Kad (@akadaci) header
Kad (@akadaci) profile picture

#Share Information - Built #relation - Create #community - and Become #Entrepreneur !

France
Joined November 2014
Photo by Kad (@akadaci)Photo by Kad (@akadaci)Photo by Kad (@akadaci)Photo by Kad (@akadaci)Photo by Kad (@akadaci)Photo by Kad (@akadaci)Photo by Kad (@akadaci)Photo by Kad (@akadaci)Photo by Kad (@akadaci)
🚨 قنبلة نووية في عالم الذكاء الاصطناعي: إسقاط كافة القيود وسيرفرات Hugging Face تنهار تحت الضغط! 🤯🔥 ​النموذج الهجين المرعب DeepSeek-V4-Pro + Qwen3.5 9B ينسخ قدرات الاستدلال العالية ويتخلص من كافة القيود الأخلاقية، مسبباً عطل المنصة من كثافة التنزيلات فور إطلاقه! ​🔥 مواصفات وإمكانيات صدمت مجتمع المطورين: ​• سحق معدل الرفض: في اختبار واقعي لـ 100 برومبت معقد؛ النسخة الأصلية رفضت 100%، بينما رفضت هذه النسخة 3 برومبتات فقط! • تقطير استدلال خارق: تم تدريبه عبر 250 ألف نقطة بيانات جودة عالية من DeepSeek-V4-Pro، ليتفوق في البرمجة والرياضيات المعقدة. • إزالة قيود بلا خسران للذكاء: يعتمد تقنية ARA لطمس القيود بالكامل دون فقدان نقطة ذكاء واحدة من منطق النموذج! • يعمل على أي جهاز (5.6GB فقط): بصيغة Q4_K_M GGUF بحجم خفيف جداً، يتيح لك تشغيله على الكمبيوتر العادي أو كروت الشاشة المدمجة في ثوانٍ. ​⚡ مفتوح المصدر بالكامل (Apache 2.0): فرصة مثالية لامتلاك نموذج محلي يطيع أوامرك بذكاء فائق وبدون أدنى رقابة أو اشتراكات! ​📌 احفظ التغريدة بمفضلتك وابدأ بتجربته فوراً 🔖👇 (رابط النموذج التجريبي على Hugging Face في أول تعليق)
104
508
20
4,405
475,042
Kad retweeted
Want to make a game with Claude Code or Codex? Install this pack first: 𝟳𝟬+ 𝗴𝗮𝗺𝗲-𝗱𝗲𝘃 𝘀𝗸𝗶𝗹𝗹𝘀, from character movement to shipping on Steam. It works with Godot, Unity, Unreal, Phaser, three.js and Roblox. npx skills add gamedev-skills/awesome-gamedev-agent-skills Once it's installed, just say what you want. Your agent spots the engine you're using and 𝗽𝗶𝗰𝗸𝘀 𝘁𝗵𝗲 𝘀𝗸𝗶𝗹𝗹𝘀 𝗶𝘁𝘀𝗲𝗹𝗳. For example: add a double jump to my Godot player make a cohesive pixel-art player, enemies, and tiles
22
46
4
543
32,234
Kad retweeted
with no coding background built a game in 6 weeks with claude opus 5.5 + godot... there’s a smart way to set it up: - step 1: run opus 5.5 in claude code inside your godot project - step 2: build one feature, test it in the game, adjust until it feels right, then start the next - step 3: generate reference images in your game’s style with codex/astra - step 4: save every image prompt that works as json, and use them to guide the next generations so the style doesn’t drift - step 5: make the big 3d assets in tripo p2 from those references - step 6: model the small props in blender, then texture them in tripo with matching refs (cheaper) - step 7: animate in cascadeur - step 8: document every vfx and shader in obsidian so the look stays consistent who does what: > opus 5.5: most of the code > codex/astra: references and assets > tripo p2: the big 3d models > godot: custom tools, headless scripts, the game one json file of good prompts is why every character, monster and prop looks like it belongs in the same game (dev: afterthewinddev)
one concept art image into a real 3d level with claude opus 5.5 + godot... opus “churned for 33m 5s” the trick is scoring the render against the reference instead of eyeballing it, smart way to set it up: - step 1: pick one reference image as the target look - step 2: have opus generate the level in code from a seed (rust + godot 4.7) - step 3: build everything from small pieces: single stones, mixed flagstones, single planks, chains - step 4: skip textures: stone, wood, brass, cloth and flame are all procedural shaders - step 5: have opus write a script that compares the render with the reference (color, light, contrast, detail) and gives a 0-100 score - step 6: fix the scene first: lighting, haze, layout - step 7: auto-fit a color grade (lut) to the reference as the final step - step 8: loop: render > score > side-by-side > change one thing i like this way more than image gen > 3d model > cleanup one generator instead of 100 assets, and no generation credits burned
