Amine Yagoub

I 💗 doing web development

[Amine Yagoub @AmineYagoube]

استلمت كود من مطور، وأنت غير تقني؟ 🤔
عملت أداة اسمها CodeTribunal ترفع الملف، والـ AI يفتح "محكمة" ويكتشف لك بالضبط أين الأخطاء الأمنية والكود الميت ويصدر حكم نهائي.
الأداة حصلت على المركز الثالث عالمياً في هاكاثون https://t.co/oztljs4BcU 🏆

#برمجة #ريادة_أعمال #ذكاء_اصطناعي

[Z.ai @Zai_org]

@AmineYagoube created CodeTribunal to help teams audit freelance code more effectively.

It sets up an "AI Courtroom" where GLM-5.1 agents debate as prosecutor and defense to uncover hidden logical risks that standard linters might miss.
https://t.co/Bo17XGYYhD

[Amine Yagoub @AmineYagoube]

@FayezShamm18239 حين يتوحد أشقاؤنا في فلسطين لا يضرهم من مارس سرا أو جهرا

[Amine Yagoub @AmineYagoube]

@HamaidiZizo هاذ الشي كامل باش يخلصو المتقاعدين؟ لا منتجات بنكية لا خدمات

[Z.ai @Zai_org]

GLM-5.2 supports two thinking-effort levels: High and Max.

For coding tasks, we recommend using Max effort to enable deeper reasoning and more reliable performance.

[Amine Yagoub @AmineYagoube]

@Zai_org Congratulations 🎉, it's Multimodal ?

[Amine Yagoub @AmineYagoube]

@Brahimteacher موسم الانتخابات

[Amine Yagoub @AmineYagoube]

@daweifs https://t.co/XOmiGeEKKx

Can you please try this one

[Amine Yagoub @AmineYagoube]

@cara_catowner @watcha_cn @Zai_org Wow 👏

[Felipe Demartini @namcios]

Dois engenheiros da Anthropic acabaram de mudar a forma como devs pensam sobre IA.

Barry Zhang e Mahesh Murag subiram no palco do AI Engineer Code Summit e disseram uma frase que incomodou muita gente:

"Parem de construir agentes. Construam Skills."

Em 16 minutos eles provam que a indústria inteira está resolvendo o problema errado.

Aqui está o que a maioria não entendeu:

→ Skills são pastas. Literalmente pastas com arquivos markdown.
→ Elas ensinam ao Claude o SEU fluxo de trabalho, a SUA expertise, o SEU domínio.
→ Um único agente genérico + biblioteca de Skills específicas supera dezenas de agentes especializados.
→ Fortune 100s já estão deployando Skills em escala pra ensinar agentes sobre processos internos.
→ Times de produtividade com 10.000+ devs usam Skills pra padronizar como código é escrito.

A analogia que eles usaram é perfeita:

Quem você quer fazendo seu imposto de renda? O gênio com QI 300 que nunca viu legislação tributária, ou o contador experiente que faz isso há 20 anos?

Inteligência sem expertise é entretenimento.
Expertise empacotada é produtividade.

O que mudou: a Anthropic parou de tentar criar agentes diferentes pra cada domínio.

Perceberam que com Claude Code, o padrão é sempre o mesmo. Um modelo acoplado a um runtime com filesystem.

A diferença entre um agente medíocre e um extraordinário não é o modelo. É o conhecimento de domínio que você alimenta.

Skills resolvem isso com progressive disclosure. O agente só carrega o nome e descrição da skill. Quando relevante, puxa o SKILL.md. Quando precisa de mais, navega os arquivos de referência. Zero desperdício de contexto.

Isso não é uma feature. É uma mudança de paradigma.

Quem entender isso agora vai operar em outro nível daqui a 90 dias.

Quem ignorar vai continuar escrevendo prompts de mil palavras toda vez que abrir o chat. E ainda explicar de novo e de novo o que “realmente” quer.

[Amine Yagoub @AmineYagoube]

@GithubProjects https://t.co/7hGkASyr4K

We built CodeTribunal to stop AI from hallucinating code reviews. Huge thanks to @zai_org for the feature! If you outsource code, you need to see this 2-min demo

[Z.ai @Zai_org]

@AmineYagoube created CodeTribunal to help teams audit freelance code more effectively.

It sets up an "AI Courtroom" where GLM-5.1 agents debate as prosecutor and defense to uncover hidden logical risks that standard linters might miss.
https://t.co/Bo17XGYYhD

[Amine Yagoub @AmineYagoube]

We built CodeTribunal to stop AI from hallucinating code reviews. Huge thanks to @zai_org for the feature! If you outsource code, you need to see this 2-min demo

#AI #الذكاءالاصطناعي

[Z.ai @Zai_org]

@AmineYagoube created CodeTribunal to help teams audit freelance code more effectively.

It sets up an "AI Courtroom" where GLM-5.1 agents debate as prosecutor and defense to uncover hidden logical risks that standard linters might miss.
https://t.co/Bo17XGYYhD

[Z.ai @Zai_org]

@AmineYagoube created CodeTribunal to help teams audit freelance code more effectively.

It sets up an "AI Courtroom" where GLM-5.1 agents debate as prosecutor and defense to uncover hidden logical risks that standard linters might miss.
https://t.co/Bo17XGYYhD

[Amine Yagoub @AmineYagoube]

@Designarena @Zai_org @AnthropicAI For me other tools have been forgotten

[Design Arena @DesignArena]

BREAKING: GLM 5.1 by @Zai_org overwhelmingly dominates design-centric coding tasks amongst open-weight models

In the categories featured below, it is most comparable to Opus 4.6 by @AnthropicAI at ~1/8th the cost

Huge congrats to the @Zai_org team for this achievement!

[Z.ai @Zai_org]

Introducing GLM-5.1: The Next Level of Open Source

- Top-Tier Performance: #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo.
- Built for Long-Horizon Tasks: Runs autonomously for 8 hours, refining strategies through thousands of iterations.

Blog: https://t.co/hmyDe4Nel3
Weights: https://t.co/CuUjXcPKJD
API: https://t.co/fz6reja4fb
Coding Plan: https://t.co/Nk8Y98HNhU

Coming to https://t.co/WCqWT0qCQb in the next few days.

[Amine Yagoub @AmineYagoube]

Stop guessing if your contractor's code is safe. Put it on trial.

🚀 Live Demo: https://t.co/cjdDXFfKEv
💻 GitHub: https://t.co/vLL7XG7Fnm

Built with GLM 5.1 + GritQL + CrewAI

[Amine Yagoub @AmineYagoube]

Non-technical founders lose millions to bad freelance code every year.
They pay $5,000, and have zero idea if it's a well-built app or a security nightmare.
I built CodeTribunal to fix this using GLM 5.1. Here is how it works:

@cara_catowner #buildwithGLM

[Amine Yagoub @AmineYagoube]

I built the whole pipeline this week for the @Zai_org hackathon.

(The entire voiceover for this video was generated using https://t.co/nhETVulwLI Audio to perfectly match the GLM 5.1 backend. Fully AI-native ecosystem 🤝)

Watch the demo:
https://t.co/BdxFFTvUCD