G Adam

Be kind.

@Teknium Can I use this model for hermes agent via pinokio launcher api.together.ai/models/Qwen/Qw…

I think this is still an underrated tool! Not only does this make it easy to install Hermes (and apparently on windows native) - it also gives it access to like 50+ other AI tools that are also built into Pinokio

@timothylindblom Newly

Introducing Newly. The world's first Agentic app builder. RT + Comment "Newly" and I'll send you 100 apps to make $10K/mo.

@callebtc It's great

anyone tried hermes agent? do you like it?

@saranormous I am not so technical and would love to try

any nontechnical folks want to get more comfortable/powerful in their use of AI and want to be a beta user on something I made?

@0xSero You deserve everything lets go my G

In 72 hours I got over 100k of value 1. Lambda gave me 5000$ credits in compute 2. Nvidia offered me 8x H100s on the cloud (20$/h) idk for how long but assuming 2 weeks that'd be 5000$~ 3. TNG technology offered me 2 weeks of B200s which is something like 12000$ in compute 4. A kind person offered me 100k in GCP credits (enough to train a 27B if you do it right) 5. Framework offered to mail me a desktop computer 6. We got 14,000$ in donations which will go to buying 2x RTX Pro 6000s (bringing me up to 384GB VRAM) 7. I got over 6M impressions which based on my RPM would be 1500$ over my 500$~ usual per pay period 8. I have gained 17,000~ followers, over doubling my follower count 9. 17 subscribers on X + 700 on youtube. The total value of all this approaches at minimum 50,000$~ and closer to 150,000$ if I leverage it all. --------------------- What I'll be doing with all this: Eric is an incredibly driven researcher I have been bouncing ideas off of over the last month. Him and I have been tackling the idea of getting massive models to fit on relatively cheap memory. The idea is taking advantage of different forms of memory, in combination with expert saliency scoring, to offload specific expert groupings to different memory tiers. For the MoEs I've tested over my entire AI session history about 37.5% of the model is responsible for 95% of token routing. So we can offload 62.5% of an LLM onto SSD/NVMe/CPU/Cheap VRAM this should theoretically result in minimal latency added if we can select the right experts. We can combine this with paged swapping to further accelerate the prompt processing, if done right we are looking at very very decent performance for massive unquantisation & unpruned LLMs. You can get DeepSeek-v3.2-speciale at full intelligence with decent tokens/s as long as you have enough vram to host the core 20-40% of the model and enough ram or SSD to host the rest. Add quantisation to the mix and you can basically have decent speeds and intelligence with just 5-10% of the model's size in vram (+ you need some for context) The funds will be used to push this to it's limits. ----------------- There's also tons of research that you can quantise a model drastically, then distill from the original BF16 or make a LoRA to align it back to the original mostly. This will be added to the pipeline too. ------------------ All this will be built out here: github.com/0xSero/moe-com… you will be able to take any MoE and shove it in here, and with only 24GB and enough RAM/NVMe to compress it down. it'll be slow as hell but it will work with little tinkering. ------------------ Lastly I will be looking into either a full training run from scratch -> or just post-training on an open AMERICAN base model - a research model - an openclaw/nanoclaw/hermes model - a browser-use model To prove that this can be done. -------------------- I will be bad at all of it, and doubt I will get beyond the best small models from 6 months ago, but I want to prove it's no boogeyman impossible task to everyone who says otherwise. -------------------- By the end of the year: 1. I will have 1 model I trained in some capacity be on the top 5 at either pinchbench, browseruse, or research. 2. My github will have a master repo which combines all my work into reusable generalised scripts to help you do that same. 3. The largest public comparative dataset for all MoE quantisations, prunes, benchmarks, costs, hardware requirements. -------------------------- A lot of this will be lead by Eric, who I will tag in the next post. I want to say thank you to everyone who has supported me, I have gotten a lot of comments stating: 1. I'm crazy, stupid, or both 2. I'm wasting my time, no one cares about this 3. This is not a real issue I believe the amount of interest and support I've received says it all. donate.sybilsolutions.ai

@Teknium Yeah LFG hermes agent

Hermes Agent about to be a BioHacking guru

@NotebookLM researches and generates a video on "The Secret Mission OPSEC Playbook: A Guide to Operational Security," after it deep dive into how a 36-minute Strava jog revealed the exact location of the French aircraft carrier Charles de Gaulle.

@F2aldi Sekalian ini kah? x.com/i/status/20349…

Cafe Cursor Jakarta is coming soon. 🇮🇩☕ Post Eid ul-Fitr Edition — April 5th, South Jakarta. Cursor Team members are flying in. Free event. Good people. Real conversations. Real Builders Come build, hang, and connect with fellow AI enthusiasts. 🎫 Free to join!

