I quit the best job I ever had to try and build what I wish existed in the world. Two projects I'm working on now: 1. The Peterman Pod - When I first started at Meta, the career stories of incredible engineers always inspired me. I aim to share transparent career stories that I wish I had more of back in the day. There are still many engineers who are heros to me that I'd love to bring on the show one day! 2. Compose - I could never really find what I wanted so I'm building the ergonomic keyboard I wish existed. Pictures of our prototype here: read.compose.llc/p/our-keybo… I've earmarked ~6 months of living expenses to fund this new career direction. I'm going to give it my all to see if it's sustainable. Thank you for your support, working on my passion projects is something I’m only lucky enough to consider because of you all 🙏 More detail here: nitter.net/ryanlpeterman/status/2…

3rd interview with Ethan Evans (@EthanEvansVP) dropping Monday 9/28

His biggest career regret is only going to become more common for software engineers now. “I wasn’t as inquisitive as I could have been about what the actual underlying particularly technical cause was.” “You need to understand how things work.” “You’re inquisitive about why it actually worked. And I think that this is just a much more sustainable foundation.” @hievanking

Native chinese speakers, how is this dub? Doing a little experimenting here: xhslink.cn/m/6sxYS9ryPbi

The m5 studio upgrade has arrived!! Had Codex chop up the footage into an ASMR unboxing video in one shot

Philip Su grew quickly to a Distinguished Engineer at Facebook and OpenAI. We talked about the psychology behind peaking in a tech career and the pressure at the highest levels. In this episode: • Not wanting IC9 and requesting demotion • How motivation changed across his career • Fulfillment and motivation after FIRE • Why sustaining IC9 was difficult Where to watch: • YouTube - piped.video/watch?v=RMo04pSS… • Spotify - open.spotify.com/episode/3Uf… • Apple Podcasts - podcasts.apple.com/us/podcas… • Transcript - developing.dev/p/openai-and-… Thank you to the sponsors of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at workos.com/ • Jira by Atlassian: Get more work done with your favorite agents and models all in one place, check them out at jira.dev/ Chapters: 00:00 Intro 00:37 Growth past IC9 05:39 Motivation changes over his career 11:36 Asking to not be promoted 17:33 What made it hard to sustain IC9 performance 22:22 What motivated him outside of promos 26:21 Is career advice useless 29:34 Motivation after you've hit FIRE 36:08 Meaning and fulfillment 38:17 Top book recommendation 40:14 What he would change 43:24 Outro

Career update after quitting my job at Meta and spending 6 months of my savings to work on my passion projects

I quit the best job I ever had to try and build what I wish existed in the world and here's how it went:

$200 max Claude and $200 pro Codex subscriptions both run out around halfway through the week for me The recent computer use improvements have drastically improved the surface area of useful work they can do Considering getting a 3rd subscription...

My keyboard Kickstarter update below after using the first sample off the assembly line for the last 2 weeks It's surreal having something go from idea to physical product, thank you for your support 🙏 Also, notes on how we'll polish it and next steps: read.compose.llc/p/first-sam…

My goal was to record a conversation completely free of "AI doomer" takes as a timeline cleanser. For this episode, I interviewed Casey Muratori (@cmuratori) who is a video game developer and programming creator also known for his talks about the history of computing. In this episode: • Surprising findings in computer history • Where bad code comes from • The only unbreakable law in software engineering • His career in the video game industry • Why you should read technical papers Where to watch: • YouTube - piped.video/jHLbL1Eg4gM • Spotify - open.spotify.com/episode/4yw… • Apple Podcasts - podcasts.apple.com/us/podcas… • Transcript - developing.dev/p/casey-murat… Thank you to the sponsors of this episode for supporting my work: • Jira by Atlassian: Get more work done with your favorite agents and models all in one place, check them out at jira.dev/ • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at workos.com/ Chapters: 00:00 Intro 01:08 Digging into computer science history 04:08 What shocked him 16:23 Dijkstra was depressed 26:17 The personal side of goto considered harmful 35:09 The anatomy of a 35 year mistake 50:12 Clean code horrible performance 58:33 How to write high performance code 01:01:18 Where bad code comes from 01:06:37 Why design docs before code is a bad idea 01:09:20 The only unbreakable law in software engineering 01:15:57 How he got into programming 01:21:16 Why he didnt work in big tech 01:30:44 Should you work at a startup early on 01:34:52 What video game engineering is like 01:39:57 Why preventing recursion is reasonable 01:43:24 Is vibe coding bad for the industry 01:50:17 Technical reading recommendation 01:54:27 Advice for his younger self 01:56:54 Outro

Asking Codex computer use to prompt Claude to continue after limit reset so I can sleep

Weekend AI project: Bathroom dashboard • Weather, UV index today • Health data from Google Health • Social media metrics for work • Calendar events for the day This was a one shot for GPT6 once I enabled "wireless debugging" on the tablet

Many people doubting the Kindle’s refresh rate and my typing speed Used Fable 5.1 to build a custom typing test to demonstrate both Latency isn’t an issue

