pek-er-nus89 (@PNus89) profile picture
Joined March 2021
Photo by pek-er-nus89 (@PNus89)Photo by pek-er-nus89 (@PNus89)Photo by pek-er-nus89 (@PNus89)Photo by pek-er-nus89 (@PNus89)Photo by pek-er-nus89 (@PNus89)Photo by pek-er-nus89 (@PNus89)Photo by pek-er-nus89 (@PNus89)Photo by pek-er-nus89 (@PNus89)Photo by pek-er-nus89 (@PNus89)Photo by pek-er-nus89 (@PNus89)
Evlilikler, erkeklerin kadınlara KATLANACAK yüreğe sahip olması sayesinde ayakta kaldı. Nesiller boyu sürmesinin sebebi ERKEKLER. Duygusal zekamız ve eşlerimize duyduğumuz şefkat yüzünden. Kadınların iyi partner olmasından değil. Erkeklerin, sırf evde huzur hakim olsun diye kadınların yaptığı tonlarca saçma boku görmezden gelmeyi öğrenmesinden. Gerçekçi olalım, kadınlarla yaşamak hiç de KOLAY değil. Romantik değiller. Bütün romantizm anlayışları ALMAK üzerine. Bana ne aldı, beni nereye götürdü, benim için ne yaptı. Ne verdikleri hiç yok. Komik değiller. Aşırı hassaslar, sorumluluk almaktan nefret ediyorlar, özür dilemekten nefret ediyorlar, kendi kocalarıyla sekste ilk adımı atmaktan nefret ediyorlar ve cehennem gibi kontrolcüler. İnatçı ve asi. Evliliklerde duyduğunuz o aile içi şiddet var ya? Çoğunu karısı BAŞLATIYOR. İtmek, tokat atmak, bir şeyler fırlatmak, ağzına geleni saymak, adam tepki verene kadar kışkırtmak. Sonra da mağdura yatmak istiyor. İçinde erkek olmayan herhangi bir ilişkiye bakın, yürümüyor. Lezbiyenler? En yüksek istismar oranı. Çünkü şiddetlerini ve duygularını tolere edecek bir erkek yok ortada. İki kadın bir arada birbirini kaldıramıyor. Kadın arkadaşlıkları? Daha da beter. Tamamen dedikodu, arkadan iş çevirme, kıskançlık, en çocukça şeyler yüzünden birbirini silme. 2022'de 10 kadın arkadaşı olur. 2026'ya gelindiğinde sadece 2 tanesi kalır. HEPSİYLE kavga etmiştir. Her biri artık düşmandır. Ama suçlu erkekler.
Evlilik hakkında linç edileceğin bir fikrini söyle
484
1,876
115
16,870
644,610
pek-er-nus89 retweeted
SON DAKİKA: Claude, 1 milyon izlenmeye ulaşabilecek YouTube Shorts videolarını ücretsiz olarak nasıl hazırlayabileceğinizi artık adım adım gösteriyor. YouTube Shorts’ta öne çıkmanıza yardımcı olup para basacağınız 8 etkili prompt: Kaydet lazım olur!
