martin.p

we shipped fat man walking today habit tracker where your character literally evolves from couch potato to beast as you build streaks.. the character on screen gets fitter as you do live on the App Store now

2 months in JP coming to an end soon. it's so weird how my timeline changed from entrepreneurship and builders to full on Japan twitter. I'm not saying I didn't enjoy the switch up once in a while, but not seeing everyone hustling kinda made me lose motivation to post a lot :D

@levelsio @arena if it wasn't hard before to tell what's real or not, it's not getting easier with this 🫠

OpenAI's new image model GPT-Image-2 has leaked It seems to have extremely good world knowledge and great text rendering Possibly better than Nano Banana Pro It's on @arena under code names: - maskingtape-alpha - gaffertape-alpha - packingtape-alpha

learn from my mistakes: set reminders for when tokens or credits are about to expire. ur future self will thank you :D

a year ago I was actually commited af to n8n workflows, as they make entry and exit point to other applications really easy. nowadays I feel like it's not even worth opening the app if my agent can basically oneshot whatever I want 🙈 Shit's changing too fast

why is anthropic banning people's accounts for analysing the leaked source code? Seems like not the smartest move to make. Just accept you fucked up, and instead why not do a video on the architecture and how they built it with claude

it likely depends on your phrasing. if you simply ask for a review it likely 'wants' to find something (same as when I'm reviewing someones code I'm subconsciously trying to find an issue that might not be there). Try providing the plan, then saying 'here's my plan, are we good to go?'

My biggest challenge with vibe coding / agentic engineering lately has been getting stuck in what I call a "plan doom loop" - have AI write a plan - review myself, seems good - have AI review plan, it always finds something - repeat It drains my time and energy to determine how important the "findings" really are Who has solved this

@thekitze now reprompt in new session with "praise it properly but rost where it's due" and let's if that changes the rating

🚨 BREAKING: GPT 5.4 rates the Claude Code codebase 6.5/10 💀 "This is not junior spaghetti. This is staff-engineer spaghetti: performance-aware, feature-flagged, telemetry-instrumented, surgically optimized spaghetti" 😭

@blankoween @TukiFromKL yeah sure it's a good piece of software but people act as if they leaked their model weights or smth.

@OnePromptMagic @TukiFromKL This is such a cope. It's 512k lines of code. You need 512k lines of code to call apis? It's the whole agentic logic in there.

🚨 Do you understand what just happened to Anthropic.. someone on their team ran a production build of Claude Code.. the compiler generated a .map file.. which is literally a blueprint that reverses the entire codebase back to its original source.. and then they published it straight to npm for the whole world to download.. it's like locking every door in your house.. installing cameras.. hiring armed guards.. then accidentally uploading your floor plans to Google Maps.. this is the same company that told Congress AI is an existential threat.. the same company that spent $8 billion building "the most safety-focused lab on earth".. the same company the Pentagon blacklisted as a "supply chain risk" because they were supposedly TOO principled.. and they got exposed by a config file that any mid-level engineer would've caught in a code review..

I'm ususally all about leting the AI do the work, the research, the thinking, while I'm doing the 'big' thinking. but lately Opus is just actually smarter than me in many if not most cases. That's why I sat down and read a 1000 pages of system architecture books. gotta keep up with the AI overlords, at least as long as I still can :D

coffee up, today's the day for building some wild shit ☕️

I just finished reading "Clean Architecture" by Robert C. Martin. In a future where agents take over all of programming, it will be crucial that clean patterns and architecture is in place. why? because agents will always look at how you've implemented your code so far and use similar style/patterns. E.g if you got loads of comments in your code the AI will continue adding comments. This will bloat the whole repository and make it less readable and maintainable. Same happens with bad code design, AI will rather multiply on your bad code than suggest a refactor, because it wasn't asked to. I then setup a claude skill that scans the repo based on my learnings in the book. Idea is to have a bigger refactor to adhere to best practises now, and later run the skill every few PRs, checking for clean architecture. I assume that after the refactor AI will however already do a cleaner approach than before due to the patterns it will find. Let's see how it goes

claude code has been amazing in helping me setup my sales pipeline, but in long sessions it often gets lazy and does things half assed. it would tell me "yeah I'm sure everything is ready to go" but when checking manually there still are many flaws or missing pieces. To solve this, I've implemented "santity-check" endpoints throughout the infrastructure that when called do all the checks I'd do manually. these provide a list of open issues I can then paste into claude to fix until all checks pass. the endpoint is alao available viam mcp so I setup a skill to do all sanity-checks and fix until green. this helped me a lot with concsistency in my AI outputs even for long sessions

I usually work with 4 claude code windows, and I'd try to not have them work on the same domain. like one builds on the product, one works on the pipeline, one is for trying things out etc. one thing that works for me is to change background color on terminals just so I can associate the context windows faster in my head. Another thing that works for me is to have all terminals on one window and NO browser open there. all of the tabs are open on another screen to prevent distraction while waiting for agents to finish. I'm definitely in the same boat as you and these are just some things that worked for me. Will continue improving on my flow and share it

My single biggest pain point right now: AI-induced attention deficit I have 5 Claude Code sessions running 10 Terminal tabs open 50 browser tabs open 100 X articles in my bookmarks When there are multiple AIs working for you, you're constantly task switching When you're waiting for AI to output, you're constantly distracted Because what used to be hard is now so easy, you always wanna do more, more, more Because of the speed of the AI news cycle, you feel a constant need to be on this app Add all this up and the result: you live in a constant state of distraction & delirium. Focus & deep work is harder than ever If anyone has figured this out pls teach me how

as technical founders sales always comes short. we're not good at it (yet), but we're getting there. One hack we're applying right now for us to keep learning: one sales tutorial every 2 weeks with followup discussion + action items - works wonders.

@zuess05 same, I even got one of those old subscriptions where you'd still switch into slow mode instead of running out of credits. but it's just still so little usage on the god models (I'm out of opus 4.6 after a day max)

I am canceling my Cursor subscription. Cursor was the absolute best tool on the internet for the last year. But with Claude Code, Codex, and Antigravity doing the heavy lifting now, it just doesn't make sense anymore.

so many people complaining about claude limits being reduced. IMO this is clearly just people getting used to the new 1M context window. it's so convenient you just keep on writing in that one chat window. the underlying issue is tho, that with longer context come higher token costs, that's just how it is. restart your sessions from time to time and you're fine. I personally didn't see any decrease in limits at all.

@levelsio how are you doing the blocking process? I assume not manually? 🙈

To give you an idea of how bad the AI bot problem was getting I muted about 17,500 of them, then started blocking them recently, so another 3,000 99% bots So I blocked about 2.5% of my follower count and didn't even get close to stop AI replies either

@dev_maims forget about whatever developers were 5 years ago. you need to work one meta level above that now. Anyone who doesn't will likely have to switch carriers as it likely won't be a hard choice in due time wether to employ someone or to just up your claude credits.

If Claude Code can now write code, run the app, debug errors, review pull requests, and even fix bugs automatically what exactly is left for junior developers to do?

@tomosman @AnthropicAI people are just getting used to keep working in their 1mio context window chats. and ofc the fuller your context, the more tokens each request burns. Just restart your session here and there.

Yo @AnthropicAI why are you pillaging everyone's usage. Has it been greatly reduced without telling anyone?