I asked Fable 5.1 to summarize how it did this in a concise technical writeup. Here's what it did: Goal: Use a Compose Keyboard with a jailbroken Kindle Scribe to edit Markdown on a Mac mini through kterm and SSH. 1. Connect over BLE. The firmware used Amazon's ACE userspace stack, with a classic-only public interface. We cross-compiled a GATT client using kindlebt and ACE libraries to access BLE directly. Connections still timed out: ACE used a public address type for the keyboard's random address. An LD_PRELOAD shim in btmanagerd tracked its advertising address and corrected outgoing HCI connection commands. 2. Complete pairing. The Kindle generated a six-digit passkey but provided no keyboard-pairing UI. We captured the btPairNumericPinToDisplay event and entered the code on the Compose Keyboard, completing authenticated pairing. 3. Persist the bond. Restarting btmanagerd immediately after pairing discarded unsaved keys. Allowing the stack to save its encryption and identity keys to bt_config.conf preserved the bond across reboots. 4. Capture input. The stock input path did not handle BLE HID reports. The shim extracted keyboard notifications from decrypted ATT traffic and forwarded them through a FIFO to an injector. 5. Deliver input to kterm. Xorg did not pick up the uinput virtual keyboard. We switched to XTEST injection, restored kterm's focus before injecting events, and handled X protocol errors without exiting. Launching kterm in the foreground from a tap-scriptlet prevented launch and home-screen redraw issues. 6. Stabilize the pipeline. We removed competing FIFO readers, opened the reader with O_RDWR to avoid startup deadlock, and checked traces when a measurement tool incorrectly reported lost keystrokes. The launcher starts the pipeline, opens kterm in landscape, and connects to the Mac using SSH key authentication. A helper re-arms background BLE connection requests every 15 seconds; stored identity keys support reconnection when the keyboard wakes. The changes are reversible. Note: this writeup was AI generated but I figured it'd still be helpful since a bunch of people were asking. You can probably feed this into your LLM and ask it to follow a similar plan. It churned on this for ~3-4 hours until it got everything working.

Used Fable 5.1 to turn my Kindle into a Linux terminal so I could work without blue light at night

Blew through both my Claude Max 20x and ChatGPT Pro 20x weekly limits in ~2 days using Fable 5.1 + GPT6. Some observations: 1. Claude Max 20x ran out noticably faster for me than ChatGPT Pro 20x using Fable 5.1 and GPT6 respectively 2. Fable 5.1 writes much better plans for humans to read (qualitative). Both one shot my work in ~90% cases though 3. Claude Code TUI >> Codex CLI in terms of product craft & user experience 4. Codex Mac app computer use is excellent. It does a ton of rote tasks for me that I didn't trust models to handle before Huge jump in capabilities, curious to see how (4) impacts jobs that do a lot of repetitive tasks on the computer

Should people still learn to code if coding is largely solved? Thariq Shihipar (Engineer on Anthropic’s Claude Code team): "I think being technical is really important. Knowing how do computers work? How do languages work? What are the hard things like? All of these things are actually really important to learn. Like we talked about earlier. Oh, the only way you can tell you've solved the Riemann Hypothesis or the Jacobian Conjecture is like, if you're a great mathematician. Right? And in the same way, the only way you can tell if you're, like, built great software is like, if you're a great software engineer. When Boris says coding is solved, it just means we don't get stuck in the same ways that we used to before. Like, very few people in the entire world could write software, and they were very rare. And even if you got them all together, there were so many other reasons why it wouldn't work. Right? And now that coding is solved, you can use coding to do all these other things that we've not done before." For the full conversation, you can search Thariq Shihipar on my YouTube, Spotify or Apple Podcasts (link in bio)

Thariq Shihipar (@trq212) is an engineer on Anthropic’s Claude Code team I asked him how Anthropic makes the most out of the models for engineering and how the industry will change soon. In this episode: • Internal best practices in leveraging the models • What percent of Anthropic's work is fully autonomous • How Anthropic maintains higher volumes of code • What has worked in preventing AI-written breakages Where to watch: • YouTube - piped.video/2Kch3tWMnw8 • Spotify - open.spotify.com/episode/5dT… • Apple Podcasts - podcasts.apple.com/us/podcas… • Transcript - developing.dev/p/how-anthrop… Thank you to the sponsor of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at workos.com/ Chapters: 00:00 Intro 00:29 Onboarding at Anthropic 02:53 Internal capabilities vs external perception 06:16 Model vs Harness 08:55 What percent of Anthropics changes are fully autonomous 14:51 Computer use 17:42 How to make the most out of your compute 20:45 Loop engineering 22:47 Where the industry will go soon 26:02 Which model do Anthropic engineers use 27:38 Is learning a particular model worth it 30:56 Prompting tips for todays models 35:04 How to get the models to do tasteful work 39:00 How much of writing is done by AI at Anthropic 45:36 Code ownership and maintenance at Anthropic 52:04 How Anthropic prevents breakages 55:24 Visibility and sharing your work 58:42 Luck surface area example 01:00:57 Should people still learn to code 01:07:42 Advice for his younger self 01:09:58 Outro

What happened to Boston Dynamics Sergey Levine (Top Robotics Researcher): “A lot of what the classic Boston Dynamics results show is very sophisticated hardware, very carefully designed hardware, with a traditional control approach, with very smart controls, engineers setting everything up, but with comparatively less emphasis on the kind of decision making aspect. And I think that at a particular point in time, that actually made a lot of sense, because if you can't build the physical body, like, it doesn't matter what kind of decision making system is running on it. But at this point, we're at a stage in the development of these things that the big challenge is how to have the decision making loop that actually works and that reacts intelligently to everything in the environment. The question is, do you need to take the rest of the environment into account, or are you just dealing with the robot?”

How the ergo keyboard sounds, I put DJI mics in between to capture As silent as a laptop keyboard