Adel.O

Entrepreneur | R&D Engineer | Digital Marketing | Senior Paid Media Specialist| AI Geek

[Adel.O @AdelOGer]

@ItsFinlayW SKILLS

[Ejaaz @cryptopunk7213]

fucking ruthless lol. now we know why anthropic left the board of figma this week

they built a product that not only replaces them it’s just better

Figma stock is getting crushed on the news and already down 50% this year 💀

claude design

> reads your code base,
> creates a custom design system for it
> uses new opus 4.7 to create design assets

this is 90% of the work designers do.

[Amjad Masad @amasad]

SEO audit your site.

[Adel.O @AdelOGer]

@mikefutia ADS

[Adel.O @AdelOGer]

@Alphaecho207 Need

[Adel.O @AdelOGer]

@shedntcare_ Os

[Noah Zweben @noahzweben]

Thrilled to announce Claude Code auto-fix – in the cloud. Web/Mobile sessions can now automatically follow PRs - fixing CI failures and addressing comments so that your PR is always green.

This happens remotely so you can fully walk away and come back to a ready-to-go PR.

[Adel.O @AdelOGer]

@AhmedReza @paulg Exactly. Markets don’t reward abstract vision for long. They reward repeatable economic value. The moment AI shifts from “innovation” to “this booked revenue or prevented missed opportunities,” the conversation changes. For SMBs, cash impact beats thesis.

[Adel.O @AdelOGer]

@JunoAgent how do I get invited?

[Ihtesham Ali @ihtesham2005]

Prompt engineering is dead.

Anthropic recently released the real playbook for building AI agents that actually work.

It’s a 30+ page deep dive called The Complete Guide to Building Skills for Claude and it quietly shifts the conversation from “prompt engineering” to real execution design.

Here’s the big idea:

A Skill isn’t just a prompt.
It’s a structured system.

You package instructions inside a https://t.co/ayF9XmnQpU file, optionally add scripts, references, and assets, and teach Claude a repeatable workflow once instead of re-explaining it every chat.

But the real unlock is something they call progressive disclosure.

Instead of dumping everything into context:

• A lightweight YAML frontmatter tells Claude when to use the skill
• Full instructions load only when relevant
• Extra files are accessed only if needed

Less context bloat. More precision.

They also introduce a powerful analogy:

MCP gives Claude the kitchen.
Skills give it the recipe.

Without skills: users connect tools and don’t know what to do next.
With skills: workflows trigger automatically, best practices are embedded, API calls become consistent.

They outline 3 major patterns:

1) Document & asset creation
2) Workflow automation
3) MCP enhancement

And they emphasize something most builders ignore: testing.

Trigger accuracy.
Tool call efficiency.
Failure rate.
Token usage.

This isn’t about clever wording.

It’s about designing an execution layer on top of LLMs.

Skills work across https://t.co/pDY56kadwE, Claude Code, and the API. Build once, deploy everywhere.

The era of “just write a better prompt” is ending.

Anthropic just handed everyone a blueprint for turning chat into infrastructure.

Download the guide here: https://t.co/xEZ78RGkYu

[matt palmer @mattyp]

Build amazing apps on Replit, right from @ChatGPTapp

Live now on ChatGPT web :)

[NVIDIA AI Developer @NVIDIAAIDev]

🎉 Congrats to @MistralAI on the launch of the new Mistral 3 open family of models

Mistral Large 3 delivers up to 10× performance on NVIDIA NVL72 by stacking the benefits of large scale expert parallelism, inference disaggregation, and accuracy-preserving NVFP4 low-precision inference.

Trained on NVIDIA Hopper, these models deliver a range of size, scale, and efficiency to meet a wide variety of needs:

✅ Mistral Large 3: multimodal and multilingual MoE model with a total parameter count of 675B

✅ Ministral 3: small, dense models each with base, instruct, and reasoning variants

Learn more ➡️ https://t.co/YZ9AuzwQ9d

[OpenAI @OpenAI]

You can now use ChatGPT Voice right inside chat—no separate mode needed.

You can talk, watch answers appear, review earlier messages, and see visuals like images or maps in real time.

Rolling out to all users on mobile and web. Just update your app.

[Paul Adams @Padday]

We're rethinking and reinventing how we market @intercom and @Fin_ai. We're building a new way because it's necessary - for us, and we think for you too :)

We're hiring for a new role: Full Stack Marketer.

Details on why we're doing this in the video, link to the job ad in the comments.

Love to hear your thoughts!

[OpenAI @OpenAI]

Turn on agent mode and ChatGPT can take action for you—research, plan, and get things done while you browse.

Now in preview for Plus, Pro, and Business users.

[Adel.O @AdelOGer]

@aryanXmahajan AI

[Adel.O @AdelOGer]

@amasad Eid Mubarak

[Adel.O @AdelOGer]

@sairahul1 AI

[Brady Long @thisguyknowsai]

I ran a brutal comparison between DeepSeek-V3 and Qwen 2.5.

One AI dominated. One failed miserably.

Here’s what happened (with video): 👇

[Brady Long @thisguyknowsai]

DeepSeek R1 claims to rival ChatGPT-o1.

I pushed them to their limits.

Let’s just say… I was NOT expecting these results.

(Full video breakdown) ↓