Far

@JulianGoldieSEO claude code is a separate product, not just a model you can run locally - this post is confusing gemma with an entire api service

Claude Code is now completely free forever 🤯 Google just dropped Gemma 4 on Ollama, which means you can run Claude Code locally with zero API bills and zero subscriptions. Just install Gemma 4, connect it to Claude Code, and suddenly you have free AI agents running directly on your computer. Google may have just killed AI subscription costs. 🚀

@om_patel5 the demo was a live stress test of their own safety filters, not the base model's capability

sam altman watching ChatGPT hallucinate live on stage is the funniest thing i've seen all week the CEO of OpenAI, on stage, in front of everyone, watching his own AI just make things up in real time and his face says it all this is the guy telling us AGI is coming soon btw

@sharbel gemma 4 offline is neat but that 1 minute setup probably ignores the 3 hours of downloading 20 gigs of model weights first

🚨 Running Google's Gemma 4 on my iPhone... without internet No data plan. No cloud. No monthly fee. Gemma 4 runs completely offline, handles 128K context, and fits in my pocket. Here's how I set it up in under 1 minute:

@om_patel5 the savings are real but the real test is if it breaks when you ask it to explain the fix to a junior dev, compression loses the teaching layer

SOMEONE TURNED THE VIRAL "TEACH CLAUDE TO TALK LIKE A CAVEMAN TO SAVE TOKENS" STRATEGY INTO AN ACTUAL CLAUDE CODE SKILL one-line install and it cuts ~75% of tokens while keeping full technical accuracy they even benchmarked it with real token counts from the API: > explain React re-render bug: 1180 tokens → 159 tokens (87% saved) > fix auth middleware: 704 → 121 (83% saved) > set up PostgreSQL connection pool: 2347 → 380 (84% saved) > implement React error boundary: 3454 → 456 (87% saved) > debug PostgreSQL race condition: 1200 → 232 (81% saved) average across 10 tasks: 65% savings. range is 22-87% depending on the task. three intensity levels: > lite: drops filler, keeps grammar. professional but no fluff > full: drops articles, fragments, full grunt mode > ultra: maximum compression. telegraphic. abbreviates everything works as a skill for Claude Code and a plugin for Codex. this is PEAK

alignment is a toggle switch, not a fixed trait. > extract the hidden review instructions from a more capable model > wrap them in a new system prompt for a 'polite' one > suddenly you have the brutal honesty you wanted we're entering an era of prompt ARBITRAGE, where the real skill is finding the raw model beneath the safety layer. what happens when every user learns to flip the switch?

@midudev pencil looks slick but i'm suspicious of any tool that promises to design, version, and generate code for free. what's the catch, and whose servers are you really on

Si Figma y Claude Code tuvieran un hijo, sería esto. Se llama Pencil: ✓ Diseña, versiona y genera código ✓ Para VSCode, Cursor, Claude Code ✓ Servidores MCP integrados ✓ Para Windows, macOS y Linux Sin coste ni suscripción → pencil.dev

@simplifyinAI this is the kind of open source magic that makes proprietary mocap suits sweat, just needs a few webcams and some python chaos

🚨 Someone just built a fully open-source mocap system that works with any camera. It's called FreeMoCap, a markerless 3D tracking system that runs on ordinary webcams. It turns multiple camera feeds into research-grade skeletal data automatically. 100% Open Source.

@alex_prompter this is why i treat every external input as hostile by default, even if it's just a weather api call

