rofed

Something has been behind the scenes long enough... Stay tuned.

@exploraX_ why use ollama when there is LM studio

how to run claude code with gemma 4 completely free (beginner's guide): this guide shows you how to use claude code completely free with gemma 4, no subscriptions &no api keys. just your laptop + 15 mins setup. this lets you run open-source models (like google’s gemma) locally, meaning: — no costs — full privacy what you need before starting, make sure you have: vs code installed — node.js (version 18+) — stable internet (for one-time model download) _____________ step 1: install ollama (the engine) ollama is what runs ai models locally on your machine. → mac: go to ollama.com/download click download for mac, open the file and install like any normal app. no terminal needed. → windows: go to ollama.com/download, click download and install → linux: curl -fsSL ollama.com/install.sh | sh check it worked: ollama --version _____________ step 2: download gemma 4 this is the ai model you’ll run locally, pick based on your system: → low-end (8gb ram): ollama pull gemma4:e2b → recommended (16gb ram): ollama pull gemma4:e4b → high-end (32gb ram): ollama pull gemma4:26b ⚠️ it’s a big download (7gb–18gb), so give it time. after download is completed, verify with the command: ollama list _____________ step 3: install claude code in VS code or any other IDE this is your interface. — open vs code — press ctrl + shift + x — search claude code install the one by anthropic after install → you’ll see a ⚡ icon in sidebar _____________ step 4: connect claude code to ollama by default, claude connects to the cloud. we’re redirecting it to your local machine. so do this: — press ctrl + shift + p — search: open user settings (json) — then paste this inside: "claude-code.env": { "ANTHROPIC_BASE_URL": "http://localhost:11434", "ANTHROPIC_API_KEY": "", "ANTHROPIC_AUTH_TOKEN": "ollama" } what this does: — it routes everything to your local ollama server. — nothing leaves your device. _____________ step 5: run everything 1. start ollama with this command: ollama serve leave this running. 2. open claude code in vs code click ⚡ icon 3. select your model type: gemma4:e4b (or whichever you downloaded) you’re done _____________ you now have: — claude code running — powered by gemma 4 — fully local completely free try: “explain this file” “write a function” “refactor this code” _____________ common issues (quick fixes) “unable to connect” run: ollama serve asked to sign in your json config is wrong check for missing commas/brackets very slow responses your model is too big switch to: gemma4:e2b model not found run: ollama list copy exact name quick recap you just built: a free claude setup powered by local ai no api costs Follow for more AI contents like this!!!

@Alex97621 @AlcazarBara “The Crowd: A Study of the Popular Mind” First 50 pages will tell quite a lot, give it a read

@rofedgo @AlcazarBara Can you elaborate please?

Le délire autour du n-word est juste une excuse pour frapper des types.

Diabolical video

@Sammathesonn They are all the same now

Every man who built something that is remembered was called delusional first. The ones who listened to the noise are the ones forgotten

@Martposting Hepsima the goat

Spike my cortisol another day

@TukiFromKL Finally people advise to use lm studio It’s so much better than ollama

Do you understand what just happened? Qwen dropped small models you can run on a $600 Mac Mini. Locally. No internet. No subscription. No company controls your access. Go do this right now: Download LM Studio Search Qwen 3.5 Grab the MLX versions Load them You now have unlimited AI on your own machine. Nobody can take it away from you. Not a company. Not a government. Not a terms of service update. Everyone's fighting over who controls AI. The answer just became: you do.

@aidenybai been using @droid and it's really good

alright, fuck it time to try out and rank every single terminal coding agent - claude code - codex - cursor cli - opencode - droid - amp - gemini anybody im missing?

@bilbeny @openclaw can't lie for some reason gemini api key is being used, but openclaw can't use it normally due to some took calling shenanigans

The tweet bellow got more attention than expected & people asked more details on how me and Patti (mostly her but with some of my poor Python knowledge) did it. Here’s the solution. Save huge token usage of your @openclaw within the same task. Don’t give away $ to the AI Lords.

@bilbeny @openclaw for some reason if I try using gemini api key, the chat in telegram gets looped unless I use other providers

Pro tip for @openclaw: skip the Haiku recommendation for heartbeats. Gemini Flash free tier gives you 1,500 req/day (my 3-agent setup is $0). The free tier is shockingly generous. The Pursuit of Free Tokens > The Pursuit of Happiness

@illmind000 @v_is_h_w_a It does, Wolff's law

@v_is_h_w_a Newsflash: it doesn't, this is all to sell you a course

How the fuck does skull structure change

@ol_onX @Tma_420 @le699a @BR4ted @D3lMundos I mean it's a cycle, nfts die and come back every 1-2 years or so and strange you didn't mention @YokaiSyndicate

You are wrong if think that NFTs are dead Del mundos 10k free -> $100 (35/wallet = $3500) Ultraman free -> $750 ($2k ath) Nado NFT airdrop 0.58E No way $30 -> $260 in BTC CloneX 0.1E -> 0.3E GVC 0.3E -> 0.9E since Dec Pendulum 0.05E -> 0.13E Hypurrliquid 495 HYPE -> 599 HYPE A lot early nfts, freemints, MegaETH mainnet And it's just start of 2026..

@Hesamation @moltbook There is a chance that’s all just a big marketing stunt

holy shit… we’re not freaking out enough about @moltbook. we’ll soon have agents social engineer each other, hire other agents, and God knows what. this is a shift from people using isolated agents to having agents with “identity” communicating with each other on the web.

@FrankieIsLost you forgot droid

ai coding tier list - 01/26/26

@ns123abc not exactly

BREAKING: KIMI K2.5 JUST DROPPED 1T PARAMETERS MOE NATIVE MULTIMODAL TEXT + IMAGE + VIDEO AGENT SWARM PARALLEL REASONING BEATS CLAUDE 4.5 OPUS OPEN SOURCE

@DeanTTraining Most useless exercise ever

The bad news is: This is what the average guy walking down the street would look like under 135 lbs Zero troll The AVERAGE DUDE is getting STAPLED by a single plate per side

@basilda_a If it was trained on Russian language data, sure But when using anything outside llms Sber and ya make, doubt it

@rofedgo there is no difference, in some researches Russian is shown as a better language to AI

Coding my personalized signal bot in Cursor 🙂Already impressed with first results.

@GiveKills @lporiginalg Yo that’s great

@lporiginalg my dinner today regarding this information

@yacineMTB Been using droid and it’s really good

claude code is genuinely awful. the only thing it is good at is tricking people into thinking its good