8
210
4
2,137
373,145
Some of you thought that Inkling 2 Small was too big at 594B parameters. We heard you: Inkling 2 Mini is a looped transformer with just 26B parameters, small enough to run on your laptop, powerful enough for agentic work with a score of 20.1 on AA Index. thinkingmachines.ai/news/ink…
534
1,471
890
15,502
2,514,544
pek-er-nus89 retweeted
The biggest opportunities right now: 1. build for solving loneliness (the more AI floods everything, the more people crave real human connection, IRL and small social) 2. build for places with no cameras and no recording (being offline and unseen is turning into the new status symbol) 3. build for the crisis of young men. Millions of guys in their 20s feel completely lost with work, dating, and purpose. Whoever builds real brotherhood, mentorship, and an actual path forward wins a massive market (and helps a ton of people). 4. build for protecting people's brains (feeds are turning everyone's attention to mush, tools that protect your focus and mood are an easy sell) 5. build for the death of "everyone agrees" (you can find a chart or a podcast clip to prove any point now, people are starving for one source they actually trust) 6. build for day 2, not day 0. Anyone can launch an app in a weekend now. But how can you keep it running, fix the mess, and grow it for 3 years. 7. build for throwaway software (not everything needs to be a $20 a month subscription, tiny apps made for one trip, one wedding, or one group chat are coming) 8. build for people whose ego just got bruised by AI. Millions of smart people are realizing their job was mostly pattern matching. Help them figure out what they're good for next. 9. build for things that take effort on purpose (when everything is instant and free, nothing feels earned, people will pay for slowness and craft) 10. build for people who miss being told they're wrong. AI agrees with everything you say now. Real rooms where smart people actually push back on your ideas are becoming a luxury. 11. build for skin in the game. The internet is full of free takes and bots. Any platform where people have to put real money, real names, or real work behind what they say wins. 12. build for agents that need to spend money (they're getting virtual cards and budgets, someone builds the spend controls, fraud protection, receipts) 13. build for the end of fake email jobs (half of corporate America knows their job is theater, build the exit ramp for people who want to do real work) 14. build for the friend with great recommendations (nobody trusts Yelp reviews etc anymore because it's all bots and SEO, people will pay one obsessive person to just tell them where to eat and what to buy) 15. build for life after the chat box. Typing prompts already feels old. The best AI products won't look like chatbots at all, they'll just sit in the background and proactively handle things. 16. build for markets too small to matter before (500 lobster fishermen was never worth a team, now it's a real business if you can figure out what to build value to add to these fishermen lives!) 17. build for helpful without being creepy. AI is getting very personal very fast. Whoever figures out how to make it feel warm instead of weird owns consumer tech. 18. build for small private rooms (the public internet feels like an ad and a bot farm, all the good conversations and deals are moving into small invite-only groups) 19. build for someone taking the blame. AI can write the contract or read the scan, but a machine can't look you in the eye when it goes wrong. People still pay for a human on the hook. 20. build for learning that actually keeps up (a four year degree is way too slow for how fast things move now) 21. build for the anti-AI premium (as everything gets generated, human-made and unpolished become status symbols people pay up for) note: more trends/ideas ideabrowser.com (free to sign up) 22. build for the return to the physical (screens fill with slop, people crave the real world, the hands on, the local, the analog) 23. build for the caregiving wave. The population is aging fast, tens of millions are caring for parents, and the whole burden is landing on families with no support. 