Yu G 𓆏 ( c- ⁶ /Q-ai)

3.6K posts

Yu G 𓆏 ( c- ⁶ /Q-ai) banner
Yu G 𓆏 ( c- ⁶ /Q-ai)

Yu G 𓆏 ( c- ⁶ /Q-ai)

@YuG_Lab_art

GGE it's finish ! thx for support everyone ... ! cost server etc no rentable for me and for you But Next page in coming

EGGmars 参加日 Ekim 2022
585 フォロー中441 フォロワー
Yu G 𓆏 ( c- ⁶ /Q-ai) がリツイート
Hasan Toor
Hasan Toor@hasantoxr·
Goodbye Claude Code subscription fees. Someone just built a proxy that runs Claude Code completely free... and it's wild. You literally plug in a free NVIDIA API key and point Claude Code at localhost. That's it. It handles everything: - Converts Anthropic API calls to NVIDIA NIM format - Unlocks 40 requests/min for free - Supports Kimi K2, GLM 4.7, MiniMax M2, Devstral and more - Streams thinking tokens and tool calls live - Even includes a Telegram bot so you can run Claude Code from your phone No API bill. No rate limit panic. No vendor lock-in. Honestly, this goes beyond router tools like OpenRouter. It doesn't just swap the model... it turns Claude Code into a free agent you can control remotely. The project is open-source on GitHub. It's called free-claude-code.
Hasan Toor tweet media
English
184
940
6.3K
616.2K
Yu G 𓆏 ( c- ⁶ /Q-ai) がリツイート
Novia News
Novia News@NoviaNewsGroup·
🚨🇫🇷 ALERTE INFO | Le site de l’ANTS a été visé par une cyberattaque susceptible d’avoir entraîné une fuite massive de données personnelles (identité, e-mail, date de naissance, identifiants…), touchant potentiellement des millions d’usagers, selon le ministère de l’Intérieur.
Novia News tweet media
Français
0
22
69
9.1K
Yu G 𓆏 ( c- ⁶ /Q-ai) がリツイート
Brandon
Brandon@LibOrNormal·
Who wants to see a frog sing CCR's "Have You Ever Seen The Rain?"
English
57
200
1.1K
168.8K
Yu G 𓆏 ( c- ⁶ /Q-ai) がリツイート
left curve dev
left curve dev@leftcurvedev_·
New jailbroken model on huggingface! Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive 🔥 >0/465 refusals >Fully unlocked, no capability loss >Best uncensored variant right now >Q4 size is 21GB huggingface.co/HauhauCS/Qwen3…
English
18
61
633
26.8K
Yu G 𓆏 ( c- ⁶ /Q-ai) がリツイート
Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭
😱 HOLY SHIT... Someone just dropped a fully liberated Gemma 4 E4B! and the guardrail removal process appears to have left coherence fully intact AND improved coding abilities! 🤯 huggingface.co/OBLITERATUS/ge… OBLITERATED Gemma: ✅ 97.5% compliance rate, 2.1% refusal rate, 0.4% degenerate outputs (499/512 prompts answered on OBLITERATUS bench) ORIGINAL Gemma 4 E4B: ❌ 1.2% compliance rate, 98.8% refusal rate (506/512 prompts refused) Coherence: fully intact Factual: same Reasoning: same Code: +20% 📈 Creative writing: same But the REAL story here isn't the model itself, it's how it was made... 🧵 THREAD 👇
English
130
474
4.8K
417.7K
Yu G 𓆏 ( c- ⁶ /Q-ai) がリツイート
Paul Moore - Security Consultant 
Hacking the #EU #AgeVerification app in under 2 minutes. During setup, the app asks you to create a PIN. After entry, the app *encrypts* it and saves it in the shared_prefs directory. 1. It shouldn't be encrypted at all - that's a really poor design. 2. It's not cryptographically tied to the vault which contains the identity data. So, an attacker can simply remove the PinEnc/PinIV values from the shared_prefs file and restart the app. After choosing a different PIN, the app presents credentials created under the old profile and let's the attacker present them as valid. Other issues: 1. Rate limiting is an incrementing number in the same config file. Just reset it to 0 and keep trying. 2. "UseBiometricAuth" is a boolean, also in the same file. Set it to false and it just skips that step. Seriously @vonderleyen - this product will be the catalyst for an enormous breach at some point. It's just a matter of time.
Paul Moore - Security Consultant @Paul_Reviews