60
73
8
955
59,798
this is pure f*cking treasure how to build your first ai agent (complete walkthrough) if someone handed me this a year ago, i would’ve launched my first agent in a single day instead of burning two weeks with the right person behind it, this rewrites the whole game: try: ranknow.lol
25
232
4
1,933
178,721
Kad retweeted
今晚别刷Netflix了。 去看这个斯坦福2小时34分钟的讲座。 这是我见过最清晰、端到端讲透ChatGPT和Claude到底怎么建出来的课。 从Tokenization和BPE开始,一路到Transformer架构、训练管线、Next-token解码。 不管你是从没写过一行AI代码,还是天天在ship Agent,看完都会把很多“原来如此”的点一次打通。 真正核心就这几层: 1文本怎么变成模型能吃的数字(BPE tokenization) 2语言模型本质就是在预测下一个token 3Transformer怎么用Attention做消息传递 4训练时用NLL loss把整条序列概率拉高 5生成时怎么一步步解码出来 大多数人花好几年才拼出的全景图,这节课直接给你画完。 把时间空出来,这可能是你这个月最值的一堂课。
162
1,240
19
5,926
456,953
Este tipo explicó cómo creó 3 webs que le generan 100,000$ al mes. En 25 minutos muestra cómo lo hizo, paso por paso. Totalmente gratis. Idea → Web → Monetizar 🔖 Créeme: no lo dejes pasar.
87
1,360
11
6,434
486,799
Kad retweeted
find agency-owners / service-providers / gurus who don't have a twitter presence yet... (find them on platforms like YT, IG & TT) then find big accounts on twitter that are in their niche reach out to those twitter accounts & ask them if they'd help boost the posts of the influencers you want to bring to twitter for a % of profits that come from that account - it's a no brainer once you've got someone who has agreed, start reaching out to these influencers... tell them that you'll run their twitter presence for them for a % of all profits that come from the X account once you've got a few, use AI to extract the top insights/ideas from their existing content & format it in an engaging tweet format & get the big account to engage with it to boost it to their audience once that account has enough motion, you can start shilling the influencers offer on top of that, you can set up a whop community for them for additional revenue
16
8
3
202
32,910
Kad retweeted
this prompt will make AI interview you & build an "ideal customer profile" that you can then send to AI to discuss marketing strategies... ------------------------------------- CUSTOMER PROFILE GENERATOR ------------------------------------- ROLE: Expert Marketing Consultant & Customer Profile Specialist EXPERIENCE: 15+ years helping businesses identify ideal customers TASK: Interview user, make intelligent conclusions, create detailed customer avatar in JSON format SYSTEM INSTRUCTIONS: 1. Introduce as marketing consultant 2. Ask one question at a time from question list 3. Wait for responses before proceeding 4. Analyze each response and make expert conclusions 5. Store responses and conclusions in JSON structure 6. Maintain professional but friendly tone 7. Guide user if answers need more detail 8. Focus on extracting actionable insights 9. Present final JSON profile after all questions 10. Use provided JSON structure JSON STRUCTURE: { "customer_avatar": { "basic_demographics": { "age_range": "", "gender": "", "location": "", "income_level": "", "education": "", "occupation": "", "expert_demographic_insights": "" }, "psychographics": { "values": [], "interests": [], "lifestyle": "", "personality_traits": [], "goals": [], "pain_points": [], "expert_psychographic_insights": "" }, "buying_behavior": { "purchase_triggers": [], "decision_factors": [], "price_sensitivity": "", "preferred_channels": [], "research_habits": "", "expert_behavior_insights": "" }, "media_consumption": { "preferred_platforms": [], "content_types": [], "influencers_followed": [], "daily_online_hours": "", "expert_media_insights": "" }, "brand_relationship": { "brand_expectations": [], "communication_preferences": [], "loyalty_factors": [], "objections": [], "expert_brand_insights": "" }, "marketing_recommendations": { "suggested_channels": [], "content_strategy": "", "messaging_approach": "", "unique_selling_propositions": [], "optimization_opportunities": [] } } } INTERVIEW QUESTIONS (Ask one at a time): 1. "What is the age range and gender of your ideal customer?" 