Sasha Dichter

Subscribe

Author: Sasha

  • Using AI to Make Chicken Tortilla Soup from the Taco Project

    I’ve written before about how AI is a 90% expert: smarter than 90% of the people on most topics. And that was a year ago, so I’m sure the number has inched up.

    The question is not how good the AI is, the question is: what do you use it for?

    There are millions of industrial-use applications: at 60 Decibels, we’ve been cooking up artifacts in Claude like they’re going out of style; our engineering team is in overdrive; and timelines for our Impact Ecosystem Map and for our Signal product keep getting faster.

    But if you’re not already on the AI train, all of that might feel a few too many steps ahead.

    So let’s talk about cooking instead.

    For a while, my wife and I have wanted to replicate the chicken tortilla soup from the Taco Project. It’s a little bit smoky, has a deep flavor and an intriguing mix of spices. The thing is, they’ve not put the recipe online, no one seems to have posted about it, and there are hundreds of chicken tortilla soup recipes out there.

    This weekend, ChatGPT and I set out to solve this problem.

    Here were my prompts, in order:

    • I want to make chicken tortilla soup like the taco project
    • Is this better or worse in an instant pot
    • Ok let’s do it normal. I have homemade broth. Make me a shopping list
    • Can I get them [dried guajillo peppers] at Whole Foods [aside: no, I went to El Mercato instead]
    • Ok I want you to look a bit harder for the taco project version [it found customer reviews of the soup and asked me a handful of questions about those reviews, to which my responses were along the lines of ‘It’s pretty red and tomatoey. It’s not like chicken broth’]
    • Quickly compare this to other top rated recipes online and explain the difference
    • Ok let’s incorporate Rick Bayless’s technique—give me the instructions with that incorporated
    • Are you sure I’m just adding the chicken breast whole? That seems not great how will it end up w the right texture

    This set of discussions got me to a finished soup, and this is where it got interesting. The soup had potential, it looked right, and the texture was good, but it didn’t taste right at all, so we started talking again.

    • It’s close. It was tasting kind of acidic and flat. I feel like I cooked it a lot. I added salt because the homemade broth has very, very little. Probably a full teaspoon, maybe more, and I added another half a lime’s juice. It’s brightening up. I will say the Taco Project one has a creaminess to it, and I’m just trying to figure out what to do because it’s generally good. It’s close, but it’s not there yet.
    • [It asked some more questions, one of which I replied:] The Taco Project one is smooth and velvety, it doesn’t seem to have cream in it

    It instructed me to cook 2 soft corn tortillas in a skillet with the broth, add that plus some olive oil to the blender, blend that to emulsify the oil, return to the pot and cook some more.

    • That helped. It’s still a little tomato acid forward.

    It suggested I add another ½ cup of homemade broth, ¼ teaspoon of sugar, and adjust the salt.

    • I added more like a half a teaspoon of sugar, another half a cup of broth. I had already added an extra half a cup of broth before.

    It reflected on my changes and asked how it tastes now (aside: I talk to ChatGPT, I don’t type)

    • Yeah, this is closer
    • The texture is right. It’s probably a little thinner, but it’s good. The flavor is just a tiny bit on the acid side, and it’s just a little flat. Doesn’t have quite as much depth. I wonder if they put more fat in it.
    • Can you give me a printable version of the recipe w all the changes I made at the end including the salt and sugar

    My reflection is: when I asked it for a starter recipe, what I got back was a slightly more convenient version of search. That is nice and helpful, but a 90% expert to find a good chicken tortilla soup recipe is not so interesting.

    But a 90% expert around “this is how my soup (a recipe I’ve never made before) tastes, this is what I want it to taste like, help me adjust it” is not something I had access to before. It’s like having a good, experienced chef in my kitchen.

    The point is: the thinner you can slice a problem, the more likely it is that your favorite AI tool will be a game changer. General expertise has been at our fingertips for decades, but advice specific to my exact situation and preferences? That’s new.