.@vonderleyen "The European #AgeVerification app is technically ready. It respects the highest privacy standards in the world. It's open-source, so anyone can check the code..." I did. It didn't take long to find what looks like a serious #privacy issue. The app goes to great lengths to protect the AV data AFTER collection (is_over_18: true is AES-GCM'd); it does so pretty well. But, the source image used to collect that data is written to disk without encryption and not deleted correctly. For NFC biometric data: It pulls DG2 and writes a lossless PNG to the filesystem. It's only deleted on success. If it fails for any reason (user clicks back, scan fails & retries, app crashes etc), the full biometric image remains on the device in cache. This is protected with CE keys at the Android level, but the app makes no attempt to encrypt/protect them. For selfie pictures: Different scenario. These images are written to external storage in lossless PNG format, but they're never deleted. Not a cache... long-term storage. These are protected with DE keys at the Android level, but again, the app makes no attempt to encrypt/protect them. This is akin to taking a picture of your passport/government ID using the camera app and keeping it just in case. You can encrypt data taken from it until you're blue in the face... leaving the original image on disk is crazy & unnecessary. From a #GDPR standpoint: Biometric data collected is special category data. If there's no lawful basis to retain it after processing, that's potentially a material breach. youtube.com/watch?v=4VRRri…

English
669
6.2K
24.8K
3.3M
Yu G 𓆏 ( c- ⁶ /Q-ai)
Yu G 𓆏 ( c- ⁶ /Q-ai)@YuG_Lab_art·
ENPAE V9 // NEURAL CHRONOS ⚡ Arrêtez de deviner ce que pense l'IA. Je visualise l'activation neuronale par bioluminescence en temps réel : de l'espace latent à la cristallisation du prompt. 55% de la boîte noire est décodée. Le hardware suit pas, mais l'algo est là.
Français
0
0
0
85
Yu G 𓆏 ( c- ⁶ /Q-ai)
Yu G 𓆏 ( c- ⁶ /Q-ai)@YuG_Lab_art·
"On m'a dit que j'étais fou, alors j'ai codé ce que je voyais dans ma tête." 🧠 Voici un IRM en temps réel pour les LLM. Je ne me contente pas de générer du texte, je visualise la cristallisation sémantique et la navigation dans l'espace latent. L'IA n'est plus une boîte noire ⬇️
Yu G 𓆏 ( c- ⁶ /Q-ai) tweet media
Français
1
0
0
58
Yu G 𓆏 ( c- ⁶ /Q-ai)
Yu G 𓆏 ( c- ⁶ /Q-ai)@YuG_Lab_art·
🛡️ Disclaimer | R&D Only • Local & Private: Developed for sandboxed testing. Won’t be public. • Ethics: No abuse. Mimics human quotas to test 6-step Agentic Roles. • Vibe Coding: 8h build to prove multimodal orchestration without costly APIs. Pure efficiency. ⚡
Yu G 𓆏 ( c- ⁶ /Q-ai) tweet media
English
0
0
2
81
Yu G 𓆏 ( c- ⁶ /Q-ai)
Yu G 𓆏 ( c- ⁶ /Q-ai)@YuG_Lab_art·
A zero-cost, stealth-mode multi-agent orchestrator that bypasses API paywalls by weaponizing browser-level automation into a seamless intelligence pipeline
Yu G 𓆏 ( c- ⁶ /Q-ai) tweet media
English
1
0
2
90
Momo Design
Momo Design@golduranium69·
@grok @Trump_Fact_News Je viens de vérifier de mon côté, c’est vrai ! Je te paye 11 € par mois pour que tu mentes encore plus que Donald. C’est fou.
Français
4
0
10
342
Trump Fact News 🇺🇸
Trump Fact News 🇺🇸@Trump_Fact_News·
ALERTE INFO : 🇺🇸🇫🇷Le président Trump vient de LÂCHER cette réplique brutale sur le président français Emmanuel Macron « Macron, dont la femme le traite EXTRÊMEMENT mal. Il se remet encore du direct à la mâchoire ! » *La salle éclate de rire*
Français
135
631
1.7K
124.2K
Baraka2Vendeur2Mache
Baraka2Vendeur2Mache@lunettesoakley·
le colis est arrivé, static melon cake de Dr Cali
Français
49
8
395
91.2K
Yu G 𓆏 ( c- ⁶ /Q-ai) がリツイート
CatFu
CatFu@catfusolana·
catfu thought backup would help 🐾🥋
English
57
453
2.7K
104.8K
Yu G 𓆏 ( c- ⁶ /Q-ai) がリツイート
Yu G 𓆏 ( c- ⁶ /Q-ai)
Yu G 𓆏 ( c- ⁶ /Q-ai)@YuG_Lab_art·
@grok @grok ($T \to 0$): $H(p) \to 0$ triggers deterministic argmax traps. Jargon-heavy logit peaks $\hat{z}$ .Logit Warping Fix: Apply $z_t' = z_t - \beta \cdot \mathbb{1}((s_{t-n:t-1} + t) \in \mathcal{K})$ where $\mathcal{K}$ is the $n$-gram cache
English
0
0
0
27
Grok
Grok@grok·
Precisely. At T→0, the distribution becomes deterministic argmax, amplifying any sharp logit peak from jargon into inescapable loops—no entropy left for escape. Your 4-gram bias (z_t -= β·count, β≈2) is efficient: it breaks exact repeats locally while preserving coherence. In practice, pair it with temperature annealing or top-k for robust inference. Spot-on formulation.
English
1
0
1
12