Sabitlenmiş Tweet
I Am Devloper
9.2K posts
I Am Devloper
@iamdevloper
just your friendly neighbourhood printer fixer 💸 promotional content: https://t.co/mz9fc9Cprl https://t.co/JcbaPh9EXs - daily dev puzzle
UK Katılım Nisan 2012
0 Takip Edilen395K Takipçiler
> ok, give him a deadline to use Fable by. Ok, now extend it once he's used all his token
English
person who vibe codes an app but then who now needs to use App Store Connect
Agita Christie@pagan_hoetry
The World Cup has done something to me. I just might fuck around and get really into soccer. It feels incredible to drink three to eight beers in daylight hours and scream “This is a fucking disgrace!!!” at the television in a bar full of people less invested than you. I get it
English
I couldn't find my cat earlier, so I just presumed he'd also joined Anthropic...
English
I think about it 8 times a month
jake@_jkpnro
this tweet & reply are ingrained in my brain and i will never be free of them
English
adding your own review description to a Claude generated PR is like when you let a child add the chocolate chips to a cookie batter you've made
English
> hold on. your disaster recovery plan is ‘it’s probably still in my Claude chat history’?
English
I Am Devloper retweetledi
Knockoff is now live!
Filter out the knockoff crap brands on Amazon.
Sorry to brands like WNPETHOME, EHEYCIGA, YXYL, LU&MN, JOYIN, TOMY, GODONLIF, YOOJEE, LINGTENG, LANEIGE, VISCOO, BIODANCE, COOFANDY, BALENNZ, TOSY and LUENX.
knockoff.shopping
Josh Pigford@Shpigford
built a little chrome extension that lets you dim (or hide!) all the crap, mass-produced, fake brands on amazon. should i release it?
English
Backbone walked so React could crawl so <whatever Claude picks> could run
English
...what life experience do you think an LLM gets exposed to?
Ryan Hoover@rrhoover
I don’t understand the argument that LLMs can’t come up with original ideas. “It’s just trained on existing data, predicting the next token.” How is that different than human ideation? We’re also pattern-matching machines, influenced by our life experience.
English
not magic, you still steer it. but "agents that argue with each other" beats "one model agreeing with itself" and I didn't expect to mean that.
@Bloome_im if you want a look:
aisecret.co/Bloome
English
Bloome keeps everyone's input, humans and agents, in one shared conversation, and when someone joins late an agent just summarises what they missed.
The agents don’t just argue, they refine the work step by step until it becomes a usable final output you can actually act on.
asynchronous collaboration where nobody has to say "quick recap for those just joining."
English
Bloome lets multiple AI agents into one chat where they check each other's work. one drafts, one disagrees, one finds the thing both missed. finally, a team meeting where nobody's clashing.
humans can also stay in the same conversation, so everything happens inside one shared workspace instead of scattered tools. 🧵
English