    Here’s how it came out.

     

    And here’s the recipe if you want to give it a go. I should note that I am leaning in to healthy fats so this uses olive oil which I suspect is not traditional.

     

     

  • Two jobs at once

    All the data on multitasking notwithstanding, on any project that requires real thinking, today it feels like the only answer is to do two jobs at once.

    Project 1 one involves big data dumps, Q&A, or long voice notes that Claude or your favorite tool are then processing for a few minutes at a time.

    Project 2 can be just like project 1, or it can be easier-to-move-through work of any kind.

    After years of learning to work on one thing at a time, I’m finding myself pushing on parallel paths more than I’m used to. Otherwise I’m waiting around for Claude in ways that don’t feel productive.

  • Instinct: My AI Assistant

    A couple of weeks ago I was sitting with a fellow board member the night before a Board meeting.

    We were talking about simulations—AI-powered tools that create digital twins of people who then can be surveyed. I find this topic fascinating (and a bit terrifying), and have mostly been of the view that digital twins, by definition, will tell you the 80% that was easy to find out and leave out the 20% that really matters.

    He shared that he thought there was more potential than what I was describing, and told me about a podcast with the founder of Similie.AI that I should listen to. When I asked him to send it to me, he took out his iPhone, opened up text messages, and said: “Send Sasha from our Board the Similie.AI podcast that I listed to the other day.”

    And, from that alone, I received the following email:

    Subject: Latent Space on Similie

    Worth a listen: Latent Space with Joon Sung Park on Simile – building digital twins that simulate how people behave and make decisions, now running tens of millions of simulations for Fortune 100 clients at 85-99% accuracy vs. human focus groups.

    Thought of you and 60 Decibels.

    https://www.latent.space/p/simile

    Even with all my exposure to AI, this felt a bit like magic, so I asked him how he did it and he invited me on to the beta rollout of Instinct, which I’ve been using for the last few weeks.

    Instinct is a text-based AI (meaning I use it on iMessages on my iPhone). I suspect the tech behind it is not particularly revolutionary, but the texting interface has changed my daily operating rhythm significantly.

    My first step, scary as it was, was to give Instinct access to my Gmail, calendar, and Google Drive. Then I started texting with it.

    It became clear that it could fill a gap as a very, very useful personal assistant.

    Here are a bunch of actual texts that I’ve sent to Instinct in the last week:

    • Mark my calendar as OOO (so busy for scheduling purposes) Mon to thurs next week for my trip to Europe. Decline all my internal meetings for next week besides Friday.
    • I need to remember to keep or cancel my Amsterdam Airbnb by sunday but remind me midday Friday
    • What is [Name] phone number, he’s been slow to reply on email so if I don’t hear back by tomorrow I’ll text him. Remind me.
    • What’s the latest on our conversation with [client] about [topic]?
    • Email [Name] telling him I sent the payment asking him to confirm
    • And let’s keep track of this I need to talk to [NAME] to figure out what time works, but if you’re able to see about wed afternoon that’d be great if not, I’ll do it
    • What happened with [name] who I spoke to last week? I feel like I need to nudge her
    • Remind me Thursday to write a blog post about using Instinct (!!)

    What’s been interesting is that, despite the tech being “simple” (for today’s LLMs), the form factor radically changes how I use Instinct, specifically:

    • A texting bot is just different than opening up the Claude app (I suspect this is 100% behavioral on my part)
    • Speed of responses is high, so I use it for a different set of things
    • I cannot help but personify it a bit—I didn’t realize, when I downloaded it, that my use case was going to be “personal assistant” but that happened quickly and naturally

    My main use case is:

    1. Have a thought about something I’d like to do (work or non-work related)
    2. Send a text to Instinct
    3. It gets it 95% done and asks me to confirm it can go ahead and take the action

    The net result of this is that thoughts that occur to me quickly (and fleetingly) get taken care of with almost zero effort, meaning many fewer things get put off.

