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?
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.
I can't see the original, but this is easily clockable as written by AI, in the same style as a thousand other spam posts that pop up occasionally. Whether or not the style is inherently bad, it has been devalued from overuse.
Part of the appeal of reading a personal reflection is hearing it in somebody's own voice. Don't give that up!
Thanks, this is just the feedback I was looking for.
Here's the original looks like I need to publish drafts for them to be visible, I've edited the original post. I'm weighing the AI version vs the 30 minute unedited brain-dump as the thing which puts me off writing these sort of updates is that my perfectionism can cause me to put several hours in to something I intend to publish and I don't want to put too much time in to this.
On the other hand sloppily written blog posts might be a net negative thing to be publishing in the first place so not doing them or keeping them private is also a valid choice. A fourth choice could be designing a prompt to do less invasive editing. What do you think is the best approach if I'm looking to keep the time I spend writing this sort of thing to a minimum?
My thoughts are similar to titotal's above: I found it hard to get through. There are a lot of stock Claude/LLM phrases, such as the "It's not this. It's this" and the usage of "Reality check", the use of slightly too uncommon synonyms, and the slightly too fancy vocabulary.
I think there's value in LLM feedback but when it rewrites whole sections it usually starts to feel annoying to me. I don't know if you have a "system prompt" for your Claude, but prompting it to preserve your voice much more, or just give you a specific list of improvements to implement might work. It could also be worth giving Claude some other things you've written as context for "your voice" and to give it strict instructions to avoid certain ways of writing.
Some of the things I did like from the Claude version because they made it more skimmable and easier to figure out what was happening:
The weeks in the section headers
Key points bolded
The section recapping what you learned about career transitions
Relatedly, I think having a TL; DR at the top of posts is generally helpful
I struggle with the same perfectionism, but reading your original post, it does not seem net-negative to me. It works very well for the personal reflection blog post format, and is much more enjoyable to read. If you were applying for writing/blogging positions it would probably be too unpolished, but even then they wouldn't care if you had older material that was less polished. If you're concerned about it you could probably mostly mitigate it by adding a disclaimer at the top that you wrote it in a limited amount of time.
You also can't really make a mistake in this kind of post because it is a personal reflection. It's about your experience, rather than e.g. you presenting research results or carefully arguing for an opinion which would be much higher stakes and would require more carefulness. You can't get your own experience wrong.
I think this post is very valuable as a resource for other people considering going to a future iteration of ARBOx or self-studying the ARENA curriculum. It reminds me a bit of the ML4Good experience reports [1] [2] [3] [4]
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 love the model - and I'm happy to give feedback on ideas for EA Forum posts if that would ever be helpful! (I'm the Content Strategist for the Forum).
Out of that list I'd guess that the fourth and fifth (depending on topics) bullets are most suitable for the Forum.
The basic way I'd differentiate content is that the Forum frontpage should all be content that is related to the project of effective altruism, the community section is about EA as a community (i.e. if you were into AI Safety but not EA, you wouldn't be interested in the community section), and "personal blog" (i.e. not visible on frontpage) is the section for everything that isn't in those categories. For example posts on "Miscellaneous topics such as productivity and ADD" would probably be moved to personal blog, unless they were strongly related to EA. This doesn't mean the content isn't good - lots of EAs read productivity content, but ideally, the Forum should be focused on EA priorities rather than what EAs find interesting.
Feel free to message me with specific ideas that I could help categorise for you! And if in doubt, quick-takes are much more loose and you can post stuff like the bi-weekly updates there to gauge interest.
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.
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:
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:
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.
I can't see the original, but this is easily clockable as written by AI, in the same style as a thousand other spam posts that pop up occasionally. Whether or not the style is inherently bad, it has been devalued from overuse.
Part of the appeal of reading a personal reflection is hearing it in somebody's own voice. Don't give that up!
Thanks, this is just the feedback I was looking for.
Here's the original looks like I need to publish drafts for them to be visible, I've edited the original post. I'm weighing the AI version vs the 30 minute unedited brain-dump as the thing which puts me off writing these sort of updates is that my perfectionism can cause me to put several hours in to something I intend to publish and I don't want to put too much time in to this.
On the other hand sloppily written blog posts might be a net negative thing to be publishing in the first place so not doing them or keeping them private is also a valid choice. A fourth choice could be designing a prompt to do less invasive editing. What do you think is the best approach if I'm looking to keep the time I spend writing this sort of thing to a minimum?
My thoughts are similar to titotal's above: I found it hard to get through. There are a lot of stock Claude/LLM phrases, such as the "It's not this. It's this" and the usage of "Reality check", the use of slightly too uncommon synonyms, and the slightly too fancy vocabulary.
I think there's value in LLM feedback but when it rewrites whole sections it usually starts to feel annoying to me. I don't know if you have a "system prompt" for your Claude, but prompting it to preserve your voice much more, or just give you a specific list of improvements to implement might work. It could also be worth giving Claude some other things you've written as context for "your voice" and to give it strict instructions to avoid certain ways of writing.
Some of the things I did like from the Claude version because they made it more skimmable and easier to figure out what was happening:
I struggle with the same perfectionism, but reading your original post, it does not seem net-negative to me. It works very well for the personal reflection blog post format, and is much more enjoyable to read. If you were applying for writing/blogging positions it would probably be too unpolished, but even then they wouldn't care if you had older material that was less polished. If you're concerned about it you could probably mostly mitigate it by adding a disclaimer at the top that you wrote it in a limited amount of time.
You also can't really make a mistake in this kind of post because it is a personal reflection. It's about your experience, rather than e.g. you presenting research results or carefully arguing for an opinion which would be much higher stakes and would require more carefulness. You can't get your own experience wrong.
I think this post is very valuable as a resource for other people considering going to a future iteration of ARBOx or self-studying the ARENA curriculum. It reminds me a bit of the ML4Good experience reports [1] [2] [3] [4]
I prefer the original FYI.
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 love the model - and I'm happy to give feedback on ideas for EA Forum posts if that would ever be helpful! (I'm the Content Strategist for the Forum).
That would be really useful!
Some of my ideas for forum or blog posts are:
I'm also interested in how you differentiate between content better suited for a blog or better suited for a forum?
Out of that list I'd guess that the fourth and fifth (depending on topics) bullets are most suitable for the Forum.
The basic way I'd differentiate content is that the Forum frontpage should all be content that is related to the project of effective altruism, the community section is about EA as a community (i.e. if you were into AI Safety but not EA, you wouldn't be interested in the community section), and "personal blog" (i.e. not visible on frontpage) is the section for everything that isn't in those categories. For example posts on "Miscellaneous topics such as productivity and ADD" would probably be moved to personal blog, unless they were strongly related to EA. This doesn't mean the content isn't good - lots of EAs read productivity content, but ideally, the Forum should be focused on EA priorities rather than what EAs find interesting.
Feel free to message me with specific ideas that I could help categorise for you! And if in doubt, quick-takes are much more loose and you can post stuff like the bi-weekly updates there to gauge interest.
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.