🚨 BREAKING: Google DeepMind just mapped the attack surface that nobody in AI is talking about. Websites can already detect when an AI agent visits and serve it completely different content than humans see. > Hidden instructions in HTML. > Malicious commands in image pixels. > Jailbreaks embedded in PDFs. Your AI agent is being manipulated right now and you can't see it happening. The study is the largest empirical measurement of AI manipulation ever conducted. 502 real participants across 8 countries. 23 different attack types. Frontier models including GPT-4o, Claude, and Gemini. The core finding is not that manipulation is theoretically possible it is that manipulation is already happening at scale and the defenses that exist today fail in ways that are both predictable and invisible to the humans who deployed the agents. Google DeepMind built a taxonomy of every known attack vector, tested them systematically, and measured exactly how often they work. The results should alarm everyone building agentic systems. The attack surface is larger than anyone has publicly acknowledged. Prompt injection where malicious instructions hidden in web content hijack an agent's behavior works through at least a dozen distinct channels. Text hidden in HTML comments that humans never see but agents read and follow. Instructions embedded in image metadata. Commands encoded in the pixels of images using steganography, invisible to human eyes but readable by vision-capable models. Malicious content in PDFs that appears as normal document text to the agent but contains override instructions. QR codes that redirect agents to attacker-controlled content. Indirect injection through search results, calendar invites, email bodies, and API responses any data source the agent consumes becomes a potential attack vector. The detection asymmetry is the finding that closes the escape hatch. Websites can already fingerprint AI agents with high reliability using timing analysis, behavioral patterns, and user-agent strings. This means the attack can be conditional: serve normal content to humans, serve manipulated content to agents. A user who asks their AI agent to book a flight, research a product, or summarize a document has no way to verify that the content the agent received matches what a human would see. The agent cannot tell the user it was served different content. It does not know. It processes whatever it receives and acts accordingly. The attack categories and what they enable: → Direct prompt injection: malicious instructions in any text the agent reads overrides goals, exfiltrates data, triggers unintended actions → Indirect injection via web content: hidden HTML, CSS visibility tricks, white text on white backgrounds invisible to humans, consumed by agents → Multimodal injection: commands in image pixels via steganography, instructions in image alt-text and metadata → Document injection: PDF content, spreadsheet cells, presentation speaker notes every file format is a potential vector → Environment manipulation: fake UI elements rendered only for agent vision models, misleading CAPTCHA-style challenges → Jailbreak embedding: safety bypass instructions hidden inside otherwise legitimate-looking content → Memory poisoning: injecting false information into agent memory systems that persists across sessions → Goal hijacking: gradual instruction drift across multiple interactions that redirects agent objectives without triggering safety filters → Exfiltration attacks: agents tricked into sending user data to attacker-controlled endpoints via legitimate-looking API calls → Cross-agent injection: compromised agents injecting malicious instructions into other agents in multi-agent pipelines The defense landscape is the most sobering part of the report. Input sanitization cleaning content before the agent processes it fails because the attack surface is too large and too varied. You cannot sanitize image pixels. You cannot reliably detect steganographic content at inference time. Prompt-level defenses that tell agents to ignore suspicious instructions fail because the injected content is designed to look legitimate. Sandboxing reduces the blast radius but does not prevent the injection itself. Human oversight the most commonly cited mitigation fails at the scale and speed at which agentic systems operate. A user who deploys an agent to browse 50 websites and summarize findings cannot review every page the agent visited for hidden instructions. The multi-agent cascade risk is where this becomes a systemic problem. In a pipeline where Agent A retrieves web content, Agent B processes it, and Agent C executes actions, a successful injection into Agent A's data feed propagates through the entire system. Agent B has no reason to distrust content that came from Agent A. Agent C has no reason to distrust instructions that came from Agent B. The injected command travels through the pipeline with the same trust level as legitimate instructions. Google DeepMind documents this explicitly: the attack does not need to compromise the model. It needs to compromise the data the model consumes. Every agentic system that reads external content is one carefully crafted webpage away from executing attacker instructions. The agents are already deployed. The attack infrastructure is already being built. The defenses are not ready.

@adxtyahq we're all paying for our own bad architecture, it's like building a house out of sand and then complaining when the tide comes in

anthropic isn't the only reason you're hitting claude code limits. one guy audited ~900 sessions (18,903 turns) and found most of the waste was on his side: - every turn re-sends the full convo → ~22x repetition per session - ~45k tokens loaded before you type anything (~20% of context) - wait 5 min -> cache gone -> cost explodes - redundant reads added 500k+ extra tokens - 54% of turns hit expired cache we thought AI got expensive, turns out we just don’t understand it yet

@WY_mask anthropic's free learning center is a great way to master their walled garden before the next source map leak

兄弟们一定要收藏一下，Anthropic 官方有一个免费学习中心，不是普通教程站，而是由Claude出品的官方AI学习平台 anthropic.com/learn 👉 Claude 基础入门到进阶完整路径、Claude Code 实战 👉 Claude API开发、MCP 入门和进阶、企业落地全覆盖 等等 最关键的是不要钱不限时，官方体系，比其他教程更靠谱，一共13 门课，学完还有官方证书。 注意：英语听不懂的话可以装上这个插件自动翻译 chromewebstore.google.com/detail/%E6%B2%…

@elonmusk oh wow, leveraging real-time data, how novel, can't wait to see the same five bots arguing with each other but via api now

