Dad. Thinker. Engineer. Becoming a member of AA (agents anonymous) 🦞🤖🧠

Joined October 2010
444 Photos and videos
Cillian Myles retweeted
The @Superlist team just shipped an MCP server. 🚀 You can now create, update, and manage tasks from Claude, ChatGPT, Perplexity and other MCP-compatible software: 👉 superlist.com/mcp Also new: an activity heatmap, better sorting, and faster file previews. Nice one @marcelkaeding 👏
4
14
1,737
Cillian Myles retweeted
We have whole companies restructuring for these 100x gains but yet their revenue stays flat or as high growth as before, profits negative.
11
4
92
15,351
Cillian Myles retweeted
May 25
I've had more "I can't believe it's this good" moments with GPT5.5 than any other model since Opus 4.5. It's shockingly, scarily capable. Days and days of amazing progress. All steering, no handwriting. Yet utterly delightful to conduct its coding. So, so good.
256
284
6,077
471,761
Cillian Myles retweeted
Tactical vs Strategic Programming, and why I'm nervous for juniors: Good programming involves a mix of tactical and strategic decision-making: - Tactical: on the ground, short-term. The soldier doing the fighting. - Strategic: high-view, long-term. The general planning the war. You need to be a tactician to write good code. To choose the right syntax. To figure out the file structure. To figure out how best to test your changes. But you need to be a strategist to build code that lasts. To design the architecture. To automate away problems. To think beyond today. Agents have eaten the tactical part of programming. When you can pay below minimum wage for code, there's no point going into the trenches yourself. But AI cannot code strategically. Agents need someone at the top of the pyramid to tell them what to do. They need oversight. So, a developer's day-to-day job has become 100% strategy. Long-term thinking, all the time. (maybe this is why I'm so tired all the time now) If you identify as a tactical programmer - a code monkey - then you are out of luck. The job has changed. Personally, I like it. I always preferred thinking strategically about code. If you asked me what my job was about, I'd say 'building apps', not 'writing code'. But what makes me nervous is that we've pulled down the only bridge that brought juniors into the industry. We used to train juniors like this: 1. Give them only tactical tasks 2. Let them build up their strategic experience slowly Eventually, they are a good enough strategist that they are no longer a junior. But what happens when all tactical code is written by AI? What is the point of a junior? We obviously need juniors. We need new lifeblood coming into the industry. We need to leave paths open for extraordinary hires to enrich our companies. But how do we train them? How do you train strategic thinking? These are the questions I'm thinking about. I'd love to know your thoughts.
81
101
1,177
87,900
Even though AI codegen tools can write code better than me in almost every context, I still practice writing code every day. It helps me stay sharp, and I still spot problems with AI generated code. Maybe this is cope, and maybe I just love writing code and don't want to loose it. But I'm not going to stop any time soon!
2
56
Cillian Myles retweeted
May 14
You've been asking for this one... Now in preview: Codex in the ChatGPT mobile app. Start new work, review outputs, steer execution, and approve next steps, all from the ChatGPT mobile app. Codex will keep running on your laptop, Mac mini, or devbox.
1,696
2,612
21,899
4,740,198
every dev should build a coding agent from scratch people (myself included) think it's magical or really hard, but the basics are very simple I love when things are boiled down to their essence, and this article does that for coding agents: mihaileric.com/The-Emperor-H…
43
Cillian Myles retweeted
Apr 29
Ternus has a unique chance to reset the relationship between developers and Apple: 1) Tear down the App Store tollbooth, 2) reintroduce Boot Camp for M macs so we can run Linux on them, and 3) fix the infuriating 500ms workspace animation delay. Approval rating 50% instantly.
127
72
1,991
148,346
Cillian Myles retweeted
Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found. All are fixed in v2.1.116 and we’ve reset usage limits for all subscribers.
1,916
2,586
39,779
6,471,998
thank god there might be hope
I've embarked on a new sprint. My mission is to make OpenAI models feel magical in OpenClaw in the next few weeks. Diving in today, I noticed a bug. When you configured OpenClaw to use the Codex harness with OpenAI models, auth was broken, and the system was silently falling back to the Pi harness. So nobody knew it was broken. Two PRs later (fix the auth bridge, stop the silent fallback), the Codex harness actually works. And the difference is night and day (pic related). Before: the agent didn't feel magical or proactive. It did the exact same shallow loop every heartbeat. Read the heartbeat file, check Discord, see nothing, say HEARTBEAT_OK. It ignored the rest of its instructions. Sometimes it would even reason about doing work and then just... not issue the tool calls. After: full agent loops. It reads its workspace context, interprets the entire checklist, inspects the repo, makes real edits, tries to verify them, and gives honest status reports when things are blocked. Later heartbeats show continuity, it doesn't repeat work, it picks up where it left off. I didn't change any prompting or scaffolding. Just swapped in the codex harness for pi. Lesson here is use the codex harness if you're building with OAI models. A lot more to do but this is a strong start.
70
Cillian Myles retweeted
We recently migrated our official websites to Jaspr. By adopting a unified Dart stack, we have simplified our infrastructure and significantly lowered the barrier to entry for community contributions. Read a breakdown of the migration: goo.gle/4tbqvUu
7
20
176
17,033
Hoping this computer use is good and trickles its way back to agents like OpenClaw 🤞 Love ChatGPT models for coding but having a terrible time with OpenClaw since cancelling Claude 🥲
Apr 16
Codex for (almost) everything. It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeatable tasks.
1
126
Hey @google @apple seems to me like OSes are going to need to make it possible for apps to download weights to a shared space on a phone so multiple apps can use them I don’t want multiple copies of weights that are multi GB
Google’s latest app is built with Flutter.
81
🙏🙏🙏
A little birdie is hinting at a Codex app for Mobile/iPad. I can't tell you who. Sorry don't ask. OK fine you pressured me. It's Tibo. It's always Tibo.
2
92
clean look ✨
Introducing Gemini on Mac. It’s the first time we’re bringing the @Geminiapp to desktop. The team built this initial release with @Antigravity, and it went from an idea to a native Swift app prototype in a few days. More features on the way!
1
2
197
GetX is no longer available… Who in the hell cares?
118
Cillian Myles retweeted
Replying to @wookash_podcast
I don’t review code written by agents. I measure things like test coverage, dependency structure, cyclomatic complexity, module sizes, mutation testing, etc. Much can be inferred about the quality of the code from those metrics. The code itself I leave to the AI. Humans are slow at code. To get productivity we humans need to disengage from code and manage from a higher level.
63
90
1,231
156,837
Cillian Myles retweeted
We prototyped a Flutter-specific app size analyzer. If there's interest, it wouldn't be hard to ship.
How big is your Flutter app's Android release?
17
12
198
11,566
You should not ask permission or wait to be told to do something If it’s important, just do it Even if you’re an employee When you do people start to look at you differently
1
52