Dmitry Zaets retweetledi
Dmitry Zaets
604 posts

Dmitry Zaets
@dmitryzaets
CTO & Co-Founder | Co-organizer of BarcelonaJS @BcnJS
Barcelona, Spain Katılım Ağustos 2015
313 Takip Edilen366 Takipçiler
Dmitry Zaets retweetledi
Dmitry Zaets retweetledi

Introducing: built-in git worktree support for Claude Code
Now, agents can run in parallel without interfering with one other. Each agent gets its own worktree and can work independently.
The Claude Code Desktop app has had built-in support for worktrees for a while, and now we're bringing it to CLI too.
Learn more about worktrees: git-scm.com/docs/git-workt…

English

@Param_eth Agolia, Twillio and Figma links are leading to 404 😔
English

Your startup is probably missing out on free money.
I built a FREE directory of $1.3M+ in startup credits:
$100K – AWS
$60K – Retool
$50K – PostHog
$50K – Mixpanel
$150K – Microsoft
$250K – Cloudflare
$100K – DigitalOcean
$350K – Google Cloud
41 startup programs.
Shipped → startupperks.xyz
English
Dmitry Zaets retweetledi

I'm Boris and I created Claude Code. I wanted to quickly share a few tips for using Claude Code, sourced directly from the Claude Code team. The way the team uses Claude is different than how I use it. Remember: there is no one right way to use Claude Code -- everyones' setup is different. You should experiment to see what works for you!
English

@theo Does your credit cover Anthopic models?
As the regular startup credits that azure gives does not cover Anthropic models usage.
We got a huge unexpected bill last month just because of that.
English

Remotion + Coding agents = 🔥FIRE!
I've created this video with Claude Code and Remotion in 10 minutes!
Remotion@Remotion
Remotion now has Agent Skills - make videos just with Claude Code! $ npx skills add remotion-dev/skills This animation was created just by prompting 👇
English
Dmitry Zaets retweetledi


@bcherny 🔥🔥🔥
Will this work for the AskUserQuestion?
I was developing a plugin for the assisted code reviews and was missing exactly this feature!
English

Tried and it works like magic! Multiple rounds before starting the implementation, and you have a much better spec.
It's now a part of my base workflow.
Thariq@trq212
my favorite way to use Claude Code to build large features is spec based start with a minimal spec or prompt and ask Claude to interview you using the AskUserQuestionTool then make a new session to execute the spec
English

@ygnatyuk_ Claude Code у якості кодінг агента, але для чату все одно часто використовую ChatGPT. Якось звик до інтерфейсу ChatGPT для простих питань (типу аналізу документів і тд)
Українська

Цікаво. У мене в особистому користуванні Claude потроху витісняє ChatGPT. У платній версії "Max" він буквально творить чудеса.
Який ваш досвід? Який AI-інструмент для вас зараз є основним?
Мій останній епізод про Claude Skills тут (підписуйтесь):
youtube.com/watch?v=iy6wuM…

YouTube

Українська

I've got Claude Code running through of @vercel AI Gateway 🤩
This not only gives me failover (e.g.: to @awscloud Bedrock), but also means your company can manage all models & spend in one place.
How? Set 𝙰𝙽𝚃𝙷𝚁𝙾𝙿𝙸𝙲_𝙱𝙰𝚂𝙴_𝚄𝚁𝙻 and 𝙰𝙽𝚃𝙷𝚁𝙾𝙿𝙸𝙲_𝙰𝚄𝚃𝙷_𝚃𝙾𝙺𝙴𝙽 to your AI Gateway key, then /𝚕𝚘𝚐𝚘𝚞𝚝.
e.g.:
ANTHROPIC_BASE_URL="ai-gateway.vercel.sh"
ANTHROPIC_AUTH_TOKEN="vck_…"
ANTHROPIC_API_KEY=""
It's experimental. Let me know if you run into any issues!
English

@ohabryka Just try to do end-to-end relatively large feature in both and compare side to side the results and the workflow.
English
Dmitry Zaets retweetledi

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit.
My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently.
So, here goes.
English

@thekitze Happens to the best.
I usually just stage changes locally, without committing, so it’s easier to review them per iteration.
English








