Joined January 2011
158 Photos and videos
Pinned Tweet
Got a new Shopify app idea. - sent 200 DMs - got 20 positive responses - going to build in 48hrs this weekend and live tweet it #buildinpublic #appchallenge
29
14
311
We got our first customer on Roughcut, zero to 1 βœ… 1 to 10 ⏳
1
1
103
Mat made a video for his startup by hand. then the replies started. "what tool is this" "what'd you use" There was no tool, so he jokingly told me to go build one I took it litterally, say hi to Roughcut πŸ‘‡ comment "VIDEO" and i'll DM you the beta link
5
1
5
657
This is just amazing
I made this motion design video in 1 prompt. Introducing RoughCut powered by Claude Fable 5. 1 voice-over script and you have a video in 20 minutes. Animation, Voice, Sounds, Music, everything! 100 beta spots available.
1
3
6
2,771
Claude weekly limit already at 53%, I've been using Fable for a day...
1
177
Fable made me the most productive I've ever been in a while. Haven't had this feeling in a long time!
44
Look at all the cool stuff you can do with grok CLI! Can't wait to use it
this is wild. grok build is now in beta. you can generate images, videos, and build full automations with a cli directly inside x. available now for supergrok x premium users. plan mode orchestrator support is built in.
1
201
Grok CLI just came out, The terminal UI looks sick, what took you guys so long ?
154
I was wondering when a new model might come out. I know what i’m doing this weekend
May 28
Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors. Available today at the same price.
1
3
117
Started seeing this: Β§ A lot more in AI generated responses. Is it the new β€” ?
2
161
I got tired of losing sessions when I accidentally closed my terminal. So I created this: Auto-resume claude code sessions. Per-pane isolation, per-project isolation so multiple sessions in the same dir don't clobber each other. gist.github.com/Crunchyman-r…
2
270
RIP buddy, bring him back
69
I like my new buddy, makes me feel like I'm pair programming, drop your buddy in here!
136
Ralph Krysler πŸͺ“ retweeted
every time you start a new claude code session you spend the first 10 minutes re-explaining your project "here's the stack. here's what we're building. here's what was decided last week. here's the file structure. DON'T TOUCH THIS PART WE JUST REBUILT IT" but it's not just your own context. your teammates shipped 3 new things since yesterday, two architectural decisions changed and a dependency got swapped out. you need to capture all of that too, or claude is building from a stale snapshot you won't remember everything. so claude compiles context from scratch, misses things, and pulls in a direction that might completely miss the point. now multiply that by every dev on your team, every session, all day literal coordinated drift what we do instead: the .hamster folder syncs decisions, plans, and context to the filesystem automatically. claude reads it and just knows. no re-explaining. no stale snapshots. everyone's always got a fresh .hamster folder which updates in real-time as the rest of the team (or you) ship decisions, tasks, briefs, methods, skills, etc try it. you'll love it β†’ @usehamster
6
12
78
9,056
Ralph Krysler πŸͺ“ retweeted
everyone on your team maintaining their own CLAUDE.md is a symptom, not a solution. the root cause is that shared context has nowhere to live and evolve as your team makes decisions. you can't fix it with naming conventions or a better folder structure. decisions need a home. not a static file someone remembers to update. a workspace that accumulates as the team works. when a decision changes, it changes once, and every agent on the team pulls from that. there's no need to keep the markdown files up to date or copy-paste anything anywhere. claude just knows. your PRDs, your tasks, your skill files, your CLAUDE.md are all projections of the same underlying decisions. if the decisions live somewhere real, everything else stays aligned. if they stay up to date automatically, the rate of progress can explode because the synchronization overhead disappears. that's what we've been building into hamster. decisions get a home. blueprint holds your product's current state. methods encode how agents should work. the projections stay aligned because the source of truth is real. dm if you want to try it GA reeealllly soon!
5
7
34
3,345
We're so back baby. But for how long ?
Mar 13
1 million context window: Now generally available for Claude Opus 4.6 and Claude Sonnet 4.6.
209
Went back from using opus 4.6 1M tokens to just normal opus 4.6 What a difficult life
1
179
I feel like all AI needs right now is 1M token context, I often find myself solving my problems at around 50% of that, so 500k to 1M is the sweet spot per problem
66
Opus on 1M token is really hard to attain, I find myself often finishing at like the 50% mark lol
141
AI coding isn’t the bottleneck anymore, PR reviews are But the fix isn’t β€œreview faster” or find tools that can help me review faster It’s building a harness where bad code can’t survive long enough to waste human attention But how do you do that ? πŸ‘‡
2
1
194
6/ You talk to AI for hours. It says it understands. Creates a PR. Says it works. You test it. Doesn't work. Now you're babysitting every agent instead of letting them run. Harness first. Then scale agents
1
93
7/ The best AI teams won’t be the ones with the smartest prompts They’ll be the ones with the strongest harnesses The ones that are enabling AI workflows, not prompting and praying πŸ˜†
74