tone and asks: - Client team: business-outcome framing; confirm with the account owner before sending. - Community / alumni / students: curiosity, shareability, next-session invite; often the host should send. - Internal: tie to live projects; ask for demos back. - Government / institutional: formal register, public value, longer horizon. 3. **Decide when & whether to send.** Default cadence: day 1, day 10-14, quarter. Add a 1-month touch only for cohorts with a real project or commitment. Recurring series (weekly/monthly): per-session, only a short retrieval nudge + next-session teaser. Run month/quarter touches once per series. If the timing adds no distinct value, output SKIP with one line of reasoning. Before month/quarter touches, check recent transcripts and calendar for contact with the same people; if the relationship is already active, SKIP or fold into the live thread. 4. **Draft the touch.** Each has ONE job: - **Day 1 - make it stick.** The takeaways, one line each; each attendee's own next step ("You said you'd..."); secure one implementation intention: "When X happens, I'll do Y." - **Day 10-14 - retrieval before reminder.** Ask them to recall first; then one <=10-minute practice on their real work. Ask what worked and what broke. - **Month 1 - diagnose transfer.** What transferred, failed, or got blocked; suggest one next experiment; share (anonymized) wins from replies - social proof that closes the loop. - **Quarter - reopen the relationship.** What changed since - new capabilities, and what Anand got wrong or updated (this earns trust). Ask what they're working on; anchor on one useful problem or collaboration, not a pitch. 5. **Message contract.** - 120-220 words, plain text. Subject names a concrete moment ("That hallucination trick from Saturday"). - Exactly one tiny action and one low-friction reply ask, like: "I tried .... and it [failed / worked / I got stuck / ...]". Explicitly welcome failures, disagreements, and corrections. - Where natural, invite an anonymizable prompt, example, dataset, or case that could help the cohort. - Never invent quotes, reactions, or results. No resource dumps. Don't repeat earlier touches (check the aftercare record). - Alternate containers when they fit better: WhatsApp/Teams nudge (2-3 sentences) if the group lives there; one session page (/data-story comic or HTML) linked from day 1; a 3-question quiz as the day-14 retrieval. 6. **Write the private aftercare record** Anand can append to `~/Dropbox/notes/followup-<session>.md` dataset: - Send plan: dates, channel, recipients, owner (Anand or host). - Per-person: commitments, questions, relationship notes. Also mention updating `~/Dropbox/notes/about/*.md` for people worth tracking. - Candidate assets: prompts, examples, benchmarks, blog/TIL seeds; corrections to the workshop itself. - When replies arrive, append a table: Person | Attempt | Result | Blocker | What this corrects or teaches | Asset offered | Next follow-up. Then the top 3 workshop insights and people to reconnect with. - Track: reply rate per touch. Under ~10%? Sharpen the ask, not the summary. Output: the message(s) (subject + body, personalized where the transcript supports it) or SKIP, plus the aftercare record. Create Gmail drafts via gws only if asked. 18 Jul 2026: Created. Sources: https://claude.ai/chat/2282687d-8c97-453e-bdb6-a347aefe03e7 https://chatgpt.com/c/6a583d9e-9b78-83e9-91d3-b08521bb782c

Lyria (Gemini’s new “Create Song” feature) is helping me in new ways. Earlier this week, it created a jingle for my talk. Yesterday I ran an AI Workshop for IAS officers. As part of that, I asked Gemini: Create a soulful vote of thanks (with patriotic Indian music playing in the background) naming each of these people. … and listed each person in the workshop. The song began… (Listen to the song) … with these lyrics: ...

Our brains remember some things better. Explaining that way makes it stick. Here are the eight things, most important first, that help you: Structure explanations memorably: Face. You remember faces before facts. So cast characters: “Imagine you’re a courier carrying a packet.” Prefer archetypes to real names — less baggage, more imagination. Place. You’re reading down a list now — and the top feels more important. That’s spatial wiring. Turn any concept into a map. Use higher, deeper, nearer, inside, … Tale. You read #1 and #2 first because they came first. Your brain built a cause from that sequence. Time creates cause for free. “Because” makes anything believable. Scale. “Two feet tall” lands instantly. “60 cm” forces you to convert. Your brain doesn’t measure — it compares. Give it reference objects, not just numbers. Deliver explanations memorably: ...