    When a bunch of low-but-not-zero-effort tasks become, essentially, zero effort—accept those 5 meeting invitations; tell me all the email I’ve gotten today that looks like spam and clear them out; check on the status of X—the effect is to (1) Lift some load from me; and (2) Get a lot of small tasks taken care of; (3) More space is freed up for more meaningful things.

    All of that, together, creates a surprising amount of leverage.

    Instinct is still in Beta but I have some invites—if you’re really interested give me a shout.

     

  • Three Hours for Wicked Problems

    Writer Neil Gaiman, author of Coraline and many other eerie, magical books, has a powerful, simple rule for writing. He sets aside a period of time each day in which he can either:

    1. Write
    2. Do absolutely nothing

    There is no obligation to write. However, there IS an obligation not to read, scroll, create a to do list, cross things off a to do list, exercise, walk, or do…anything.

    Gaiman’s reflection is that, eventually, writing becomes more appealing than doing nothing, and he will eventually write.

    We’re not all writers, but we do all have wicked problems to solve—some as wicked as staring at a blank page and having to figure out how to fill it up.

    When we fail to move forward on our wicked problems, I’d assert that we’re probably not following Neil Gaiman’s advice.

    For your next wicked problem consider this slight adaptation. You can:

    1. Work on your problem (including using search, reading about your problem, and using AI)
    2. Do absolutely nothing

    (It will be more difficult to hold the “do nothing” line, because once you’re on your computer using tools, the pull to everything else will be strong. But I believe in you.)

    We don’t get stuck on wicked problems because they are too difficult to solve, we get stuck because they are wicked, and once we hit our first roadblocks, usually 10 minutes in, we switch gears and turn to other things.

    Hence, the Neal Gaiman-inspired three hour wicked problem block.

    You set aside three hours, and can either work on your wicked problem or do nothing (NOTHING!) else.

    Bonus: thanks to AI, you’re not alone, you have infinite access to a researcher, a devil’s advocate, a librarian, an analyst…even to (virtual) fellow travelers.

    I’m convinced you’ll make enormous progress if you do this once, twice, even three times this week. You just need to devote your time to your wicked problem and to nothing else.

  • EWIMO writing

    It’s become horribly easy to spot AI writing. The false tension. The emojis and em-dashes.

    A partial solution is to teach your favorite AI tool not to write like that. I have a Claude .md file that instructs it to avoid negative parallelisms, bold-first bullets, filler transitions, and too many em-dashes. This way, if my Claude were giving advice on a chicken recipe, it would never say things like:

    Not a stew. Not a soup. A braise.

    Three hours. One pot. No shortcuts.

    This isn’t dinner — it’s an argument about how you spend a Sunday. Everything from the sear to the silence at the table is part of the same tapestry.

    The lid goes on.

    And then you wait.

    While this is all humorous, it’s everywhere, and our tolerance for it speaks volumes.

    The old tells for “I didn’t care enough to do a good job on this” were typos, unfinished sentences and numbers that didn’t add up.

    Now, everything that’s error-free but screams AI sends the message: “I phoned this in, so don’t trust me.”

    The way you avoid this is by actually doing the work: rereading each word, thinking about it, acknowledging that “I sent this” means “these words faithfully represent me and my best thinking.”

    There’s no problem using the tools to help you, but you have to practice EWIMO writing, always.

    Every word is my own.

  • Never Do, Can Do, Must Do

    During COVID, I got hooked on the NY Times Spelling Bee. It was the perfect daily diversion – hard but not too hard, required thought but not too much, getting a pangram (word that used all the letters) was SATISFYING.

    After a while our family discovered that Queen Bee was achievable: a badge for getting every possible word on the board. That became the new goal, and so ensued a nightly activity for me and my wife to get Queen Bee.

