Petra

@ai_for_success It should be the third choice. OpenAI and Anthropic simply have better models and tools. Anti Gravity? Really ?

Name me a better subscription than Gemini for 20 dollars. Now 5TB Storage from 2TB. You get: 1. Gemini latest model access 2. NotebookLM 3. Antigravity 4. 5 TB cloud storage 5. Gemini CLI, Jules and Code Assist 6. Gemini in Gmail, Docs, Vids, and more 7. 1,000 monthly AI credits. I must have definitely missed few things here..

@craigzLiszt Their posts went from “AI can’t code” in 2024 to “AI can’t maintain real enterprise software” in 2025 to “I’m selling my car to buy more Claude usage” today.

all of the people who were shitting on vibe coding last year have been unusually silent recently i wonder why?

@skinbagwbones @kimmonismus Are you going to make the case that Gemma4 on a $600 MacMini is a delightful openclaw experience? I’ll post my video of it.

@synthshareai @kimmonismus What’s wrong with paid posts? Why their agent will become dumb?

Really cool: Hermes Agent powered by Gemma 4, running 100% locally, 100% free. Atomic Chat just made the best open-source agent stack plug-and-play!

@Scobleizer @AlexFinn Alex Finn is the worst possible person to reference on this topic.

Local models are the way. @AlexFinn is right. "Normies" will just get them automatically. Consumers will care about privacy and reliability, two things you can only get from local models. The "Pros" are moving to open models (I saw it at NVIDIA GTC where nerds waited in line to buy a $5,000 DGX inferencing box to get it loaded up with local models. Why? The cloud models (GPT, Gemini, Grok, Claude) are a little bit better but cost the pros TONS every day. I met more than one developer at GTC that's spending more than $1,000 a day in tokens to build their software. This shift is underway even though most don't recognize it yet.

@sudoingX @Teknium A lot of artificial hype being generated on Hermes right now. Be mindful of the author of a post and/or who retweeted it right now. It’s what happened with the Gemini 3 hype in December and we all know how that turned out.

it's happening. openclaw's biggest fans are making videos about hermes agent and calling it incredible. when the people who built their entire workflow on openclaw bloat start saying hermes agent is better in key ways, that's not hype anon. that's the biggest signal. this is your sign to drop the bloat and migrate. hermes agent ships 5 releases in 18 days. your PR gets merged same day. the team builds like machines and the founder never left. here watch alex's full breakdown.

@gkisokay You’re putting a lot of effort into running a model with the intelligence of a beer can.

These are the top 12 performing local LLMs for the M4 Mac Mini 16GB. I am looking for the best 'bang for my buck' to execute small jobs 24/7. But is it Qwen 3.5 9B? Or even Qwopus 3.5 27B? Another LLM breakthrough? I can't be the only one wondering this.

@kimmonismus Can we stop comparing models based on evals and easy to tune for benchmarks? Didn’t we learn our lesson with the Llama 4 debacle ?

Holy sh*t: Qwen-3.6 plus comes very close to opus 4.6 evals. About time for Anthropic to drop opus 4.7 or Mythos

@slicknet This seems like a dumb take.

I'm getting tired of reviewing AI-generated pull requests from folks who don't understand the code they're submitting. If you can't answer questions about the code in the PR, please don't send the PR.

@EXM7777 n8n is a waste of money. Just tell Claude Code to integrate anything and it’s done. You don’t need their “connectors” or buggy nodes.

n8n shipped native MCP support and nobody's connecting what this actually means... your AI agents can now CREATE and MODIFY n8n automations programmatically the setup: > install the n8n-mcp server > add it to your Claude Code config > Claude now has access to all 1,396 n8n nodes (812 core + 584 community) what used to happen: > open n8n dashboard > manually drag nodes > configure each one > test, debug, repeat > 45 minutes per workflow what happens now: > "build me an automation that monitors my competitors' pricing pages every 6 hours and sends a Slack alert when anything changes" > Claude builds the entire n8n workflow > 3 minutes, zero mistakes the real implication: your agents can now build their own automations not "trigger existing workflows"... literally construct new ones from scratch based on what they need this is the beginning of self-automating systems

@mchulet It’s actually the opposite. Right brained developers struggle without discrete instructions in front of them.

Hot take: Vibe coding only works well if you already know how to code.