24. build for finding things you didn't know to search for (algorithms just feed you more of what you clicked yesterday, people miss stumbling onto something totally different) 25. build for the housing and rootlessness problem (people can't afford to settle down, and the whole idea of a stable home base is up for grabs) 26. build for anti marketing (the slickest, most polished websites now look like AI slop or a scam, sometimes a plain text page from 1998 converts better because it feels like a real person built it) 27. build for agents that sit on hold for you (canceling a gym membership, fighting a medical bill, haggling with your internet provider, aint nobody got time for that) 28. build for software you actually own (people are exhausted from renting 30 different subscriptions every month, pay once and run it on your own machine is a massive wedge) 29. build for stuff that only works locally. The internet feels like one giant mall where every city has the exact same coffee shops and trends. Things that refuse to scale are suddenly cool again. 30. build for the 90% automated, 10% human sign-off model (clients don't actually care if AI did the heavy lifting, they just want one real expert to check the work and put their name on it) 31. build for infinite creative testing. Some brands are lighting money on fire on Meta because their ads die in 10 days. Build an automated pipeline that pumps out 100 fresh UGC and static ad variations a week based on what's actually converting in their ad account. 32. build for cold outreach that doesn't look like cold outreach. Mass blasting 50,000 people with "Hope this finds you well" is dead lol. Build an agent that watches for one specific trigger like a new VP hire or a broken checkout page, builds a custom teardown on the fly, and sends it before a human SDR even wakes up. 33. build for programmatic free tools instead of blog posts. Spin up 200 tiny, hyper-specific calculators, little apps and templates for one niche, rank them, and turn the traffic straight into conversions. 34. build for the food and toxin awakening (people are finally waking up to ultra processed food, microplastics, and why everyone feels sick and tired all the time) 35. build for the death of third places (there is almost nowhere left to just hang out without spending $50, which is why run clubs, saunas, and neighborhood clubs are blowing up) 36. build for people who can't retire at 65. Either they can't afford it or they're going to live to 95 and don't want to spend 30 years watching TV. The second act"market is huge. 37. build for the "undo" button for agents. Giving an AI access to your inbox, calendar, or bank account is still terrifying. Whoever makes it safe to let go of the wheel wins. 38. build for the sports betting and day trading hangover (a whole generation of young people are addicted to gambling on their phones and blowing up their bank accounts) 39. build for the death of the attention span. Smart adults can't even sit through a movie without checking their phone or finish a book anymore, and they're starting to hate themselves for it. 40. build for keeping marriages alive. Couples are stretched thin with work, kids, and money, and traditional therapy is $250 an hour with a waitlist. Anything that actually saves relationships is priceless. 41. build for people who don't own anything anymore. You rent your apartment, lease your car, stream your music, and subscribe to your software. Anything that helps regular people actually own an asset again wins. KEEP BUILDING
435
1,369
137
11,810
838,417
pek-er-nus89 retweeted
The math on the $100 Google AI Ultra plan is honestly not mathing 🤯 For $100/mo, you get: ✨ Gemini Carbon access for Antigravity & the Gemini app ☁️ $40/mo in Google Cloud credits 📺 YouTube Premium Family plan ($27 value) 🏠 Google Home Premium Advanced ($20 value) ❤️ Family Health Premium ($10+ value) 💾 20TB cloud storage for the entire family (up to 6) The perks alone cover nearly the entire subscription.
311
101
78
3,164
650,764
pek-er-nus89 retweeted
🚨 BREAKING: Claude has a hidden ADHD Executive Function Mode. You can use it to hack your brain’s dopamine and finish a week’s worth of work in 4 hours. Here are 7 prompts to access it:↓
