I'm a 36 year old iOS Engineer/Software Engineer who switched to working on Image classification systems via Tensorflow a year ago. Last month I was made redundant with a fairly generous severance package and good buffer of savings to get me by while unemployed.

The risky step I had long considered of quitting my non-impactful job was taken for me. I'm hoping to capitalize on my free time by determining what career path to take that best fits my goals. I'm pretty excited about it. 

I created a weighted factor model to figure out what projects or learning to take on first. I welcome feedback on it. There's also a schedule tab for how I'm planning to spend my time this year and a template if anyone wishes to use this spreadsheet their selves.

I got feedback from my 80K hour advisor to get involved in EA communities more often. I'm also want to learn more publicly be it via forums or by blogging. This somewhat unstructured dumping of my thoughts is a first step towards that.

I'd like to get feedback on the writing style of this post. I want to try to write up bi-monthly updates but don't enjoy sinking time into writing.

I've never really stuck with blogging despite it being valuable for sharing what I'm working on as I'm a bit of a perfectionist. I end up spending hours combing over the posts I make. I'd like my posts to only take 30 minutes, so my current ideas are to write quickly and post as is, or to have an AI edit out my mistakes.

Which of the two do you prefer? Do you have any suggestions on ways to make quick blog posts without potentially attaching poor communication or AI slop to myself?


My original post.
My prompt.


Claude's edit of my post:
------
My Two-Month Deep Dive into AI Safety: From Imposter Syndrome to Clarity

How ARBOx and ARENA helped me navigate a career transition into AI Safety—and what I learned about myself along the way

Two months ago, I committed to spending my summer diving headfirst into AI Safety. As someone with a background in Swift development and traditional software engineering, the world of Transformers, Linear algebra, and AI alignment research felt like an entirely different universe.

Here's what happened when I threw myself into ARBOx and ARENA—the good, the challenging, and the surprisingly clarifying moments that helped shape my career transition.

Week 1-3: ARBOx in Oxford - Swimming in the Deep End

ARBOx accepted me for their intensive program: one week of prerequisites, followed by two weeks of in-person training in Oxford.

The reality check was swift. During pair programming sessions, I was often the weaker partner. While my colleagues brought post-grad experience with deep learning or career backgrounds in ML, I was frantically trying to remember basic PyTorch syntax. My years of Swift development, unit testing, and design patterns suddenly felt irrelevant when staring at Jupyter notebooks full of tensor operations.

However, being the "slower" partner was actually incredibly valuable. My more experienced partners were amazingly patient, and having someone literally show me concepts I didn't understand was worth twice the learning compared to struggling alone. Sometimes the best education comes from admitting what you don't know.

The human element made all the difference. Working on AI Safety material in isolation can feel overwhelming—like you're trying to solve impossible problems alone. Being surrounded by 19 other people going through the same learning process, discussing niche AI Safety topics over meals, was genuinely inspiring. It reminded me that this field is built by communities of people, not just individual brilliance.

Weeks 4-7: ARENA Fundamentals - Slowing Down to Speed Up

After Oxford, I faced a choice: rush through ARENA's materials to keep up with their intense timeline, or slow down and actually master the fundamentals.

I chose to slow down, and here's why that decision was crucial.

Everything builds on the basics. My biggest blockers during ARBOx were gaps in PyTorch, linear algebra, and tensor operations. Rather than continuing to build on shaky foundations, I decided to really nail these prerequisite skills. If I'm transitioning careers, I reasoned, these fundamentals won't just help with AI Safety—they'll be essential for any ML-related work I pursue.

Active learning over passive consumption. ARENA encourages rapid progress through pair programming, often skimming reading materials to finish notebooks in a day. While this works well for exposure to topics, I found more value in:

• Writing Anki flashcards for key concepts
• Watching YouTube videos to visualize complex topics
• Going through additional reading materials
• Actually understanding rather than just completing exercises

I've created a fork of the ARENA syllabus to work at my own pace, and I'm considering building demos of my favorite exercises to start developing a deep-learning portfolio.

The Career Reality Check: Research vs. Engineering

Midway through this journey, I applied for SPAR (Supervised Alignment Research)—a 3-month program requiring 10-30 hours per week. On paper, it seemed perfect: hands-on AI alignment research experience during my career transition.

