diff --git a/src/content/posts/one-year-in.md b/src/content/posts/one-year-in.md
index 23c244e..aaa6940 100644
--- a/src/content/posts/one-year-in.md
+++ b/src/content/posts/one-year-in.md
@@ -1,45 +1,40 @@
 ---
-title: "One Year and 10000 Stars Later"
+title: "10000 Stars Later"
 author: saba
-description: Reflecting back on the last year of building Khoj, and how we got here.
-tldr: "The article chronicles the evolution of Khoj from a personal search engine to an open-source cloud service leveraging large language models, online search, and other AI tools, while emphasizing key lessons learned in building an open-source company like prioritizing documentation, community engagement, and iterative development to address user needs."
+description: Reflecting back on the last few years of building Khoj, and how we got here.
+tldr: "The article chronicles the evolution of Khoj from a personal search engine to a cloud-scale personal AI with ability to paint, research online, provide specialized personas & run autonomously. It emphasizing key lessons learned in building an open-source company like prioritizing community engagement and iterative development to build human aligned AI."
 heroImage: /blue_wave.png
 pubDate: 2024-06-17
 ---
-## Scaling an open-source consumer AI service
+## The Khoj Journey So Far
 
-The journey with Khoj has been enlightening. Back in 2022, we were just dabbling with the idea of a personal search engine - something to sift through your mountain of notes and documents with a natural language interface. My co-founder [Debanjum](https://linkedin.com/in/debanjum) was knee-deep in language models, while I was iterating on our dev ops.
+The journey with Khoj has been an enlightening roller-coaster. Back in 2021, we were dabbling with creating these personal AI search engines - something to sift through our mountains of [org-mode](https://orgmode.org/) notes using a natural language interface. My co-founder [Debanjum](https://linkedin.com/in/debanjum) was turning these AI models into a local document search engine, while I was iterating on making Khoj easy to use, setup for other avid note takers.
 
 
 ![Star History Chart](https://assets.khoj.dev/star-history-202467.png)
 
-Here's the ride we've been on:
+Here's the ride we've been on so far:
 
-1. Our small note-handling side project called Khoj with 300 GitHub stars landed us a spot in [YCombinator](https://ycombinator.com) for summer of '23.
-2. Someone hard-launched us on HackerNews in July '23 and we [got roasted](https://news.ycombinator.com/item?id=36641542) for not supporting open source LLMs.
-3. Tried letting people run LLMs locally without internet, but making GPU-enabled, cross-OS Python work smoothly in an app is way harder than it seems.
-4. Went back to Hacker News with an improved version and the [feedback](https://news.ycombinator.com/item?id=36933452) was much better.
-5. Realized AI could widen the existing accessibility gap, so we integrated personal AI assistance into [WhatsApp](https://www.ycombinator.com/launches/JG4-khoj-your-superhuman-companion).
-6. In November, we opened up a beta version of our [cloud service](https://app.khoj.dev)!
-7. We felt the limitations of recency in training data. We integrated online search into Khoj's tool belt, and found it to generally be a great information aggregator. It's way easier than consuming search results.
-8. Performance was spotty at one point, so we migrated to ECS containers.
-9. Added some specialized [agents](https://app.khoj.dev/agents) to handle different use cases better. Set up [automations](https://app.khoj.dev/automations) for repetitive queries with inbox digests, alerts, etc.
-10. [Some](https://www.youtube.com/watch?v=Lnx2K4TOnC4)  [delightful](https://www.youtube.com/watch?v=10DUZA4KEvg) YouTube/[Twitter](https://x.com/tuturetom/status/1792877330571944078) posts led to a big traffic spike we scrambled to handle. That ECS migration was a massive lifesaver. Our UX continues to be the butt of jokes.
-11. Finally hired our first teammate, [Raghav](https://www.linkedin.com/in/raghavtirumale/), who's hit the grounding *sprinting* for the summer.
+1. We built a local document, image AI search engine for [Emacs](https://www.gnu.org/software/emacs/) users. Created ability to chat with GPT, even about your notes, back [in 2021](https://github.com/khoj-ai/khoj/commit/0ac1e5f372dbe6baf16f1b0c3d4df1bf5da5efdb) [^1]. Did decently well on r/OrgMode. Missed being ChatGPT 🫠
+2. Our hobby project to create an open-source, personal AI called Khoj, with 300 GitHub stars, landed us [a spot](https://www.ycombinator.com/companies/khoj) in [YCombinator](https://ycombinator.com) for the summer of '23.
+3. Someone hard-launched us on to the front page of HackerNews in July '23 but we [got roasted](https://news.ycombinator.com/item?id=36641542) for being mere chatgpt wrappers 🥶 and not being open source enough 🙄.
+4. We did a [ShowHN](https://news.ycombinator.com/item?id=36933452) of our new local chat with your docs experience. It got us on the front page of HN, this time with positive vibes.
+5. We wanted AI to close, not widen, the accessibility gap, so we worked with Meta to integrate our personal AI into [WhatsApp](https://www.ycombinator.com/launches/JG4-khoj-your-superhuman-companion).
+6. In November, we launched a beta version of the Khoj [cloud service](https://app.khoj.dev)! This allowed folks to use Khoj, even if they didn't have powerful GPUs.
+7. Over the next few months we iterated based on user feedback, to turn Khoj into a capable AI agent. It now had the ability to research online, paint images, take on specialized [personas](https://app.khoj.dev/agents) and perform tasks [autonomously](https://app.khoj.dev/automations) on your behalf.
+8. Performance was spotty, so we migrated from EC2 to ECS for smoother scaling.
+9. [Some](https://www.youtube.com/watch?v=Lnx2K4TOnC4) [delightful](https://www.youtube.com/watch?v=10DUZA4KEvg) YouTube/[Twitter](https://x.com/tuturetom/status/1792877330571944078) posts made us go trending at #1 on Github. We scrambled to handle the big traffic spike. That earlier ECS migration became a massive lifesaver. Our UX still looked like it was straight out of a cartoon.
+10. We hired our first teammate, [Raghav](https://www.linkedin.com/in/raghavtirumale/), who's hit the grounding *sprinting* for the summer.
 