55
594
41
7,183
1,174,478
pek-er-nus89 retweeted
We shrank 1 GB of Wikipedia to 105.39 MB, losslessly. Introducing tufazip: the best entry on the Large Text Compression Benchmark using a neural network as its sole predictor. Everything above it mixes a transformer with hand-built models. Full post 👇 tufalabs.ai/research/tufazip
495
1,033
545
14,273
3,004,980
pek-er-nus89 retweeted
如果你想赚钱,你就去盯 HuggingFace 和 Civitai 的每周热榜,专找刚火起来、但装环境能把人逼疯的开源视觉模型,比如最新的换装、老照片修复或者声音克隆。自己把复杂的 Python 依赖和显卡报错全踩一遍,打包成解压就能双击运行的「免安装绿色整合包」,挂闲鱼、小红书和面包多,定价 29–69,包远程帮装一次收 199。一个模型热度能吃小一个月,冷了就封下一个,等于拿全球开源社区给你免费打工。有人就靠这一招,三个月干了二十多万。
20
47
541
35,230
pek-er-nus89 retweeted
I still don’t understand why everyone is not doing this yet. Elon Musk reposted my GrokBot guide, with which I earned $6,230 just last week Eight Grok agents on the desk, $200 a month, running a floor that usually costs a crypto fund $620K a year in analyst salaries The morning call is at 5:30. I am not in it  1. SEARCH uncovers hidden Telegram calls, dev GitHubs, and early alpha ahead of CT 2. RUG monitors developer wallets around the clock and dumps everything the moment LP is touched 3. SNIPER fires fast on-chain buys the exact millisecond safety checks clear 4. RISK audits mint permissions, contract code, and LP locks to block honeypots before entry 5. WHALE tracks smart money wallets and flags heavy accumulation in real time 6. EXIT shifts stops dynamically, locking in profits as liquidity expands 7. SHILL monitors hype velocity, social buzz, and big influencer mentions 8. HEAD OF DESK routes data, never places trades, verifies handoffs, and surfaces only the single call needing a human 422 tokens scanned, 37 qualified setups, 16 executed trades while I was asleep. Net result: +$6,230 after fees and zero bad fills Every agent operates with its own cloud browser, terminal, and memory, keeping the entire desk running even when my laptop is shut Getting this running takes way less effort than you think: Set up Grok Bot and create your Head of Desk Assign the remaining 7 agents clear roles like onboarding a new team Walk through the workflow once on screen so they can observe Connect your wallet and Telegram webhooks Zero coding, zero VPS, zero waiting around for developers Crypto trading used to cost 16 hours a day at the screen, expensive alpha groups, and constant exhaustion. I put mine together in a single night Save this before placing your next trade
168
198
10
1,722
281,754
"If your wages only allow you to eat and sleep, it's not a job; in the past, that was called slavery." - George Orwell
193
9,453
195
45,636
426,136
pek-er-nus89 retweeted
UNCENSORED GEMMA 4 NOW RUNS ON A 6-YEAR-OLD LAPTOP. NO GPU NEEDED 😳 Someone just released a less-restricted build of Google's Gemma 4 E4B. And the model is only 4.8GB. - Runs with 8GB RAM - Supports older GTX 1060 / 1650 GPUs - Fewer refusals than the standard version - Works completely offline - Apache 2.0 license Setup takes just a couple of minutes: 1. Install Ollama 2. Open your terminal 3. Run: ollama run huggingface.co/igorls/gemma-… That's it. Start chatting locally. No cloud. No subscription. No data leaving your machine. Try it 👇 huggingface.co/igorls
free ai video generation on your own pc, no subscription, no credits 😳 This open-source project lets you generate AI videos locally, even with just 8GB VRAM. - Text, image, video & audio inputs - Generate videos up to 1 minute - Built-in timeline editor - New H3 Image support up to 16MP - Works on Windows, Mac & Linux» How to get started: 1. Download from GitHub 2. Click Install & Launch 3. Enter your prompt 4. Generate your video No cloud credits. No monthly subscription. Runs locally. Try it 👇 github.com/FlashML-org/FreeV…
2
39
3
345
27,770
pek-er-nus89 retweeted
Just fed Claude my salary and resume. Dude, that thing showed me income sources I never would've come up with in a million years. The 7 prompts I used for it:
84
310
9
5,452
1,120,591
pek-er-nus89 retweeted
Launching uncensored models on AxiomAI Ask and create anything, all in perfect privacy Imagination is your only limit now
22
70
20
1,054
187,963
pek-er-nus89 retweeted
