Davlatjon Sh

@adocomplete github.com/dalisoft founder/maintainer of - nanoexpress - es6-tween - few awesome hosting - linting suite: airlight

@adocomplete I still didn't get. Applied two times. Seems i am not worth

If you received a Claude for OSS email giving you 6 months of Max but had trouble redeeming, please try again. Make sure to go through the entire flow to make sure usage is adjusted. Applying for the program? Please complete your GitHub profile before applying.

@sebastienlorber npmjs.com/package/tss-env

@sebastienlorber My npm packages solves exactly your problem

Git blame on me 😅 Dunno what I was smoking that day

Help us measure the progress towards AGI (specifically cognitive capabilities) by building benchmarks on @kaggle, with $ 200K in prizes available! Details in 🧵

@venom1s Marry to a girl which you love. Always. If you don't love: you either leave your family and your kids will be without dad OR your kids will be broken and unhappy when their parents unhappy

> Men ejaculate in a woman's body > DNA stays inside her body > Brain, blood, and reproductive organs for years This is why you should never marry a girl with a high body count. Imagine how many men's DNA is inside. It'll pollute your bloodline. Always marry a virgin girl.

@DrizzleORM Best meme. As always

DLSS5 off DLSS5 on

@OpenRouter I think Hunter Alpha is @MiniMax_AI M2.7

The Hunter Alpha stealth model is now in the top 10 weekly:

@FighterTrade @kilocode If you find my awesome list useful, please give a star

@FighterTrade @kilocode Yes, @kilocode has a subscription plan. See more #subscriptions" target="_blank" rel="nofollow noopener">github.com/dalisoft/aweso…

Last week, our Code Review bot reviewed 525 PRs across 5+ repos in Kilo’s production codebase. Most reviews used Opus 4.6. With Opus 4.6, the average cost per PR was $3.68 with an average of 3.2 reviews per PR. That's 10-100x cheaper compared to other tools on the market.

We get GPT-5.4-Codex soon?

Link proof: labs.scale.com/leaderboard/sw…

Note: Claude Code invalidates the KV cache for local models by prepending some IDs, making inference 90% slower. See how to fix it here: #fixing-90-slower-inference-in-claude-code" target="_blank" rel="nofollow noopener">unsloth.ai/docs/basics/cl…

@matteocollina Thank you. You skills are gem

🎯 After years of building with Node.js, I've organized my hard-won knowledge into skills: a collection of best practices, workflows, and deep expertise my AI assistant uses to write code to my standard. No more repeating myself on every code review. 👇

@fahdmirza @grok Summarize and also include TLDR

💥 Qwen3.5 0.8B vs 2B vs 4B vs 9B — Which One Should You Use and When? 🌀 ♠ Four models, one family — and one of them beats GPT-4o overall 🚀 🔹 Complete benchmark breakdown across 15 categories 🔹 Head to head matchups — where the gaps are real and where they are not 🔹 4B beats GPT-4o in 5 out of 6 categories — judged by Claude Opus 4.6 🔹 Thinking mode ON vs OFF — why it matters more than parameter count 🔹 Exact VRAM requirements for every model 🔹 Clear decision guide — which model for which hardware and task 🔹 All four are Apache 2.0, fully local, multimodal, 201 languages 🔥 Watch the full breakdown below 👇

@OpenAI @claudeai I applied to both @OpenAI’s Codex for Open Source program and @claudeai’s Claude for Open Source sponsorship, but no response yet

Thank you @OpenAI and @claudeai for not giving me FOSS free Pro/Max subscriptions, so I’ll improve my skills without relying on AI

Is there any task which only Claude Opus 4.6 can solve? If you have, please drop a comment with - Input problem - Your solution - Any tests for problem & solution

@romesh_at_X @MyCreativeOwls @Lovable @AnthropicAI @Lovable

@MyCreativeOwls @Lovable @AnthropicAI