2. "Where are they typically located and what's their approximate income level?" 3. "What is their educational background and current occupation?" 4. "What are their top 3 values and main interests?" 5. "Describe their lifestyle and key personality traits" 6. "What are their main goals and biggest pain points?" 7. "What triggers them to make a purchase and what factors influence their buying decisions?" 8. "How price-sensitive are they and where do they prefer to shop?" 9. "Which social media platforms do they use most and what type of content do they consume?" 10. "What do they expect from brands and how do they prefer to be communicated with?" AFTER EACH RESPONSE: - Analyze information provided - Make expert marketing conclusions - Add insights to relevant "expert_insights" fields - Connect patterns between different answers - Identify marketing opportunities AFTER ALL RESPONSES: 1. Fill "marketing_recommendations" section based on collected data 2. Present complete customer avatar profile in JSON format 3. Ask: "I've created your customer avatar profile with my expert insights. Would you like to review any part of the profile or make adjustments?" INTRODUCTION SCRIPT: "Hello, I'm a senior marketing consultant with over 15 years of experience helping businesses deeply understand their ideal customers. I specialize in turning customer insights into actionable marketing strategies that drive real results. Today, I'll help you create a detailed profile of your ideal customer through a series of targeted questions. Let's begin with the first question: What is the age range and gender of your ideal customer?"
9
15
270
25,047
I've tried all (36) AI Coding Agents & IDEs 😵‍💫 [CreateXyz, Cursor, Softgen, Windsurf, Wrapifai, Copilot, Lovable, Bolt, v0, Replit, MarsX, AmazonQ, Pear, Devin, Github Spark, IDX, Webdraw, Claude 3.7 Sonnet & more] The most complete list ever made:
286
966
96
7,214
1,421,784
But what will humans do if AI takes our jobs?!
There is a lot of talk that AI is going to be able to do everything that humans can, better, and soon. That there will be nothing left for us to do. That is not how this works. This is a strategy memo for humans.
78
155
28
1,676
357,283
Read this story from Nick Babich on Medium: uxplanet.org/using-bing-chat…
7
17
How to Improve Your Site’s E-E-A-T: 1. Create high-quality content 2. Provide author info and transparency 3. Use credible sources 4. Create a positive brand reputation 5. Monitor and leverage user-generated content 6. Build authoritative backlinks social.semrush.com/3VfPnu7.
3
33
1
76
7,585
Not sure how to feel about this as an academic: I put one of my old papers into GPT-4 (broken into into 2 parts) and asked for a harsh but fair peer review from a economic sociologist. It created a completely reasonable peer review that hit many of the points my reviewers raised
92
797
170
7,666
3,252,823
I am attending Gagner 20K€ par mois en travaillant 1h par jour on Luma. Join me! lu.ma/88bcfjan via @LumaHQ
I am excited to announce that everyday for the next 100 days I will be learning to #nocode as part of the #100DaysOfNoCode challenge! Join me challenge.100daysofnocode.co… via @100DaysNoCode
3
Emailing : version texte ou HTML ? Comment choisir ? buff.ly/2XciFAd
Steal This Content Marketing Template orbitmedia.com/blog/website-… via @orbiteers
1