-That brings us to today! Through all this, we've picked on a few pieces of conviction:
+[^1]: There was no UX, just an experimental API for an intrepid explorer to discover
 
-- AI will fundamentally shift how we learn and understand information
-- We need to have an open-source alternative to cornerstone AI applications. Even when the creators rotate and swap out, people should be able to own their service and ensure service/user alignment.
-- AI is already making the hard-to-reach (like medical and legal advice) way more accessible
-- Communication will get easier to the point of seamlessness for people across languages
-- We will spend a lot less time rifling through specific bits of information ourselves, more time doing creative tasks on top of it
 
-## Cool, so what did we learn?
+That brings us to today! Cool, so what did we learn?
+### Building an Open Source AI Company
 
-The dynamics of building an open-source company are quite different from closed-source companies. A lot of our users are hackers and developers. This helps us find security vulnerabilities, and it also means that users can sometimes jump in, get their hands dirty, and solve their own problems!
+The dynamics of building an open-source company are quite different from closed-source companies. A lot of our early users are hackers and developers. This makes Khoj development more collaborative and transparent with less effort. It means the community can find vulnerabilities, test capabilities, report issues and contribute fixes earlier and faster. It means they can just jump in, get their hands dirty, and solve their problems without our assistance. **It means Khoj can get aligned to human faster and stay aligned with them for longer.**
 
-As maintainers of the repository, we need to do a better job of making it easy as possible for developers to help themselves. Documentation should be tight, complete. If someone asks you a question, answer it, and add the answer to your documentation right away. Your documentation should be really easily searchable ([Algolia + Docusaurus is GOAT](https://docusaurus.io/docs/search#using-algolia-docsearch)) For people looking to get involved, you should flag good first issues for getting setup.
+As maintainers of the repository, we need to do a better job of making it super easy for developers to help themselves. Documentation should be tight, complete. If someone asks you a question, answer it, and add the answer to your documentation right away. Your documentation should be really easily searchable ([Algolia + Docusaurus is GOAT](https://docusaurus.io/docs/search#using-algolia-docsearch)). You should flag good first issues for getting new contributors started with less effort.
 
 The [Discord community](https://discord.gg/BDgyabRM6e) has been OP. Most of the people who self-host Khoj make their way there and give ample, active feedback. It's become a great place to share ideas and build our understanding of what AI will look like. That being said, it's really hard to scale great support while building your product. Sometimes you also have to say no to support requests, and that can be really hard. Especially when we were working on exclusively self-hosted LLM-application support, there was such a long tail of complex, bespoke user issues that we couldn't address. That can feel really disappointing.
 
@@ -47,4 +42,14 @@ The [Discord community](https://discord.gg/BDgyabRM6e) has been OP. Most of the
 
 Your team should be able to manage communication in a Slack channel or a WhatsApp group. You don't need a massive Notion or Jira dashboard when it's just two of you and an intern. Stay lean, keep your processes lightweight and efficient. Do weekly and monthly planning to stay focused.
 
-The last year has been really eventful, full of learnings and adaptations. Biggest lesson, you have to keep your ear to the ground, really listen to what pain points people are having and wonder whether they're being addressed appropriately. We're not perfect, but we're learning. The key thing is to just keep iterating.
\ No newline at end of file
+The last year has been really eventful, full of learnings and adaptations. **Biggest lesson is to keep your ear to the ground, really listen to what pain points people are having, iterate on it quickly and cut out the noise.** We're not perfect, but we're learning.
+
+### Convictions about AI
+
+Through all this, we've also picked on a few pieces of conviction about AI:
+
+- AI will fundamentally shift how we understand and access information. We need to carefully design our AI interfaces to ensure this shift improves our capabilities.
+- We need our personal AI to be aligned to us. Open-source AI is much easier to keep aligned to individual human interests. It is important to minimize chances of misalignment wherever possible. Even if the creators rotate and swap out, people should be able to take ownersip of the service and ensure service/user alignment.
+- Communication will get easier for people across languages, personas and mediums.
+
+**How we construct these new machines over these next few years will decide if AI improves the human condition. That is our north star. That is what we continue to innovate towards.**