@AngelicaOung This is how old folks felt a few decades ago, at the height of cartoons being used in war to educate people about the situation. Love the vibes.

Did YOU want to watch CCTV's AI Martial Arts cartoon about the Straits of Hormuz crisis? Complete with fighting Persian Cats? Well I subtitled it for you so you can enjoy it in all its trope-laden glory! Remember kids, the mountains will stay standing while the green water flows, and the true art of war is not figuring out how to fight, but how to stop!🥷😼🦅

@NotebookLM I learn about China's 2026 master plan and ask NotebookLM to make this impressive work

We wanted to come on here to clear the air and confirm that the rumors are true... Cinematic Video Overviews are officially rolled out to 100% of Pro users in English! Please respect our privacy during this time by flooding our replies with your favorite creations.

@shuding Pretty

With Vercel’s geolocation headers, i.e. headers.get('x-vercel-ip-latitude'), I made this pretty “where’s my IP” service in a few lines of code: cobe.vercel.app/ip vercel.com/kb/guide/geo-i…

@GMapsPlatform Wow impressive

🔑 No credit card required! With the new Maps Demo Key, you can get a working API key with just your Google account and start building in seconds ➡️ goo.gle/3Pu9JB2 We’ve removed the barrier to entry, giving developers direct access to build with select Google Maps Platform products — including Maps JS API, Places UI Kit, and Weather API. Whether you're testing new features or validating technical feasibility, prototype with confidence in a controlled sandbox with automatic usage guardrails. ➡️ Seamlessly works with AI agents to turn prompts into working geospatial prototypes. ➡️ Maps Demo Key is the easiest way to test AI-generated geospatial code without hitting setup blockers. ➡️ Easily transition to a full account to unlock our generous monthly free usage tier, additional APIs, and technical support — all while keeping your project moving. Try it at the link above.

@usenaive Naive

Introducing Naive - hire autonomous employees with their own identity. Own compute. Own bank account. Own legal entity. Own email. Own credentials. Own mobile. No humans-in-the-loop. They sign up for tools, pay for services, deploy apps, file documents, and run your entire company. Describe a business. Naive runs it. Reply "Naive" + RT. Get $100 credit for free.

@gaxrav Placebo is proving that psycho cybernetics is a powerful harness for reality

placebo proves your entire life is just a function of your beliefs. you can bend reality however you want if you really tried. it's all malleable.

@blinkdotnew Claw

Introducing Blink Claw - the first platform to hire unlimited AI employees that run your business 24/7. 180+ AI models included. Gmail, Slack, LinkedIn, HubSpot - one-click connect. No API keys, no $600 Mac Mini. Reply "Claw" + RT. Your first agent is on us. ($50 - 200 creds)

@jamesclift Durable can we have a platform where it lets user type in any real-world news, idea, or "what if" scenario, then instantly runs a virtual world AI characters that evolve and predict what could happen next so user can test decisions and see the future without any real risk.

Introducing Durable. The first AI business builder that replaces your 9-5 income. RT + comment “Durable” and we'll build your business for FREE.

@MillyTamati @claudeai @beehiiv Will check this one, I love to do experiements and might need this lol

This is the STRONGEST data signal re: jobs / hiring I've ever seen Less than a week ago, me and @claudeai shipped a job board for weird jobs Since then: ~ 541,000 have seen it on socials ~ 3192 joined our @beehiiv newsletter ~ 35,432 have visited the site I'm telling you: people are SICK TO DEATH of boring-ass rigid, narrow job descriptions They want weird! They want broad! They want freedom and flexibility to come and make *real* impact, not just operate inside an old-school box This is the job board for people who build, tinker, get shit done, and move the needle inside orgs! We have soooo much talent chomping at the bit for these roles, and now companies - we need you to catch up! If you're hiring, I'll share it with 52,193 readers tomorrow! DM me and we'll get it live :) PS: if you're into this - comment / like / repost to share this message!

@NebulaAI @NebulaAI I cannot DM you

@asynchronope Very cool, shoot me a dm with your email

Introducing Virtual Computer We're giving you a persistent computer with built-in agents that use the web, develop software, and get smarter over time. Create and deploy a website. Generate and edit videos. Automatically fix bugs as they get reported. Your AI team works 24/7 to achieve your goal. Reply with what you'd build - gifting $50 in credits to the most interesting answers

@agentcardai Verification timed out

Introducing AgentCard. Your agent can now buy anything: • pay for inference & APIs • order DoorDash, Amazon, Ubers • run marketing • trade Polymarket 24/7 Open to all, not just businesses 🔥 Instant. Private. Reusable. Live today.