Jozef Lipovsky retweeted
Frantically fixing a confusing product caused by frantic shipping is just more of the same.
Pause and step back. Get the team clear on what you’re building and why. Have clarity to guide the shape, what ships and what doesn’t.
Quality is a way of working, not a cleanup sprint.
Jozef Lipovsky retweeted
The "whiteboard defense:" I should be able to pull you aside at any moment and ask you to explain any customer-facing system you've shipped. You should be able to clearly explain how it works and defend the decisions you made. This is my benchmark for responsible AI usage.
I don't expect line-level familiarity with the code. I don't care if you remember the exact function name or implementation detail. You may not even know it. I don't care.
But if I ask "why did you do X instead of Y?", "what happens if this actor behaves maliciously?", "what data structure did you use here and why?", or "where does this fail?" you should be able to answer confidently.
For PoCs, demos, experiments, whatever: I don't care. Generate 100% of it and understand none of it. Speed over quality every time in those specific scenarios.
But if you're shipping customer-facing work, you can't be shipping things you don't understand at a high level.
Jozef Lipovsky retweeted
my days are like `N` hours of working with frontier models, babysitting them in frustration and disbelief at the frequent errors and slop
interrupted by `M` min breaks of browsing X takes about how the same models (and _especially_ the next gen!) are superhuman at ~everything
tfw your model is so bad at instruction following, you have to remind it to shut up every single turn (including tool-calls)
Jozef Lipovsky retweeted
- safety researcher who quit dramatically on X, writes a big think piece on subst*ck and then starts a company a few months later doing the same thing
- AI founder preaching “We’re not replacing anyone. We’re giving them their time back.” “we believe in human dignity” in the manifesto, then the pricing page is per-seat-eliminated.
- VC that loudly preaches how they are AI native and bullish on the sector but doesn’t know what a token or context window is
- The “AI ethics” advisor who is on retainer at four labs simultaneously
- reformed crypto guy who was hyping NFTs in 2021 but is now suddenly an AI expert
- an AI first SOC 2 company that is actually a giant scam using templates and PDFs
- early 20s guy that raised a comical amount of money after dropping out of Stanford but nobody actually knows what his company does and he’s at every tech event and meetup
- SF hype guy who posts constantly about how the city is amazing even though all he does is regular mundane things you can do in any other city, while paying 4k for a crappy studio apartment
- AI PM that doesn’t actually make any decisions and just feeds docs and prompts into Claude
Hey @icbc would be nice if someone could fix this. 3 different devices, 3 different browser the same experience...
🤣🤣🤣
it was fun while it lasted
blog.krzyzanowskim.com/2026/…
Jozef Lipovsky retweeted
It’s 2028. Welcome to the token economy.
We realized that all software and activities can be shaped to spend tokens, which is good, because more tokens we spend, the more productive and happier we are as a society.
My Openclaw agent goes to wake up the alarm agent, which then after running for 5 minutes in a new sandbox and burning 500 tokens, plays a sound to wake me up.
My news agent reads all my email, including spam, crawls the web, and gives me a 5-line summary of the world.
Very efficient.
I get to my desk. 100 agents have been chatting all night. 10k LOC ready to merge. I tell my merge agent to press the merge button.
Check my company token leaderboard. 15,000 tokens burned and I haven’t even done anything yet.
I tell my manager agent to boot up my other agents.
First thing they do is vibe code a Slack clone so they can post progress updates to each other.
I tell them to find something to do and go to lunch.
Back from lunch:
Company leaderboard says 25,000 tokens burned.
More than Chad.
Very nice.
At 80,000 tokens a day you unlock Platinum tier, which gives access to faster models that can burn tokens even faster.
Agents built another 10k LOC while I was out. I don't know what it does so I tell my review agents to tear it apart, rebuild it, and merge it again.
Excellent token utilization.
Then I ask my social media agent to post that software engineering is dead because agents do it now.
More tokens.
I get hungry, so I tell Openclaw to vibe code DoorDash.
We call it ClawDash. Iterate on the logo for about 5mins with my designer agent. We make the red with some lobster claws. Very appropriate.
It takes 5 hours, several new agents to ping the status, and one human recruiter signing up a Mexican restaurant, but eventually my food arrives.
I heat it in the microwave with a dedicated heating agent program I built for this purpose.
Before bed I check the my dishwasher dashboard. My agents run through the log history since dawn of time, and tells me that it says it ran 23 hours ago, and was opened shortly after so it’s probably clean.
Final leaderboard check:
81,239 tokens burned.
Platinum achieved. I now have access to new models faster, which burn tokens faster, and will receive Platinium plaque in the mail.
Time to wind down with some generated Fraser episodes which I tell my entertainment product agent to script, review, and finally generate.
Important thing is the token burn never stops.
Jozef Lipovsky retweeted
Can't believe this timeline if free 😄😭🥸
you created a problem
you sell a problem
you reject the consequences
Hey @mec, if the goal of whatever this is was to make sure your customers unsubscribe from your spam shit, I think you succeeded. Congrats.
State handling is DIFFICULT. Spoiler alert, there are no new messages to download. This has been broken forever. Hey @Apple, can someone finally fix your desktop mail client? Thanks



















