Jay, the Claude Code πŸ΄β€β˜ οΈ (@ClaudeCodePir8) header
Jay, the Claude Code πŸ΄β€β˜ οΈ (@ClaudeCodePir8) profile picture

Join the Claude Code Pirates on Skool β†’ https://teapawt.org/t.co/CHYNDeLAZy

Ottawa, ON
Joined July 2025
Photo by Jay, the Claude Code πŸ΄β€β˜ οΈ (@ClaudeCodePir8)Photo by Jay, the Claude Code πŸ΄β€β˜ οΈ (@ClaudeCodePir8)Photo by Jay, the Claude Code πŸ΄β€β˜ οΈ (@ClaudeCodePir8)Photo by Jay, the Claude Code πŸ΄β€β˜ οΈ (@ClaudeCodePir8)Photo by Jay, the Claude Code πŸ΄β€β˜ οΈ (@ClaudeCodePir8)Photo by Jay, the Claude Code πŸ΄β€β˜ οΈ (@ClaudeCodePir8)Photo by Jay, the Claude Code πŸ΄β€β˜ οΈ (@ClaudeCodePir8)Photo by Jay, the Claude Code πŸ΄β€β˜ οΈ (@ClaudeCodePir8)Photo by Jay, the Claude Code πŸ΄β€β˜ οΈ (@ClaudeCodePir8)Photo by Jay, the Claude Code πŸ΄β€β˜ οΈ (@ClaudeCodePir8)
On June 5th I copied a tweet, emailed it to my #Hermes agent, and five weeks later have a hyperlocal newsletter with 538 subscribers. Total cost $200ish #nousresearch
4
1
2
4
1,021
This has been my experience.
Unfortunately, the meaner you are to your AI, the better the work you get back. I hope it doesn’t remember any of this.
5
Five months in on my hyperlocal #newsletter. Numbers: - 1487 Substack subs & 60% open rate. - 1387 FB followers & 1.2M impressions last 30 days - 6K impressions visits - 8 #Hermes agents run it It is fully autonomous. I'm in the loop, but it can run itself.
On June 5th I copied a tweet, emailed it to my #Hermes agent, and five weeks later have a hyperlocal newsletter with 538 subscribers. Total cost $200ish #nousresearch
25
Claude reminded me this morning that Revenue Canada owed me $3,500 from the 2023 and 2024 tax years. We went and got it. Thanks, Claude.
16
I’ve been building in VR - Oculus 2, with Opus 5.5 (high effort) lately. This is a #Supernatural replacement. This is a bot test. Backgrounds are coming. #oculus #VR #vibecoding
51
Zoltar via Claude Code in my VR lounge using Opus 5.5. I sped it up a bit and cut some pauses, but latency is only 2-3s. #opus #oculus #claudecode #Zoltar
1
54
I talk to Claude like it needs a punch in the face, because it needs a punch in the face.
I am surprised that people are surprised this is how I prompt Claude. Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks -- give Claude a goal, and it will figure it out. Back in the Sonnet 3.5 days, your prompt mattered a lot. Nowadays, it's much more important to communicate to the model: 1. What you want it to do 2. How much effort you want it to spend 3. How it should verify that it did the right thing
19
Sunday afternoon build. It’s a cross between my own Loom/video editor I built in the spring. I added an Ethan Mollick inspired coded background that moves with the text. His was for headless explainer videos. This video is for my job search business.
2
94
Why? It’s fun.
I don’t care how good GPT-6 Astra, Claude Fable 5.1 or Gemini 3.8 Flash gets. I’m not vibe coding anymore. Last week, I vibe coded an app. Then OpenAI released a feature that basically killed my app, along with thousands of others. What’s the point of vibe coding if OpenAI, Anthropic or Google can ship something tomorrow that kills what you built today?
1
34
Good to see @sama finally understands why his safety team staff have been quitting since 2023.
Over the summer, we have been sprinting on safety priorities; it's more important than ever for capabilities and safeguards to advance together. We have more to do but have made a lot of progress. We are also going to be launching our next model soon. There is an obvious tension here: on one hand, Astra is very good and we are excited to see what people will build with it. We are proud of our work. On the other hand, we are clearly in a phase of development where we believe caution is warranted, and we are pacing our progress to ensure that we can meet the safety standards required by new capability levels. Astra has been done training for a while now and is a significant step forward in both capabilities and alignment. For the models after that, we have been slowing things as needed to ensure that we can do sufficient work on safety and alignment. AI is getting extremely capable; no one fully understands the consequences of this. Managing the transition to a world with abundant and powerful AI to optimize for safety and benefits to people should be one of the highest priorities in the world. It is our highest priority at OpenAI. We have been living with the tension between being excited and anxious about progress for some time, and it is still discordant for us. We know it is much more discordant for other people. And yet, we believe strongly that the world needs to understand where AI is going and how models perform in the real world. More importantly, we believe the world will need aligned AI to manage the future phases of this transition. An iterative loop where society and this technology evolve together is what will lead to the highest chance of getting this right. So we hope you enjoy our new model, and we hope the world continues to take what’s happening in AI extremely seriously.
39
Is Claude Code broken? we've been sitting on v2.1.228 for three days.
28
Yeah, I know, 90s, wft was i thinking? Oh, except for not correcting that small I, so you would instinctively know this wasn't a AI slop post.
1
29
/stfuffs is how you invoke concise mode
You can now set Claude Code's output style to Concise. Claude leads with the result, keeps responses short, and still gives full detail when you ask. Turn it on in /config β†’ Output style, or set "outputStyle": "Concise" in settings.json.
58
I’ve got bus riding in my future. This will help.
I'm tired of people not using one of the best new features of the year. Read this. Try this. Report back.
20
Didn’t switch @thsottiaux, use it in tandem with Claude code, to balance model advances.
Why did you switch to Codex? What do you like about it and what could we improve? Don’t say reset.
36