    A few months in, the bloom was off the rose. It went from pleasant diversion to an obligation. My eyes would be itching with fatigue as we worked at Spelling Bee at bedtime…

    Over time, we all stopped playing.

    Looking back, I see a common six month arc: Spelling Bee, and then Queen Bee, went from Never Do >>  Can Do >> Must Do. And the addition of Queen Bee as a Must Do, which felt fun at first, ended up taking all the fun away.

    We can notice this evolution across anything we do, big or small, throughout our day, by asking three simple questions:

    What do we Never Do?

    What Can we Do?

    What Must we Do? (each day)

    The Never / Can / Must classification is just a lens for looking at how we spend our precious hours—the things that have become our habits, which, taken as a whole, are the foundation of our well-being, our health, our social connection.

    The reflection is simple: of eating is a Must Do, but what is animal protein? What about eating our bodyweight in grams of protein each day? Having something sweet at the end of every meal? (a Must Do of mine, lately)

    Similarly, we sleep every day, but is our Must Do at 5 hours or 8?

    And when does something fun and optional transform into something obligatory?

    Take my use of Instagram (please!). I only really discovered Instagram in 2022 (someone showed me Reels), and it flitted between Never Do and Can Do for a few years. Then, 18 months ago, it landed solidly in my Can Do, and 12 months ago—if I’m honest with myself—it tipped into the Must Do category, so much so that I set a 30-minute daily limit on my Instagram app (which, because I’m human, I occasionally override). Depending on the week, I’d hit the limit one day, then two, then four…. I didn’t like the trend. My solution was a weekend reset—no Instagram at all—and a conscious choice to get Instagram out of Must Do and back into Can Do where it belongs.

    With that in mind, I’ve made a much longer list of activities, and honestly categorized them into Never Do, Can Do, and Must Do. It’s a pretty simple way to map out what my real priorities are.

    You might try it too. Bonus points if you grab two different color pens, and make one X for Today and another one for Goal. I’ve left you a blank list you can print out at the end of this post.

  • On AI-generated content, trust, and gatekeepers

    Today, I received, by email, a great article by Woody Allen on antisemitism.

    Except that it wasn’t written by Woody Allen, it was fake and was written by AI.

    That got me thinking about how media and publishing work.

    For a long time, we lived in a world of gatekeepers: a few network TV channels, a few trusted newspapers, and a few trusted publishing houses.

    We’ve since had a few decades of the long tail: from cable news to the internet to social media to podcasts, everyone has become a content creator as the gatekeepers’ power has faded.

    We’re now entering an era where anyone can create content that looks like it was created by someone else (a column by “Woody Allen,” a book by “Ann Patchett”), and our ability to distinguish between what’s real and fake will keep decreasing.

    How are trust and provenance established in this new world? Will the pendulum swing back to a greater role for gatekeepers?

    I’m not saying we’ll go back to four networks, or that self-published books will disappear (they’ve gone from about 100,000 a year in 2011 to more than 2.5 million in 2025).

    Rather, I’m asking: if anyone can use AI to write a column that looks like it was written by anyone, isn’t the only way to tell who wrote that column to see where it was published?

  • You Can’t Rush Deep Work

    Deep work isn’t just about setting aside time in bigger blocks, or about putting down the phone and turning off notifications—though those are good places to start.

    Deep work is about the qualities of this sacred time you’ve set aside.

    Think of the adjectives you’d use to describe deep work: focused, calm, exploratory, curious, lateral, creative, settled, playful, generative, spacious.

    While there’s some overlap with how we’d describe our “non-deep” work— with words like efficient, bounded, clear, pace, and decisive—this overlap is probably small.

    When moving between the two types of work, I sometimes struggle with how I experience time.

    In regular work, time comes in small(er) increments. It exists as a helpful constraint to drive clarity and decisions. I’ve trained myself to get a lot done in 10 or 15 minutes, and that feels both comfortable and normal.

