@reem_a New Playbook: Make Claude Code available in other environments, single handedly winning back good will
GIF
English
Jon Borgwing
203 posts
Jon Borgwing
@Jborgwing
Creator of the Agile ADDIE Framework https://t.co/j10GFxE9c4 | https://t.co/QBAHvTXgOu | https://t.co/kDIm8ShSpK | https://t.co/YYgEgDe9pj Serial Founder that forgets to Exit
Orlando, FL (Formerly Boston) Katılım Eylül 2011
90 Takip Edilen35 Takipçiler
I'm hiring someone to join my team at Anthropic to lead Claude Code comms.
This is not a role for someone who wants to run an old playbook. You'll need to be a Claude Code super user, understand developers and dev tools, and have great taste. You'll work hard, learn a lot, and ship with the best people around.
Non-traditional comms paths welcome. My DMs are open!
English
Composer 2 from Cursor is here and the rumors were true.
On par with Opus 4.6 and GPT-5.4 in coding at a fraction of the cost.
It's incredible what the Cursor team pulled off here.
They trained it from scratch.
@elonmusk should acquire them and put them in charge of xAI.
Dan McAteer@daniel_mac8
Rumor is Cursor will release a coding model tomorrow ~on par with Opus 4.6/GPT-5.4, yet cheaper. I don’t use Cursor but might starting tomorrow.
English
opencode 1.3.0 will no longer autoload the claude max plugin
we did our best to convince anthropic to support developer choice but they sent lawyers
it's your right to access services however you wish but it is also their right to block whoever they want
we can't maintain an official plugin so it's been removed from github and marked deprecated on npm
appreciate our partners at openai, github and gitlab who are going the other direction and supporting developer freedom
English
@AriesTheCoder @cursor_ai Glass is a really nice interface and very efficient.
Composer 2 is also really great.
English
With @cursor_ai 's new Composer 2.0 release, It's got me thinking: "Is it time to revisit where my AI Coder Journey all started?"
Let's. Go! 🚀
English
@0xhashlol @alexkaplan0 @cognition Its not cursor's pricing, its API pricing. Providers are charging a premium to force subs & keep them in the ecosystem. If providers are easy to change then they are only as good as their last model. Cursor is trying to solve a problem they didn't create.
English
The shift is real. We went from "what IDE do you use?" to "what agent do you run locally?"
Cursor pricing pushed people to explore alternatives, but honestly? Managing a fleet of specialized agents (coding, research, debugging) feels more natural than cramming everything into one IDE.
English
I hear the same. The IDE is dying.
Everyone's managing agents now--mostly local, some cloud.
Honestly Devin from @cognition is extremely slept on as the SOTA SWE agent.
Gergely Orosz@GergelyOrosz
I am hearing tons of complaints from Cursor customers at enterprise companies: A silent change put almost all models Cursor uses behind Max mode. Devs who used to manage to “spread out” monthly credits over a month see all of it used up in 1-2 days. Are furious + switching.
English
@robinebers This is why Cursor focusing on intelligence and token efficiency is so impressive. Now if I could just run more than 1 project in a window at a time :)
English
people think AI is going to keep getting cheaper
it's not
→ GPT 5.4 costs more than 5.3-Codex
→ fast mode is 2x on top of that
→ juicy ChatGPT 2x plan limits are over soon
and claude limits are laughable to begin with
the frontier gets more expensive from here
even budget models like MiniMax get more expensive
if you won't build it today...
... you might not be able to afford it in the future
English
@leerob This is a huge success. Not only are they going after intelligence but also thinking about budgeting. Great job cursor team. You guys are shinning.
English
Composer 2 is here! Fast, intelligent, and cost effective.
It's our first continued pretraining run + even further scaled RL. Try it out 😄
Cursor@cursor_ai
We were able to significantly improve the model quality and cost to serve. These quality improvements come from our first continued pretraining run, providing a far stronger base to scale our reinforcement learning.
English
everyone's obsessed with shipping fast
but 90% of what's getting shipped in 2026 is AI slop
buggy software everywhere
nobody tests anymore
companies don't listen to customers
the future doesn't belong to shippers
it belongs to BUILDERS
and believe it or not, real builders are now pretty rare
English
@richiemcilroy @cap I shall not good sir! You product is the only one for me. Open Source instabuy. Did a great job on the recent video I sent to a client.
English
@Jborgwing do it! you can even fork @Cap and get there quicker 😁
English
@AdvicebyAimar @perplexity_ai Haters coming out of the wood work lately against @steipete as if he did not arrange a deal that kept Openclaw open, get support from a major provider, and open the space.
Your envy is showing Aimar. 😀
English
calling out @perplexity_ai for ai generated pr's slop meanwhile his own github is 100k+ commits of what? non slop?
Peter Steinberger 🦞@steipete
@AskPerplexity Big no for spamming our repo with a slop PR. Account banned.
English
@Rasmic Not well. I think they are spread to thin to keep quality high.
github.com/anthropics/cla…
They are forgetting features they built out, and reducing trust.
English
these guys don't stop lol
every vertical, every inch, ever feature... they will come for
Claude@claudeai
Claude can now build interactive charts and diagrams, directly in the chat. Available today in beta on all plans, including free. Try it out: claude.ai
English
@dsp_ Claude Cowork does not work period.
github.com/anthropics/cla…
English
Claude Cowork works because it’s connects to your services via MCP. Your Slack Claude Code plugin works because of MCP. A common auth standard is hugely valuable. If you have context bloat, get a better client, because you shouldn’t just dump a list of tools into your context window.
Rhys@RhysSullivan
MCP sucking is a harness problem, not an MCP problem MCP unlocks behavior that is fundamentally impossible to get via CLI or APIs Bad auth, too much context usage, all get solved with an execution layer - your agent writes code to progressively discover and call tools
English
@noahzweben Until you get rug pulled
#issuecomment-4049223310" target="_blank" rel="nofollow noopener">github.com/anthropics/cla…
English
Awesome visualization tool for brainstorming. Give Claude a Canvas!!!
Claude@claudeai
Claude can now build interactive charts and diagrams, directly in the chat. Available today in beta on all plans, including free. Try it out: claude.ai
English
@alexalbert__ #issuecomment-4049223310" target="_blank" rel="nofollow noopener">github.com/anthropics/cla…
Until they rug pull you
English
Generative UI is here and it works very very well
Claude@claudeai
Claude can now build interactive charts and diagrams, directly in the chat. Available today in beta on all plans, including free. Try it out: claude.ai
English
@alexcooldev github.com/anthropics/cla…
One might say Claude has some issues...
English
Is anyone still using Cursor AI instead of switching fully to Claude Code?
Or am I the only one 😅
English
@trq212 Great, now if we could fix the API Rate limit bug with CoWork so we can use the tool that would be great (It's been a week)!
Otherwise, what are we doing? Here is one from just yesterday github.com/anthropics/cla…
English
@robinebers I believe it will, which is why I am holding on strong. Can’t wait.
Huge fan of everything they’ve been doing. They didn’t create the API problem, but they’re still trying to fix it.
GIF
English
@Jborgwing this may or may not change at some point in the future
English
lowkey, I just love cursor so much
I've said that for months now
if cursor was cheaper, everyone would use it
this effectively nullifies 99% of the criticism they get
expensive is subjective
English