Real Alpha
Watch modeSubscribed

Moonshots · 3 min · Oct 23, 2026

A portable memory file can carry your identity across AI models

Salim Ismail exports a persistent profile from each model into a shared Markdown file, then reuses it across assistants. That gives users continuity without betting on one provider.

Salim Ismail, Host

Founder, Open ExO

Co-wrote Exponential Organizations; was Singularity University's founding executive director; sold Ångströ to Google.

  • Peter Diamandis, Host · Founder, XPRIZE

    Co-founded Singularity University and founded Zero-G; co-wrote the books Abundance and Bold.

  • Dave Blundin, Host · Founder & GP, Link Ventures

    Has co-founded 23 companies; founding CEO of Vestmark and chairman of insurance marketplace EverQuote.

  • Alexander Wissner-Gross, Host · Computer Scientist & Founder, Reified

    Has backed and advised 40+ tech companies, directly and through 021T Capital and Reified; writes The Innermost Loop.

About this segment

Salim Ismail exports a persistent profile from each model into a shared Markdown file, then reuses it across assistants. That gives users continuity without betting on one provider.

From “SpaceX’s AI Business Up 830%, OpenAI Agents Lie, and Startup Turns Mercury Into Gold | EP #305”, Oct 23, 2026. Watch the full episode

“So I've been running a query against each model saying, extract all the relevant stuff and put it into this metadata markdown file structure”
Salim Ismailat 1:07:51 · Moonshots1:07:51

Takeaways

  1. Export useful context from each model into a shared Markdown file.
  2. Keep identity, projects, and preferences portable across assistants.
  3. Persistent context can matter more than one clever response.

In this episode

Full episode
  1. 47:23AI agents need controls as well as autonomy6:09
  2. 19:04Musk is blurring the boundaries between his companies3:10
  3. 1:54:54A fusion startup is testing gold production from mercury6:45
  4. 1:39:28AI helped a small team design scorpion-toxin binders5:41
  5. 58:10AI is cutting the cost of replacing legacy software3:52
  6. 1:33:33Containerized AI compute could support $5–35 million deployments4:53

  7. 1:05:52A portable memory file can carry your identity across AI models2:34

  8. 1:24:08Data-center communities could receive dividends from credit financing5:13Up next

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

  1. 1:05:58

    And I'll be going, damn this thing. I'll be crossing it. I think this is another evolution. I think more and more intelligence will get at the harness level rather than the model level. The really difficult part is going to be, and we're seeing this as we try and express workflows in companies, is figuring out what the actual intent is and can you break it down to a step-by-step level, right? Because you need to articulate in any circumstance what does success look like and what trade-offs are acceptable and when an agent needs to stop and ask. So we're going to have to navigate a whole bunch of this, But I think it looks really amazing at first glance.

  2. 1:06:30

    I'm going to play this video while we talk about it, Anthropic's Claude Duet here. Anthropic example says it notices a real estate broker's property showing has been booked on the wrong day. It spotted that a brand strategist had a client call scheduled right before her flight. It remembers that you've told Claude what you told Claude before, uses the same skill and connections, and runs Anthropic's most powerful model.

  3. 1:06:57

    Importantly, it does ask permission before it acts on your behalf, before it sends messages, makes a payment, or signs anything. It's, for now, U.S. only with a wait list for paid subscribers. So here's my question for you guys. How do you choose? You know, I've been using Hermes and GrockBot. My friend Mike Koenigs is like, you got to use Dots now. And I'm going to go meet with him and learn about, you know, his installation of Dots.

  4. 1:07:24

    Then we got Claude Duet. I mean, are you playing with all of them? Do you choose one of them? I'm sure everybody listening has got that same question, and I think it's important for us to talk about. I'll tell you what I'm doing because I do all of them because these agent layers are really important for the organizational stuff we're doing because persistent context becomes much more valuable than a clever response, right?

  5. 1:07:47

    And so what we've been doing is saying, okay, every task or every person, what you need to do is create an AI memory across all of the projects and all of the different models that you're using. So I've been running a query against each model saying, extract all the relevant stuff and put it into this metadata markdown file structure so that there's a persistent identity of who Salim is, what I'm interested in, what projects I'm up to, et cetera.

  6. 1:08:12

    And then that becomes portable across models. We're going to need something like that at the individual level and then in companies at the workflow level. Well, this is the battle royale.