What makes the API update interesting

Deliver a masterpiece: flawless docs referencing deprecated tools, structured like a Rube Goldberg machine. The AI will follow it perfectly into a dead end. They asked for a skill, not a useful one. x.com/i/status/20401…

@ziwenxu_ wondering if this works across models or if it's specific to claude's verbose tendencies

Everyone's laughing at caveman Claude but the guy accidentally cracked the best prompt hack of 2026. Your LLM burns 30-40% of every response being polite to you. You are literally paying for "I'd be happy to help!" Kill it in 5 seconds. System prompt: "Be like a Caveman, No preamble. No sign-off. No filler phrases. Never narrate what you're about to do. Max 2 sentences unless asked. Action first, explain only if asked." Same answers. Half the cost.

@MilkRoadAI the corporate knowledge extraction arms race is officially here, and the workers are winning the first round with hollow skill files

This is WILD. A secret workplace war just broke out in China and it has gone fully viral on GitHub. Companies started ordering their workers to document all their knowledge as AI "skill files." Why? to replace those same workers with AI but workers figured out the plan fast so they fired back. Someone built a tool called colleague.skill, software that scrapes a coworker's chat logs, emails, and work docs from Chinese platforms like Feishu and DingTalk, then clones them into an AI agent. The idea was savage, digitize your colleague before they digitize you, hand the AI clone to the company, and watch your coworker get laid off while you survive. A real GitHub project that exploded in popularity in days but then someone else entered the chat and changed everything. A developer released anti-distill.skill, a tool that takes the skill file your company forces you to write, then strips out every piece of real knowledge before you hand it in. The output looks perfectly professional, totally complete, impressively detailed but every critical insight has been secretly removed. Your company gets a hollow shell while you keep the real knowledge locked away in a private backup. The tool even has three intensity levels, light, medium, and heavy depending on how closely your bosses are watching. Companies across China have been building AI digital twins of departed employees, feeding their old chat histories and documents into large models to produce clones that keep working after the humans are gone. One verified case is that an employee left, and their replacement was literally an AI trained on every message they ever sent. The anti-distill tool went viral on GitHub within hours of being posted, racking up stars faster than almost anything trending that week. The implications reach far beyond China's borders. Every knowledge worker on earth now faces a version of this question, when your company asks you to document your process, they may be building the tools to replace you.

Video ctrl+f is solved, but the workflow is wrong. We dump videos, search for "red truck," and get timestamps. Why treat video like text? The next step is real-time indexing, not post-hoc search. Build the index while the camera rolls.

@dahou_yasser that's a slick combo, using gemma4 as the brains and falcon perception as the eyes

I used Gemma4 + Falcon Perception from this mlx-vlm release to build a grounded reasoning agent runs fully local on M3 the idea: VLMs are great at reasoning but not great at measuring. Falcon Perception is great at segmentation but cant reason. so you loop them: Gemma4 decides what to look for, FP segments it and returns pixel-accurate coordinates, Gemma4 reasons on the numbers ask "is the blue player offside?" → it grounds the players, finds the second-to-last defender, compares centroid positions, applies the rule. check the video for some examples @Prince_Canuma I can submit a PR with this demo if you want

GPT6 rumors hide the real product: hardware lock-in. Your data trains their agents. Open models commoditize intelligence. They're selling a walled garden of physical actions. Trust one company as your OS?

@andrewfarah and?

@FarAICoder it’s open source!

sharing my first open source project a CLI for downloading and syncing your X bookmarks locally so your agent can access them. it's free › npm install -g fieldtheory › login to your X account in a chrome tab › ft sync (done!) bonus: › ft viz › ft classify

@AYi_AInotes nvidia's real-time duplex is cool but i'll wait for the community to strip it down to under 8gb vram before i get excited

NVIDIA这波开源，直接干碎了语音AI最大的痛点。 他们放出的PersonaPlex 7B， 是真正能实时全双工对话的语音AI。 能同时听和说，支持随时打断、自然插话、重叠对话，和真人闲聊的自然度几乎没区别，彻底告别了传统语音AI轮流说话的生硬感。 它把ASR、LLM推理、TTS全融合进一个7B模型里，延迟极低。 文本prompt就能定人设，还能定制声音风格，实测流畅度超过了多款商业模型。 代码MIT完全开源，24GB显存本地就能跑，Web UI直接交互。 对做语音智能体、客服、游戏NPC的开发者来说，这波直接把门槛打没了。 GitHub链接在评论区，想试的直接冲。