f**king goldmine of WiFi hacking tools hackwifi.surge.sh/wifi/ 21 tools. real commands. BOOKMARK rn
29
218
2
2,298
176,610
pek-er-nus89 retweeted
holy f*ck... high-end 3D modeling just got stupidly accessible a game studio would charge $5k–$12k for a creature like this. 3D artists who don’t learn these tools by 2027 are cooked: → Blender MCP (34k stars) Grok Bot drives Blender for you — models, materials, entire scenes from a prompt github.com/ahujasid/mcp-for-… → Hunyuan3D 2 (15k stars) one image or text prompt in → high-res textured 3D model out github.com/Tencent-Hunyuan/H… → TRELLIS by Microsoft (14k stars) text or image to production-ready 3D assets you can drop straight into a scene github.com/microsoft/TRELLIS → InstantMesh (4.6k stars) single image → clean 3D mesh in seconds github.com/TencentARC/Instan… → MeshAnything (2.3k stars) turns messy AI geometry into clean, artist-style meshes github.com/buaacyw/MeshAnyth… → SuperSplat (10k stars) edit 3D Gaussian splats right in your browser github.com/playcanvas/supers… → three.js (118k stars) put your monster on a website, live, in 3D github.com/mrdoob/three.js credits to @MetaDumplings for this insane 3D artwork want the exact workflow to connect Grok Bot to Jev and create models like this? check out the full guide below:
11
43
3
441
25,723
pek-er-nus89 retweeted
Introducing Firecrawl Local. We rebuilt the Firecrawl repo so agents can scrape locally. - 37x faster rust based scrape primitive (vs self-hosted) - 230x less memory (11 MB idle) - 100% open source Compatible out of the box with all of our MCP & SDKs. github.com/firecrawl/firecra…
239
380
127
5,548
845,255
pek-er-nus89 retweeted
there are literally hundreds AI training jobs out there that you could qualify for completly remote, legit and that pays very well for your expertise you just have to do your research, create your profile on different platforms and apply the work main platforms I’m using: - @mercor - @micro1_ai - @alignerrAI - @outlier_ai_
Opportunity: Another remote job you can apply to right now Micro1 pays people up to $120/h to train AI The median rate on the platform is around $70/h, and 2 out of 3 roles accept applicants from any country How to join: - Sign up: refer.micro1.ai/referral/job… - Create your profile - Head to opportunities There are all sorts of jobs you can apply for remotely, it will all depend on your degrees and skills
17
16
1
558
30,991
pek-er-nus89 retweeted
DeepSeek reasoning + 9B Qwen + fully uncensored 😳 result is actually wild - only 5.7GB - refuses almost nothing - strong reasoning free & no gate
this 9B qwen is fully uncensored + high iq thinking 😳 - heretic abliterated - almost zero refusals - runs on normal pc its free, no gate
13
50
2
606
27,847
pek-er-nus89 retweeted
Best Uncensored AI models you can run with no GPU : Overall : Qwen3.5-4B Uncensored (HauhauCS) Smallest : Qwen3.5-2B Uncensored Multimodal : Gemma 4 E4B Heretic Best quality : Qwen3.5-9B Heretic Writing : Qwen3-4B Heretic 16GB+ RAM : Qwen3.6-35B-A3B Uncensored (MoE, 3B active) Avoid : Huihui Qwen3.5-4B (KL 3.65, lobotomized) What they need : 2B → 2GB RAM, ~15 tok/s 4B → 4GB RAM, ~8-12 tok/s 9B → 7GB RAM, ~6 tok/s 35B-A3B → 20GB RAM, feels like a 4B Where to get them : Qwen → huggingface.co/HauhauCS or search "heretic GGUF" Gemma → huggingface.co/igorls Setup : ollama pull hf.co/<repo>:Q4_K_M ollama run <model> /set nothink /set parameter num_ctx 8192 that's it. no API key, no account, no card, no GPU the 7 steps on how to make it fast on CPU below:
Here's 7 steps to run an uncensored AI with no GPU (or a 6-year-old one): every local AI post I make gets the same reply: "cool, I don't have a Mac Studio or a 5090" FAIR, this one is for you... I tested it on a 2019 laptop with no dedicated GPU By the end, you'll know how to: - run an abliterated model on CPU and 8GB of RAM - make it usable on a GTX 1060 / 1650 / any old card - do it for $0, no API key, no account So, let's go step by step: 1. Install Ollama curl -fsSL ollama.com/install.sh | sh Windows: download the installer from ollama.com, no WSL needed. Ollama runs on CPU automatically if there's no usable GPU. if you have an old Nvidia card it puts what fits in VRAM and the rest on CPU, no config 