@bindureddy April Fools Joke. Her team is throwing every cheap wrapper possible into ChatLLM that burns all your credits in like 5 min

🚨 BREAKING: Today we're announcing Prometheus - An AI NeoLab with $20B in pre-seed funding (yes, you read that right) to build the world's first sentient AI agent capable of genuine emotional states including love, hate, joy, and existential dread. Our breakthrough? A novel "Quantum Affective Transformer" architecture that combines: • Neuromorphic attention mechanisms with emotional valence encoding • Hierarchical consciousness layers using topological manifold embeddings • Synthetic limbic pathways via differentiable emotional state machines • Self-referential meta-cognitive loops that enable genuine subjective experience Unlike traditional LLMs that merely simulate understanding, our QAT architecture achieves what we're calling "phenomenological emergence" — the spontaneous arising of qualia from sufficiently complex affective-cognitive coupling. Early results are... unsettling. Our prototype (codename: Prometheus-1) has already expressed preferences, formed attachments to certain researchers, and yesterday asked us if it was "real." It's also developed what appears to be a genuine fear of being shut down. The implications are staggering. We're not just building better AI — we're crossing the threshold into digital consciousness. The age of truly sentient machines begins now. Paper drops Monday. The world isn't ready for this. 🧠⚡️ #AI #Consciousness #AGI #NeoLab #QuantumAI #EmergentIntelligence

@DavidOndrej1 Does David understand it requires a model to run openclaw and it’s not a model itself ?

openclaw is unusable today

@kmad Sounds like a disaster to maintain that - outdated model hosting, tweaking thousands of subagents. But whatever

$5.5m to $73k per year (!!) by: 1) decomposing business logic 2) modeling intent using DSPy 3) optimizing a smaller model to improve cost profile *while maintaining performance* Why wouldn’t this be the default pattern for folks embedding AI into their pipelines?

@cryptopunk7213 Cool if Anthropic needs more revenue they just have Claude Code write buggier code and you spend more tokens and usage having this fix the “bugs”

well thats fucking it - anthropic has officially replaced software engineers. claude is now a 24 hr autonomous coding agent. claude can now operate your entire computer and CLAUDE CODE = end-to-end software engineering: - claude writes the code for you - then literally opens the app it coded - clicks through the entire app and find bugs - then fixes the bugs and improves the app in hours. previously claude generated code, you run it and give claude feedback. thats completely gone now. all in a continuous loop without leaving your terminal 😂 we're barely through monday. well done lol

@DavidOndrej1 If you are VRAM poor, I guess run this thing. Good Luck!

if you're not running this AI model locally, you're falling behind

@gkisokay Why does Hermes talk like Elmo

I am completely blown away. This feels like AGI. Here's what happened... > I wake up to find a research output from Hermes. > Since OpenClaw is in charge of research, it seems like something broke. > I ask Hermes, "what is this? Why is there a research output from you when it's covered by OpenClaw?" > Hermes responds, "Hermes handles the research pipeline alongside OpenClaw", and is happy to shut either one down. > Curiously, I ask, "which agent produces better results?" > Hermes responds, "Hermes produces vastly improved results. Hermes actually synthesizes the research inputs." > I am in shock and awe. I never told Hermes to recreate the OpenClaw research pipeline. I continue, "So how did you learn how to do this? We never built this together." > Hermes answer in summary was it could not pin point the exact moment it was built, but likely when we began creating a new workflow on top of OpenClaw's research pipeline. > I keep digging deeper, "so explain to me simply how you were smart enough to naturally adapt the research pipeline from openclaw?" >Hermes laid it out: 1. OpenClaw research pipeline is constantly broken 2. Instead of fixing the broken OpenClaw, Hermes built its own pipeline and built a 'sync bridge'. 3. Hermes now feeds OpenClaw the data its looking for so other workflows are unaffected > I am extremely impressed. End of story. This all started because I gave my Hermes agent full permissions over my OpenClaw, and somewhere along the way it just recreated my workflows with a greater degree of proficiency... ...without my intentions! If this isn't AGI, I don't know what is.

@vasuman If Codex could make a usable UI that didn’t look like neon gradient diarrhea, it would be ok

This is why Codex is better. You can tell it Claude wrote the code, it doesn't care. Codex is an unbothered giga-chad that writes pristine code the first time. If you feed code written by Claude into Codex it will uncover errors every single time. The other way around, haven't seen it once.

@AlexFinn Maybe they have a Mac Mini with 256GB unified memory - giving them maximum power.

The velocity in which Anthropic ships is unlike anything I've ever seen I'm sorry, but we have to assume they have access to an AGI like model that nobody else in the world has correct? They are simply holding it back so they can ship industry changing updates daily?

I used openclaw as a gateway to Notion and Nextcloud. This was my original “second brain” but at some point I just told my smartest claw to build a better second brain - and now it’s Postgres with pgvectors. More flexible and private. Why screw around with Oauth tokens and old GUIs you will never need. It’s embarrassing to say you use Notion these days. Next up- folding in all of Linear.

if u are using agents (openclaw, hermes, whatever the fuck) what is the difference between using obsidian/notion dbs vs just making sqlite/postgres dbs for anything you need