Firebug24k @firebug24k

ran it. took 3 minutes and now my Claude workflow is 10x cleaner. what it built: > rewrote my claude. md with my preferences > flagged 6 places where I waste time and wrote fixes for each > rebuilt my research scraper based on my usage patterns > auto-generated 3 agents: UI review, creator analytics, deployment fastest setup optimization I've ever done.

Shann³ @shannholmberg

5 months ago

find every inefficiency in your Claude workflow with one prompt it finds where you're wasting time, where your prompts could be sharper, what patterns are slowing you down. copy the prompt below (bookmark to save it for later): ----- Scrape all of my Claude session on this

37 46 918 292K 3K

spent the entire day testing Qwopus (Claude 4.6 Opus distilled into Qwen 3.5 27B) on a single RTX 3090 through Claude Code. this is my new favourite to host locally. no jinja crashes. thinking mode works natively. 29-35 tok/s. 16.5 GB. the harness matches the distillation source and you can feel it. the model doesn't fight the agent. my flags: llama-server -m Qwopus-27B-Q4_K_M.gguf -ngl 99 -c 262144 -np 1 -fa on --cache-type-k q4_0 --cache-type-v q4_0 if you want raw speed, base Qwen 3.5 MoE still wins at 112 tok/s. but for autonomous coding where the model needs to think, wait for tool outputs, and selfcorrect without stalling, Qwopus on Claude Code is the cleanest setup i've found on this card. i want to see what everyone else is running. drop your GPU, model, harness, flags, and tok/s below. doesn't matter if it's a 3060 or a 4090, nvidia or amd. configs help everyone. let's push these cards to their ceilings. let's make this thread the reference.

Sudo su @sudoingX

5 months ago

Qwopus on a single RTX 3090. Claude Opus 4.6 reasoning distilled into Qwen 3.5 27B dense, running through Claude's own coding agent (claude code). 29-35 tok/s with thinking mode on. the jinja bug that kills thinking on base Qwen doesn't carry over. harness and model matched.

keyboard_arrow_left Previous keyboard_arrow_right Next

45 47 657 296K 615

🚨BREAKING: GOODBYE POWERPOINT forever. Claude just collapsed 10 hours of presentation building into 100 seconds completely free. Here are 12 prompts to go from completely unprepared to completely untouchable in every meeting: (Save this):

OpenAI and Anthropic engineers don't prompt like everyone else. I reverse-engineered 7 techniques from talking to 8 insiders directly. The difference is insane. Here are the edge-case prompts they don't want you to know:

Someone just coughed on you. You were on a crowded flight. Now your coworker is sick. The window to prevent infection is narrow. Here’s exactly what to do in the critical hours after a high-risk exposure 🧵1/13

I spent all of Christmas reverse engineering Claude Chrome so it would work with remote browsers. Here's how Anthropic taught Claude how to browse the web (1/7)

Hands down, this is the clearest and most effective explanation of Transformers on YouTube. The lecture was delivered by Professor Bryce as part of Davidson’s CSC 381: Deep Learning (Fall 2022). If your goal is to truly understand Transformers and self-attention, this is the only video you need and there’s no reason to watch anything else.

It's insane how good this Claude-in-Chrome tool is. I use the tool by default to fix all design issues with Claude Code. Fixes 100% of design issues. I don't even bother fixing design issues myself. I now just queue them for Claude Code to fix them automatically in one go.

These are insanely good prompts

Claude Code status line formatter to show model info, git branch, tokens in and out, context window status, session timer, and more. I built my own but this is very easy to use and set up! Link below

Five neural nets, achieving completely local voice AI, no internet, on an M1 with only 16GB ram. Neural-based voice activity detection and turn detection means it's interruptible, but never interrupts me, and is able to sit idle and waiting. It's been flawless so far. 12B parameters is definitely smart enough for some very cool use-cases (will share more later). Computers that can "think" feel strangely alive compared to dumb or networked hardware. Fast? No. But crazy that it works at all on such a modest machine. The stack: - Silero VAD voice activity detection - Whisper Large v3 turbo - Smart Turn v2 by @trydaily - Kokoro_tts - Gemma_3_12B_it_QAT_Q4 rock-solid on @lmstudio - vision easily removed thx to gguf @ggerganov - @pipecat_ai integration by @kwindla

Tech giants use Multimodal RAG every day in production! - Spotify uses it to answer music queries - YouTube uses it to turn prompts into tracks - Amazon Music uses it to create playlist from prompt Let's learn how to build a Multimodal Agentic RAG (with code):

Claude Code with the prompt: "You are my personal assistant and chief of staff. Self organize using markdown files" Has replaced the entire bucket of what you would label productivity software. 95% of my input is talking to it via @superwhisper

sunil pai @threepointone

12 months ago

last week I learnt how @southpolesteve uses claude code _ itself as a personal assistant_ for stuff, instead of building a custom personal assistant, which got my gears turning maybe the app builder can be the app itself

7 1 139 328K 123

my friend JUST used claude code to rank #2 on google for "mobile diesel repair" within 24h. phones WON'T stop ringing and he made THOUSANDS of revenue. he shows EVERYTHING, the prompts, the whole claude code process, ranking locally hacks in this 32 min saucy tutorial

Open-source voice cloning at 16x real-time? Chatterbox TTS (0.5B Llama) now runs on vLLM, 5–10x faster than the original implementation. On a 3090: - 40 min speech in ~2.5 min - Same quality, way faster github.com/randombk/chatt…

Cool: Hugging Face is now supported in opencode, select your favorite model from the Hub and it will consume your inference quota directly. I recommend starting with GLM-4.5 (great at coding + awesome at agentic tasks)

Victor M @victormustar

a year ago

Hugging Face PRO is the wildest $9/month deal in AI right now🤯 🔹 25 min/day of H200 compute on Spaces ZeroGPU 🔹 ~1M free inference tokens from 15+ providers (Groq, Cerebras, etc.) 🔹 1TB private storage and more 🔹 More cool things...

25 158 1K 794K 1K

😭😭

good list of claude code tips. it's surprising how often i hear about compacting being the weak point of CC - has anyone written a hook/hotfix or explored different methods of compaction here?

LLM framework for easy structured data extraction from documents

A GitHub repo with list of 1000s of free APIs.