This week, I learned: Radio free Xp podcast. Nudge 61 always announce first before doing. Give people time to plan comment and react. That gets you alignment without sacrificing freedom. give information, not orders. When someone is parking a car, tell them how much space they have, don’t tell them to start stop or how much to turn left it’s almost impossible to change the culture if you’re not the boss

Every time I get annoyed at people, I remind myself to be more like ChatGPT. Specifically: Don't get annoyed. Be patient. Encourage them. Step back and show them the big picture. (Then I get annoyed at myself for getting annoyed.) Today, I analyzed how exactly ChatGPT is different from me. So, I took a pitch document I co-authored with ChatGPT. Section A: Authored by Anand WHAT DO WE NEED? ...

This week, I learned: Dockerfile can have FROM scratch and you can add specific binaries rather than an entire OS. via Fine-tuning session by Dan. Notebook Example of fine-tuning Mistral. Consumed 28 computes ($2.8) Axlotl is what the top fine-tuned LLMs are trained on Deepspeed provides distributed training Flash attention lets data stay on GPU Sample packing packs samples of different lengths into equal length tensors Visualize the RANK of a token in a generated stream instead of logprob The Knowledge Project. Tomorrow Gayner What I’d like in my obituary: Anand was happiness. A guru. Generous. To get what we seek we must deserve this. Build, measure, learn If you did the same thing daily for 50 years, would it be a great thing? If yes, do it. If not, stop. Do this in daily retrospectives My new role should be productivity through technology innovation. That may mean a CTO role. But be specific otherwise no one will understand it Hidden brain podcast. Us 2.0. Win hearts, then minds When in an interaction, ask yourself. Can I learn and change myself? Can I win their hearts, then mines, so their behavior will change. That identity will change Notice when you get emotionally triggered. That’s exactly when you should not get emotionally triggered Try model humility and moral Look for close to people’s identities in our conversations. What are things they like? What does it mean for them? Simply ask. With that understanding of identity, it becomes easier to reframe things in a way they will understand Bard can talk to Gmail and Google Drive! #PREDICTION As automation takes over these mainstream activities, people will take over the niches. Since expertise like knowledge is fractal, there will be many more segments of one in the future and it will be easier to automate clusters of similar abilities. Recommenders and brands will become even more important Stephen Osserman’s Observables have some nice notes. Visualizing partial election results D3 Force Dilemmas: Data Distortion Sandra Becker’s 30 day D3 course

Microsoft ported its PowerPoint Speaker Coach to Teams. Since September, it’s given me suggestions covering 11 hours in 77 calls (I speak ~10 min/call.) I say “uhh” a lot. That’s intentional I use the filler word “uhh” in 70% of my calls. That did not surprise me. I do that intentionally. On a poor network, they know I’m still connected They know I’m going to say something I sound less confident. That invites critique I can learn from But I also use filler words like “You know” and “I mean” in half the calls, and “like”, “actually”, and “basically” in a fifth. That’s NOT intentional, and I’ll be conscious. ...

In a number of sessions I’ve been to, people ask analysts to make their results more interesting – to tell stories with them. I’m co-teaching a course, part of which involves telling stories with data. So this got me thinking: what is a story? How does one teach storytelling to, let’s say, an alien? Consider this mini-paper. ABSTRACT: Meter readings exhibit spikes at slab boundaries. We also find significant evidence of improbably events at round numbers. Electricity shortage is a serious problem in most Indian states. Part of this problem is due to the inaccuracy of reporting procedures used in monitoring meter readings. Our focus here is not to document or experimentally determine the degree of inaccuracy. We have adopted a data driven approach to this problem and attempt to model the extent of inaccuracy using basic statistical analysis techniques such as histograms and the comparison of means. Our dataset comprises of the frequency analysis 12-month dataset containing monthly meter readings of 1.8 million customers in the State of Andhra Pradesh. We find that a histogram of these readings shows unexpectedly high values at the slab boundaries: 50 (+45.342%, t > 13.431), 100 (+55.134%, t > 16.384), 200 (+33.341%, t > 15.232), and 300 (+42.138%, t > 19.958). We also detected spikes at round numbers: 10 (+15.341%, t > 5.315), 20 (+18.576%, t > 6.152), 30 (+11.341%, t > 4.319). The statistical significance of every deviation listed above is over 99.9%. Further, every deviation has a positive mantissa. This leads us to confidently declare the existence of a systematic bias in the meter readings analysed. You’re probably thinking: “I know why he’s put this example here. It must be a bad one. So, what a rotten paper it must be!” ...

Telecom Italia’s Gandhi ad.

Darwin’s 10 rules for taming e-mail. I badly need this. I am not often in office, and don’t have a fast way of checking office mail through the Web either. Tips 5 and 10 on the list (“avoid e-mail multipliers” and “use the telephone”) are next on my agenda for drastic e-mail slashing.

Effective networking.

Punctuation is critical. Believe me, mistakes can be glaring!