moi

course poursuite avec celui que je dois être

[OpenShip @openshipio]

You don't even want to know what sending 80,000 emails would cost you in 1 week.

Postmark: $100+
SendGrid: $90+
Resend: $80+
Mailgun: $80+

OpenShip: $0.

Deploy it on your 5$ VPS.
Unlimited domains.
Unlimited inboxes.
No per-email bill.
No vendor lock-in.

And yes - it works with one-click setup.

No deep infrastructure work.
Just add a few DNS records, and you're ready to go.

[moi @DarkLink79]

hype

[GORM THE OLD @GORMTHEOLD25]

Resident: in da Hood 4 (A.I. Video)

[Wu-Tang 👐🏾 @Massamba_3]

Tu m’étonnes qu’ils étaient boosté apres, mes bons vieux

[Kaeru 🎮 @MemeCryptoFR]

🌞 Resident Evil 4 version détente, ça donnerait ça 😅

Plus de zombie, plus de cris, plus d’horreur. À la place : soleil, habitants sympas, musique chill et Leon qui vient juste passer de bonnes vacances 😭

[ℏεsam @Hesamation]

bro created an AI job search system for Claude Code that scored 700+ job applications and actually got him a job.

AND IT'S NOW OPEN-SOURCE.

It scans multiple company career pages, rewrites your CV per job, and even fills application forms. The repo has:
> 14 skill modes (evaluate, scan, PDF, ...)
> Go terminal dashboard
> ATS-optimized PDF generation via Playwright
> 45+ companies pre-configured (Anthropic, OpenAI, ElevenLabs, Stripe...)

GitHub: https://t.co/PwrYBOAphi

[Boris Cherny @bcherny]

I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most.

Here goes.

[Oliver Prompts @oliviscusAI]

someone built a VS Code extension that turns your AI agents into pixel art characters working inside a virtual office.

it’s free, open-source, and honestly the coolest dev tool i've seen all month.

[Melvyn • Builder @melvynx]

Holy shit

The guy who BUILT Claude Code just shared his actual workflow

Boris Cherny runs 10-15 Claude sessions in parallel every single day

While you're prompting one AI, he has 5 in his terminal + 5-10 on the web all shipping code simultaneously

And the real weapon?

His CLAUDE․md file

Every time Claude makes a mistake, the team adds a rule so it NEVER happens again

Boris literally said: "After every correction, end with: Update your CLAUDE․md so you don't make that mistake again"

Claude writes rules for itself

The longer you use it, the smarter it gets on YOUR codebase

His other insane detail: he hasn't written a single line of SQL in 6+ months

Claude just pulls BigQuery data directly via CLI

Claude Code now accounts for 4% of ALL public GitHub commits

Engineers who haven't set this up yet are already behind

This CLAUDE․md template is the difference between using AI as a chatbot vs using it as a fleet of senior engineers

Drop it in any project, free

[Stitch by Google @stitchbygoogle]

Meet the new Stitch, your vibe design partner.

Here are 5 major upgrades to help you create, iterate and collaborate:
🎨 AI-Native Canvas
🧠 Smarter Design Agent
🎙️ Voice
⚡️ Instant Prototypes
📐 Design Systems and DESIGN.md

Rolling out now. Details and product walkthrough video in 🧵

[NVIDIA GeForce @NVIDIAGeForce]

Announcing NVIDIA DLSS 5, an AI-powered breakthrough in visual fidelity for games, coming this fall.

DLSS 5 infuses pixels with photorealistic lighting and materials, bridging the gap between rendering and reality.

Learn More → https://t.co/yHON3nGyxE

[🙏THUG🙏 @ANIDEEZY]

never in my life seen a nigga play resident evil like call of duty search n destroy

[Axel Bitblaze 🪓 @Axel_bitblaze69]

spent most of my sunday reading this page guide from anthropic

it’s basically their full technical breakdown on how to build skills for claude

few learnings i’d like to share,

first thing thats basic, and im guessing most you might know is how much time we all waste repeating ourselves to AI

every new chat starts the same way, explaining your tone, explaining your style, explaining how you want things done
over and over again

instead anthropic’s solution is something they call skills

basically you teach the AI once. your tone, your workflow, your rules. save it in a folder and now every conversation already knows how you work.

second thing i learned is something anthropic actually admits themselves
AI is lazy unless you tell it not to be
their models tend to skip steps or rush answers unless you explicitly tell them to slow down.

their own suggestion is literally just telling it.. take your time, be thorough, don’t skip steps

sounds simple but once you start adding that the quality actually improves a lot.

third thing that stuck with me is the idea that AI shouldn’t be trusted for accuracy checks

anthropic says something very clear in the guide.. language models interpret things
code verifies things

so if you need something validated, calculated, or checked properly, don’t ask the AI to reason through it.. ask it to run a script instead.

for example instead of saying “does this data look right?”

you say “run this python script to validate the data”

the difference is huge.

another interesting point they make is about context.. everyone assumes more context = better output

but anthropic says the opposite happens a lot of the time. too much information actually makes the model worse.

their system is designed to load the minimum amount of instructions necessary because once you dump huge amounts of text into the model, performance starts degrading.

the last part of the guide talks about something i think most people still underestimate

AI becomes much more powerful when it’s connected to tools

AI alone is basically like a very smart intern that knows a lot but can’t actually do anything.

AI connected to tools.. your documents, databases, project managers, scripts.. suddenly becomes something that can actually execute work.

after reading this whole thing my perspective changed a bit.. we’re slowly moving away from just chatting with AI
towards teaching AI how to behave and operate

not with code necessarily, but with structured instructions that define how it works.

and my biggest takeaway from the whole guide is simple

the people who learn how to properly teach AI their expertise and workflow are going to have a massive advantage over the next few years

everyone else will still be typing random prompts into chat and wondering why the output feels average.

spent most of the day going through it and yes it was worth the time.

[Eva 30Th Short movie @Dabedbyeam]

Evangelion Asuka short movie Eva 30Th HD

[NikTek @NikTek]

Resident Evil 9 Leon's Theme Music is straight up fire.

I can feel my testosterone levels shooting up every this starts playing

[Mark Gadala-Maria @markgadala]

Someone is using AI to make babies do stand up comedy.

We are cooked.

[☆オードリーAudrey☆ @aitaikimochi]

The new Evangelion anime series teaser PV aired on Japan's TBS channel today, and here's English subs for the trailer!

Directors: Kazuya Tsurumaki & Toko Yatabe
Writer: Yoko Taro
Music: Okabe Keiichi

The NieR influence for this anime is so strong omg 😱

[Anime Rave @AniRave]

The Neon Genesis Evangelion 30th Anniversary Festival has begun, debuting a new short anime film.

Hideaki Anno revealed they finished it at 6 AM today.

The “EVANGELION 30+” short stars Asuka Langley as the protagonist, features both Asuka Langley and Asuka Shikinami, and explores 90s Evangelion, parallel worlds, and an alternate epilogue to the original timeline.

[J. Cole @JColeNC]

My new album The Fall-Off available now everywhere https://t.co/xYS9YERjyu

[Google DeepMind @GoogleDeepMind]

Step inside Project Genie: our experimental research prototype that lets you create, edit, and explore virtual worlds. 🌎