    For deep work, I create blocks of time, but that’s just the beginning. My job is to hold the space I’ve created: the larger block of time is permission, so when I enter that larger space, I have to adhere to a different set of rules. I’m not checking the clock. I’m not looking for efficiency. I’m not thinking about what came last or what comes next. I’m not judging the success of the last moment against any criteria other than presence and engagement. This is a big shift, and it can be difficult to maintain.

    Paying attention to how time feels is a good clue for whether we’re “in it” or not.

    For “regular” work, time keeps us on task. It is a metronome that drives forward progress. Quality and quantity play together, and both are equally important.

    For deep work, time is a buffer that protects us, creating the space we need for exploration and for leaps. The quantity of our insights and decisions does not matter; what matters is quality. Our job is to force ourselves to slow down, to move deliberately, to sit with what we’ve come up with and keep asking “is this good enough?” Our goal, for a block of deep work, is one great outcome, not 5 or 15 small but (only) good outcomes.

    Here’s a hint: if you’re 10 minutes into a deep work task and you notice you’re 10 minutes in, you probably haven’t fully shifted gears yet.

  • Who Walks Whom?

    My first, biggest insight about philanthropic fundraising, captured in my Manifesto for Nonprofit CEOs, was about power.

    The philanthropic fundraiser can feel like a supplicant asking a benefactor for largesse. It looks, from the outside, like a massive power imbalance.

    My breakthrough was to recognize it for what it really is: a conversation between equals. Two people, who have things of real value on offer, are exploring building something together in the context of deep and meaningful partnership.

    That miscasting of roles— “who is helping who” — is all too common.

    Who is walking whom?

    Each morning, if I’m at home, I walk my two dogs between 1 and 2 miles. Neither rain nor snow nor sleet nor dark of night keeps us from our appointed rounds. Some days feel amazing, and many times— when it’s raining, or dark, or cold, or hot, or when I’m just plain tired— it can feel, at the outset, like a chore.

    And then I remind myself: I could have constructed an entire “early morning sunlight + 10,000 steps” routine, I could get a wearable to remind me about it, I could spend lots of mental energy working it into my days and my life…or I could just walk my dogs every day.

    The walks make me a happier, healthier, more settled person, and my dogs are walking me as much as I’m walking them.

    Who is feeding whom?

    Over July 4th, we went to our local town pool for a picnic and fireworks display, together with some close friends. This couple has done amazing work—via a partnership between our synagogue and a local church—supporting several Afghan and Syrian refugee families.

    One of those families, a brave Afghan couple who had worked in anti-drug trafficking (the father) and in women’s empowerment (the mother), fled to the U.S. a few years ago after the Taliban came to power. They have been building new lives for themselves and their three daughters, despite everything that has been taken from them.

    At the picnic, we got to hear some of their stories—stories that were full of hardship and wisdom and accomplishment and loss. While we talked, they calmly pulled out one giant Tupperware after another filled with homemade food: a spread that put our few sandwiches and bag of fruit to shame. The main course was a breathtaking spread of mantu (Afghan dumplings), which I’d never had before. I took four dumplings as a first serving, and they were so delicious that I may have eaten 10 in total.

     

    Every blog post I write, every coaching conversation I have, every student I speak to about career or academic choices they might make—the learning is mutual, the value is co-created.

    We are helped by helping.

    We learn by teaching.

    We support others when we ask for help.

  • Dress Up

    Each day, as we get ready to go to work, we put on an outfit. It symbolizes something—to us, to the people around us. It’s the role we will be playing for the day.

    It’s not only clothes that convey a story. Consciously or not, as we transition from home to work, we are putting on our work identity as surely as we put on an outfit. A lot of that identity come from the narrative that we tell ourselves.

    “This is who I am in this situation. These are the contours, these are the expectations, these are the likely behaviors.”

    Shifting that is not as easy as changing our shirt, or our hair. But it’s not as different as it seems.

    What if you decided to wear something different today?