Pinned Tweet
"An engineer needs to solve algorithmic problem as a sword needs a whetstone if it is to keep its edge" - Tyrion Linuxter
Risyandi retweeted
◆ Built for tasks that take more than one step
⚡ Max scores 50.2 on AutomationBench v1.0.6—just 0.1 points behind Claude Opus 5.
🖥️ Pro scores 56.4 on OSWorld-2, ahead of Qwen3.8-Max at 46.7.
From workflow automation to computer use.
🤖 Made with AI
Risyandi retweeted
Meet Nex-N2.5 family, our latest open source agentic models.
Mini (35B) and Pro (397B) bring multimodal understanding and computer use. Max (1.6T) is a text-only MoE model built for complex reasoning, coding, and agent workflows.
Strong benchmark results in workflow automation and computer use:
⚡ Max scores 50.2 on AutomationBench v1.0.6—just 0.1 points behind Claude Opus 5
⚡ Pro scores 56.4 on OSWorld-2, ahead of Qwen3.8-Max at 46.7
With continuous action, visual feedback, and self-correction, NEX-N2.5 can work across Blender and CAD tools, handle expense reimbursements, and even play PC games—turning visual understanding into sustained, real-world execution.
🔗@huggingface
huggingface.co/nex-agi/Nex-N… huggingface.co/nex-agi/Nex-N… huggingface.co/nex-agi/Nex-N…
🔗@modelscope
modelscope.cn/models/nex-agi… modelscope.cn/models/nex-agi… modelscope.cn/models/nex-agi…
🔗 Github github.com/nex-agi/Nex-N2.5
🔗Website nex-agi.com/
Something big is coming. I'm going to init (AUGUST 31 - SEPTEMBER 4).
Five days of Appwrite launches, live sessions, and surprises. One ticket holder wins exclusive swag on the last day.
Claim your pass: new.appwrite.io/init/6a8fef1…
10
Reuse AI Skills Across Multiple Coding Tools with One Shared Folder insights.risyandi.com/2026/0…
12
Risyandi retweeted
J'ai 12 workflows Claude qui font tourner mon SEO
Chacun remplace une tâche que je facturais 800€ en consulting :
Pas des prompts que tu dois relancer toutes les 5 minutes. Des workflows que tu lances une fois et qui font le travail
1/ Stratégie SEO
Il lit ton site, ton marché et tes concurrents, et sort la feuille de route : quoi viser, dans quel ordre, pourquoi
2/ Recherche de mots-clés
Volume × difficulté × potentiel business. Il te sort les requêtes qui rapportent des clients, pas du trafic vanité
3/ Analyse de performance
Il lit ta Search Console et te dit ce qui monte, ce qui chute, et où sont tes écarts de CTR
4/ Analyse concurrentielle
Trafic estimé, mots-clés, backlinks, stratégie de contenu de tes 5 concurrents. En un seul passage
5/ Rédaction IA
Il rédige la page complète à partir du brief SEO : intention de recherche, structure, EEAT, zéro tiret long d'IA
6/ Optimisation on-page
Titles, metas, Hn, densité, liens. Il repasse sur tes pages existantes et corrige ligne par ligne
7/ Maillage interne
Il trouve les pages qui devraient pointer vers ta page cible et te donne les ancres exactes
8/ Analyse de backlinks
Domaines référents, ancres, ratio nofollow, ce qui est risqué et ce sur quoi capitaliser
9/ Audit d'indexation
Noindex, canonicals, robots.txt, sitemap. Il trouve les pages qui devraient être indexées et ne le sont pas
10/ Données structurées
Il détecte le type de page et génère le schema JSON-LD prêt à coller. Sans plugin
11/ Analyse de marque
Où ta marque est citée, comment tu apparais dans les IA, et ce qu'il manque pour être la référence
12/ SEO local
Fiche Google Business, cohérence NAP, avis, SERP de marque. Tout ce qui te fait ranker dans ta ville
Le truc, c'est que rien de tout ça n'est compliqué. La plupart des SEO ne prennent juste jamais le temps de le scripter
Un system prompt par agent, une conversation par rôle, et ça tourne sans toi
-----
Tu veux les 12 workflows prêts à copier-coller ?
1. Follow
2. Like + signet
3. Commente "workflow"
Risyandi retweeted
Don't waste 2 years learning to build LLMs like Claude & ChatGPT.
Stanford just dropped a 2 hour course on how to build LLMs from scratch.
