1. I I have been doing some early testing and will share other cool applications in a longer post soon. T... I have been doing some early testing and will share other cool applications in a longer post soon. Try Drex Max here: console.nace.ai 💬 1 🔄 1 ❤️ 6 👀 829 &#x 10/19 22:18 ♡
2. Decision models are going multimodal. Drex Max looks really strong. It can make fast decisions stra... Decision models are going multimodal. Drex Max looks really strong. It can make fast decisions straight from screenshots, screencasts, scanned documents, scientific charts, and pho 10/19 22:18 ♡
3. A Apply to the Nebius AI Builder Program here https://t.co/wUJBCeqHcu Apply to the Nebius AI Builder Program here dev.nebius.com/builders 💬 0 🔄 0 ❤️ 4 👀 868 📊 1 ⚡ Powered by xgo.ing 10/19 21:48 ♡
4. No better time to learn how to build with agents and open models. I encourage students to apply con... No better time to learn how to build with agents and open models. I encourage students to apply context engineering techniques, then build their own domain-specific harnesses. And 10/19 21:46 ♡
5. Generally, good advice here. Systems thinking is at the top of my list too. That’s how you interact ... Generally, good advice here. Systems thinking is at the top of my list too. That’s how you interact and build effectively with agents today, by thinking of the subparts of the syst 10/19 20:52 ♡
6. L Learn how to build evals, folks! It's one of the pillars of the intelligence stack. Agents are hu... Learn how to build evals, folks! It's one of the pillars of the intelligence stack. Agents are hungry for data and can get it in many ways, but you can't build anything use 10/19 08:23 ♡
7. Nice paper on scaling data environments from scratch. They built an engine that creates data-analys... Nice paper on scaling data environments from scratch. They built an engine that creates data-analysis environments from scratch. They apply RL, which adds 20.9 points on DABstep-Ha 10/19 05:45 ♡
8. // Latent Semantic Memory for LLMs // This paper presents some really interesting findings about ag... // Latent Semantic Memory for LLMs // This paper presents some really interesting findings about agent memory. They find that sixteen memory tokens beat full-context inference on F 10/19 01:59 ♡
9. Great application of small language models from Salesforce and colleagues. AI-scientist pipelines a... Great application of small language models from Salesforce and colleagues. AI-scientist pipelines are well known to struggle to propose novel and diverse research ideas. This team 10/18 06:04 ♡
10. Mind-blowing to see these Pareto improvements in performance and cost. More than anything, it's cr... Mind-blowing to see these Pareto improvements in performance and cost. More than anything, it's crazy how quickly these improvements are landing across providers. This matters 10/18 03:50 ♡