2. Pick the right size for your box (this is where people fail) - 4GB RAM or 4GB VRAM: Gemma 4 E2B. ~3GB. dumb but runs anywhere - 8GB RAM, or 6GB VRAM (GTX 1060 / 1660 / RTX 2060): Gemma 4 E4B. ~5GB. the sweet spot - 12GB+ VRAM: skip this post, run the 12B from my earlier one guide the mistake is pulling the 12B on 8GB and concluding "local AI is unusable". it was never going to fit (I see in comments how people arguing for it lol) 3. Pull the model ollama pull hf.co/igorls/gemma-4-E4B-it-… same author and method as the 12B heretic. ~5GB, runs in 5GB RAM. KL 0.055 from the original, refusals ~98% → ~21% on the hardest adversarial set with thinking on, near zero with thinking off Gemma 4 is Apache 2.0, so no license homework on this one 4. Turn off thinking ollama run hf.co/igorls/gemma-4-E4B-it-… /set nothink on a GPU thinking costs tokens. on CPU it costs minutes. and the abliteration targets non-thinking mode anyway 5. Keep context small /set parameter num_ctx 8192 CPU speed is memory bandwidth, nothing else. every token re-reads the whole model from RAM. the KV cache grows with context and competes for the same RAM. 8k is plenty for chat, drafts, critique. 32k on CPU is self-harm 6. Three settings that make the difference (optional, worth it) restart Ollama with: OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=q8_0 ollama serve flash attention + q8 KV cache halves what the context costs in memory, with no real quality loss. on a 6GB card this is often the difference between "whole model on GPU" and "half of it spilled to CPU" if Ollama runs as a service, setting this in your shell does nothing. on Linux: sudo systemctl edit ollama, add Environment="OLLAMA_FLASH_ATTENTION=1" and the KV line, restart old card note: flash attention wants RTX 2000 or newer. on a GTX 1060 it may not engage. skip this step, it still runs 7. Check it's actually using what you have /set verbose ← prints tokens/sec after every answer ollama ps ← in a second terminal ollama ps shows "100% GPU", "100% CPU", or a split like "60%/40%". if you have a card and it says 100% CPU, your driver isn't loaded. nvidia-smi should list the card. fix that before touching anything else What to expect: - CPU only, modern laptop: ~8-15 tok/s. reading speed, not typing speed - GTX 1060 6GB / 1660: whole model on GPU, ~25-40 tok/s - GTX 1050 4GB: split. faster than CPU, slower than you'd like - a 2020+ Mac with 16GB: just works, ~20 tok/s honest take: - E4B is a 4B-class model. good for writing, chat, drafts, roasts, critique. bad for hard reasoning and agentic coding. don't plug it into Claude Code, you'll hate it - 10 tok/s feels slow for 2 minutes and then it doesn't. you're not paying anyone - if you can get 12GB VRAM used for $150, do it. the 12B is a different league - there's no secret trick after this. the rest is buying RAM *IMPORTANT: don't use it for anything illegal or harmful. that's on you, not the model next: how I run the 12B on an 8GB card without it spilling to CPU save it so you don't lose it
33
119
2
1,006
39,870
pek-er-nus89 retweeted
If you’re using Claude Code to build do the following and I promise the experience gets 10x better: /model = Opus 5.5 /advisor = Fable 5.2 Then copy and paste the following into your session - - Opus 5.5 runs the main session and edits the code - search maps the repo on Haiku 5.5, read-only - grep finds every call site on Haiku 5.5 - test-runner runs the suite on Haiku 5.5 and reports only failures - Fable 5.2 on call as advisor, reads the full transcript when consulted - JEV routes micro-forks in milliseconds Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with Fable 5.2 as advisor. 2. Create three read-only Haiku 5.5 subagents: search (maps the repo), grep (finds call sites), test-runner (runs the suite, reports only failures). 3. Add one rule to CLAUDE.md: consult the advisor before a plan locks, after the same error twice, and before a task is marked done. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. Nothing gets edited until I say go. Credit goes to @skunzu for creating the original write up on this! I just made it much shorter. Appreciate the setup Skunzu, my sessions are 10x better now!
25
25
1
824
91,471