• 00:00 - LLM tokenization
• 25:44 - how LLMs decode user prompts
• 35:40 - training pipeline of LLMs
• 1:16:47 - LLM architecture from scratch
Anthropic pays $750,000/year to engineers who understand this exact knowledge of LLMs.
Bookmark this & give 2 hours today, no matter what. Then read the article below.
Risyandi retweeted
Gmail is FREE
TikTok is FREE
Google is FREE
Chrome is FREE
YouTube is FREE
ChatGPT is FREE
Facebook is FREE
Instagram is FREE
WhatsApp is FREE
You pay with your personal data.
Readers added context they thought people might want to know
Proton Mail also offers a free plan. It is funded by paid subscribers and does not sell user data or show ads, per the company.
proton.me/pricing
proton.me/mail
Risyandi retweeted
10 repositorios de GitHub para scrapear todo internet
Guárdalos todos. Cada uno extrae datos limpios de cualquier web. Ese nivel de acceso normalmente exige llamadas de ventas y contratos.
My entire AI stack is now Chinese 🇨🇳
87% cheaper. same revenue
swaps by task:
1. reasoning / backend brain
Opus 4.8 → Kimi K2.7
benchmark gap: ~8% · price: ~11x cheaper
2. code generation
GPT-5.5 → Qwen 3.7 Max
benchmark gap: ~18% · price: ~7x cheaper
3. agent loops + tool calling
Sonnet 4.7 → GLM 5.2
benchmark gap: ~3% · price: ~5x cheaper on input
4. cheap volume / bulk processing
GPT-5.5 mini → MiMo V2.5
benchmark gap: ~6% · price: ~12x cheaper
5. image generation
GPT-Image-2 → Wan 2.5
benchmark gap: ~5% · price: ~8x cheaper
6. video generation
Sora 2 → Kling 3.0
benchmark gap: roughly equal · price: ~6x cheaper
[ result after 30 days: ]
operating costs dropped 87%, output quality dropped 4% on average, revenue unchanged
the most important that these models will be not banned in a month and i can run them locally
nobody will steal my data and i can learn them as i need
full article drops tomorrow with:
> exact routing logic per task type
> the 2 cases where I still pay for American
> the migration playbook anyone can copy in a weekend
VERY IMPORTANT to get migrated now, while it's not too late
Ex-Google engineer explained AI agent loops, harness, evals in 20 minutes - better than 500$ courses.
trace every run → judge it with an LLM → diagnose → fix → ship.
That loop is how agents self-improve over time.
Agent loops + memory + harness + evals - thats the stack.
Watch it, then save the framework below.
1/5 Five researchers left the Ethereum Foundation last week to launch an independent R&D lab called Ethlabs.
The goal: shorten the path from user needs to protocol upgrades with clearer accountability.
Here's why this structural shift matters for founders 👇
Risyandi retweeted
All Paid Courses (Free for First 4500 People)
𝗣𝗮𝗶𝗱 𝗖𝗼𝘂𝗿𝘀𝗲 𝗙𝗥𝗘𝗘 (PART - 1)
1. Artificial Intelligence
2. Machine Learning
3. Prompt Engineering
4. Claude,Chatgpt,Grok
5. Data Analytics
6. AWS Certified
7. Data Science
8. BIG DATA
9. Python
10. Ethical Hacking
(72 Hours only )
Like + RT + comment ' Drive '
Must Follow me so I can DM you.
