Are you a fellow American who never understands what is going on with offsides in these World Cup matches? Spend 5 minutes playing my (vibecoded) game to learn:
offside.futbol/
1
2
36
Very good read. But also, it’s very refreshing these days to read a piece of well-thought-out writing that is completely free of AI-assisted language.
Some more thoughts on looping in coding agents. lucumr.pocoo.org/2026/6/23/t…
1
20
Maybe this is an unfair comparison, but Apple saying they’re going to release the AI stuff “in the Fall” sounds insane when you contrast it with Anthropic releasing like 10 things a week
1
24
At the extremes, Goodhart’s Law makes tokenmaxxing look silly. But the average employee right now doesn’t know how to use AI properly. They don’t know how to spend that many tokens. So tokenmaxxing is actually a good policy.
I know a few people inside Big Tech, and I'm sorry to report but Token Psychosis is real.
Their bosses are hyperfixated on AI usage and tracking who uses the most tokens, so they're essentially running agents 24/7 on do-nothing tasks just to use more tokens. Incredible stuff.
1
1
56
“Connected agent updating an HTML document” replaces and is way better than a large number of SaaS products right now
Finally killed Asana by rebuilding my to-do list as a live artifact in Claude then using scheduled tasks to scan my slacks, email and calendar each day to propose to-dos
Infinitely, unbelievably better and more effective
More and more workflows being sucked into Claude
1
28
Wanted to give them the benefit of the doubt, but Opus 4.7 has been pretty bad for me. Takes at least 2-3x the tokens to complete an equivalent task as 4.6, so I run out way faster than before. The results aren’t significantly better either, certainly not 2-3x better
12
Anthropic vs OpenAI so far is one of the shining examples that product still actually matters. Not just momentum, business agreements, brand recognition, etc
22
No one tweets on this level
Starting to appreciate AI’s so-called “jagged frontier.” It’s obviously really powerful for coding, accounting, graphic design, economics, trip planning, reviewing legal documents, DIY projects marketing, advertising, etc. Yet somehow still terrible at writing and interviewing.
1
11
Skills are amazing, but the more I try to share them with others, I’m convinced that the best thing to do instead is share a CLI and tell them to have their agent make their own skill in a way that makes sense for them
it can be tricky to share skills between harnesses since the features of those harnesses can be quite different like you said (e.g. does it have subagents, does it have askuserquestion, what is the frontmatter, etc)
but I do think skills as a concept will still be a winning move in the end, the harness can create skills for you and the progressive disclosure of skills is a killer use case. your slash commands are already quite close to that, maybe if you let them live in a folder?
9
Kudos for willingness to rebuild, but why would I want all this running on a proprietary service rather than my own Claude Code?
18
Hey everyone, we’re “build first” now! First step, you need to write that prompt…
At @Google, we are moving from a writing‑first culture to a building‑first one.
Writing was a proxy for clear thinking, optimized for scarce eng resources and long dev cycles - you had to get it right before you built.
Now, when time to vibe-code prototype ≈ time to write PRD, PMs can SHOW not tell. Role profiles are blurring, creativity and building are happening in parallel.
70
The silver lining to this awful era is that it allows a lot of tech/silicon valley people to show who they really are. People will be less trusting of tech in the future, which they probably should be.
Embarassing thing to tweet. Here's a non-exhaustive list of state-led initiatives that made life better for the weak + poor:
- Deposit insurance
- Clean Air Act
- Ending leaded gasoline
- Child labor laws
- Child vaccination programs
- OSHA
- Rural electrification
- GI Bill
22