But as I worked through the application, something became clear: I was applying for the wrong reasons.

Here's what gave me pause:

• Time commitment vs. exploration breadth: Committing 3 months to one niche area when I only have 12 months total for career transition
• Skills mismatch: The program values my software engineering background, but I need to develop ML skills most
• Practical constraints: I'll be working from Bali for 2 of the 3 months, limiting my in-person or synchronous involvement.
• Motivation misalignment: I found myself struggling to get excited about reading & writing papers, applying for funding, and running scaffolding experiments

Realising that pure research might not be my best fit helped clarify what actually excites me. AI Safety engineering—building robust systems, tinkering with deep-learning model, creating tools that researchers can use—aligns much better with my background and interests.

Sometimes the most valuable outcome of an application process is discovering what you don't want to do.

What I've Learned About Career Transitions

Imposter syndrome is data, not truth. Feeling like the weakest person in the room doesn't mean you don't belong—it often means you're in exactly the right place to learn quickly.

Community matters. The isolation of solo learning can make career transitions feel impossible. Finding your people—even temporarily—provides motivation and perspective that no amount of individual study can replace.

When to go slow or fast. The pressure to quickly "catch up" in a new field can lead to surface-level learning. Sometimes the best strategy is to thoroughly understand the foundations, even if it feels like you're moving slowly. For less foundational topics a quicker approach can pay dividends so you can get a sense of which topics interest you and go in greater detail later when you've a better idea of what to focus on or can apply the knowledge in a real project.

Career fit-testing is as important as skill building. Don't just ask "Can I do this work?" Ask "Do I want to do this work?" The difference between research and engineering roles, for instance, isn't just about skills—it's about what energises you.

What's Next

I'm continuing through ARENA fundamentals with a focus on building solid foundations rather than racing through material. I'm also exploring AI Safety engineering opportunities that better align with my background and interests.

The goal isn't to become an AI Safety researcher in two months—it's to understand the landscape well enough to make informed decisions about where I can contribute most effectively.

For anyone considering a similar transition: Don't underestimate the value of being honest about what you don't know, finding communities of fellow learners, and taking time to understand not just what you can do, but what you want to do.

What's been your experience with career transitions in technical fields? I'd love to hear about your journey in the comments below.

Python & Fellowship Tests
Repost from blog (I'd appreciate any feedback)

This Autumn has been a bit of a mix of continuing with Arena, being sick, and applying for half a dozen fellowships and courses.

Claude and Astra's fellowships both required code signal's industry coding assessments. I did a week of preparation for both of them before taking the test but did a lot worse than I thought I would. Being relatively new to Python and not being able to code at high speed without making mistakes was my downfall with these. I'm generally not great at thinking fast be it coding or chess.

I did enjoy practising Python. It's very valuable given most the career switches I'm considering use it. It was refreshing to see this kind of test instead of algorithm and data structure tests, which I feel involve revising something you're not going to need for the job. I created some mock practice tests using LLMs that were excellent preparation for the real deal. I've also picked up some Anki flashcards for the most common Python functions, which should come in handy for next time.

I also did tests that involved writing essays about papers for Cooperative AI Research fellowship, MARS, LASR, Deepmind, ERA, and the 2nd stage of Astra. With the exception of the ERA test (really interesting paper on LLM coding capabilities), I didn't enjoy these. But they were probably valuable for fit testing; if I'm not enjoying reading papers and writing about them, AI safety research probably isn't going to be my cup of tea.

I've decided, for the time being, to stop applying for new fellowships. Joining a fellowship would be a great fit test in itself, but it's quite a large time commitment, especially when you include the x number of applications you'll need before getting accepted to one. I have limited time to do fit tests this year, so my priority now that I'm getting a sense that pure research isn't my thing, is to focus on finishing ARENA, start to explore career paths other than AI safety, and contribute to more open-source projects. I need to be careful not to use up all my time doing applications rather than getting my hands dirty with projects that will give a much better indication of my fit for a given career path.

I'm currently taking a career break intended to fit-test what impactful careers suit me. I've created a  spreadsheet with a weighted factor model (Altruism/Career projects tab) and a rough schedule. I'm eager to get feedback on how I'm planning to spend my time and how I've prioritized what to work on.

blog-post on topic.