Risyandi retweeted
Can AI improve a perfect song lyric? I’ve made a little game as part of #musicathon to find out. tinker-bot.replit.app
Risyandi retweeted
SYSTEM DESIGN — MASTER TREE 🌲
System Design
│
├── 01. Core Foundations
│ ├── Client-Server Architecture
│ ├── Monolith vs Microservices
│ ├── Stateless vs Stateful
│ ├── Horizontal vs Vertical Scaling
│ └── CAP Theorem
│
├── 02. Networking Layer
│ ├── DNS
│ ├── HTTP / HTTPS
│ ├── TCP vs UDP
│ ├── WebSockets
│ ├── Load Balancers
│ └── Reverse Proxies
│
├── 03. API Layer
│ ├── REST APIs
│ ├── GraphQL
│ ├── gRPC
│ ├── API Gateway
│ ├── Rate Limiting
│ └── Authentication
│
├── 04. Database Layer
│ ├── SQL
│ ├── NoSQL
│ ├── Indexing
│ ├── Replication
│ ├── Sharding
│ └── ACID Transactions
│
├── 05. Caching Layer
│ ├── Redis
│ ├── Memcached
│ ├── CDN
│ ├── Cache Invalidation
│ ├── Write-through Cache
│ └── Cache Eviction Policies
│
├── 06. Messaging Systems
│ ├── Kafka
│ ├── RabbitMQ
│ ├── Pub/Sub
│ ├── Event Streaming
│ ├── Async Processing
│ └── Queue Workers
│
├── 07. Reliability Layer
│ ├── High Availability
│ ├── Fault Tolerance
│ ├── Circuit Breakers
│ ├── Retries
│ ├── Disaster Recovery
│ └── Backpressure Handling
│
├── 08. Observability
│ ├── Logs
│ ├── Metrics
│ ├── Tracing
│ ├── Monitoring
│ ├── Alerting
│ └── SLA / SLO / SLI
│
├── 09. DevOps & Deployment
│ ├── Docker
│ ├── Kubernetes
│ ├── CI/CD
│ ├── Infrastructure as Code
│ ├── Blue-Green Deployment
│ └── Canary Releases
│
└── 10. Future Architectures
├── Serverless
├── Edge Computing
├── AI-Native Systems
├── Autonomous Infrastructure
└── Self-Healing Systems
Most developers learn frameworks.
The top 1% learn systems.
Risyandi retweeted
I loved this spec, so re-designed aiengineeringfromscratch.com - very beautiful indeed.
if software is spec, what if we got AI to make specs that weren't slop?
working on this
(very inspired by the beauty of makingsoftware.com by @danhollick)
Risyandi retweeted
10 Best open source repos for Harness engineering to try this weekend:
1. Harness: github.com/harness/harness
2. PostHog: github.com/PostHog/posthog
3. Chaos Mesh: github.com/chaos-mesh/chaos-…
4. GrowthBook: github.com/growthbook/growth…
5. Kubescape: github.com/kubescape/kubesca…
6. Flagsmith: github.com/Flagsmith/flagsmi…
7. ChaosBlade: github.com/chaosblade-io/cha…
8. Litmus: github.com/litmuschaos/litmu…
9. Kusion: github.com/KusionStack/kusio…
10. Rig: github.com/rigdev/rig
Risyandi retweeted
📚 Design tool library
Find the right tool for your role, ranked by what actually matters 👇
designtools.fyi
This is cool
“I don’t think I’ve typed a line of code since December.”
When Andrej Karpathy said that, most people treated it like a crazy AI quote.
@garrytan treated it like a question:
“What happens when one person operates like an entire software team?”
Then he built gstack.
And honestly… this repo feels less like a dev tool and more like a preview of where software is going.
Not AI as autocomplete.
AI as:
- CEO
- Staff engineer
- QA lead
- Security reviewer
- Designer
- Release manager
- Browser operator
- Parallel execution layer
All coordinated through structured workflows.
The craziest part is the numbers.
Garry says his current pace is ~810× higher than his 2013 output — normalized for logical code changes, not inflated AI LOC.
Same person.
Same brain.
Different tooling.
That’s the shift everyone is underestimating right now.
The winners in the next era probably won’t be the people who code the fastest.
They’ll be the people who can direct, review, and orchestrate AI systems the best.
A few things in gstack that genuinely stood out to me:
→ /office-hours challenges your product assumptions before you build
→ /autoplan runs CEO + design + eng reviews automatically
→ /qa opens a real browser, tests flows, finds bugs, and fixes them
→ /review catches production-level issues before shipping
→ /pair-agent lets multiple AI agents collaborate together
→ parallel AI sprints running at the same time across projects
This is the first open-source repo in a while that actually made me stop and rethink how software teams will work 2–3 years from now.
We’re moving from:
“AI helps developers code”
to
“developers operate systems of AI workers.”
That’s a very different future.
100% Open-source
Link in comments 👇
Risyandi retweeted
20 must follow accounts if you build software:
- @levelsio
- @marclou
- @theo
- @jackfriks
- @ChShersh
- @robj3d3
- @icanvardar
- @bruvimtired
- @yacineMTB
- @Ahmekal
- @forgebitz
- @JanuBuilds
- @dhh
- @FrancescoCiull4
- @enjojoyy
- @SoraiaDev
- @maks6361
- @eliana_jordan
- @razvanmuntian
- @itsolelehmann








































