Ask us your questions about Recursive Language Models (RLMs) & where LMs are underutilized or inefficient. We’ll pick some to feature in an upcoming explainer w/MIT PhD student Alex Zhang (
@a1zhang
), who recently developed RLMs. For more on his work: https://
bit.ly/4vGyLxo
LLMS
-
Recursive Language Models: Expert Q&A with MIT PhD Student
By
–
-
128k Context Window Ablation Study on Billion-Parameter MoE Models
By
–
any references come to mind for 128k context on a 1Bish MoE? not sure i understand this area very well. i guess the primary ablation i would want is on context length quality vs width dimension…?
-
Trillion-fold compute growth: AI training scales toward 2028
By
–
Since I began work on AI in 2010, training compute for frontier models has grown by one trillion times. Now we're looking at something like another thousand-fold growth in effective compute by the end of 2028. 1000x the existing 1,000,000,000,000x. Extraordinary stuff.
-
How to launch and test Claude Code in a project
By
–
5. Lanza Claude Code y pruébalo en un proyecto
— Nico (@nicos_ai) 22 avril 2026
Entra en la carpeta de tu proyecto y arranca Claude con el modelo elegido.
A partir de aquí ya puede leer archivos, modificar código y ejecutar tareas. pic.twitter.com/d1TiIV3mMX5. Launch Claude Code and test it in a project Enter your project's folder and start Claude with the chosen model. From here on, it can already read files, modify code, and execute tasks.
-
Connect Claude Code to a Local Ollama Instance
By
–
4. Connect Claude Code to Your Computer This step is key: instead of using Anthropic's servers, you point it to your local Ollama. Set up the "base URL" so that Claude looks to your machine (localhost).
-
Instructions to Download Local Code Models
By
–
3. Descarga un modelo para programar
— Nico (@nicos_ai) 22 avril 2026
Elige según la potencia de tu PC:
• Potente: qwen3-coder:30b
• Más modesto: qwen2.5-coder:7b o gemma:2b
Luego, en la terminal, descárgalo con:
ollama pull NOMBRE_DEL_MODELO pic.twitter.com/75wM6mu9KG3. Descarga un modelo para programar Elige según la potencia de tu PC:
• Potente: qwen3-coder:30b
• Más modesto: qwen2.5-coder:7b o gemma:2b Luego, en la terminal, descárgalo con:
ollama pull NOMBRE_DEL_MODELO -
MIT Improves Reasoning Model Calibration Through Reinforcement Learning
By
–
“Reinforcement Learning w/Calibration Rewards” What makes top reasoning models overconfident? MIT found that in these models, RL rewards correct answers, not certainty. Training models to estimate confidence improved calibration while maintaining accuracy:
-
MIT CSAIL Advances Reliable AI Systems at ICLR Conference
By
–
This week, MIT CSAIL will join other top ML researchers at ICLR to tackle a shift in focus from more powerful AI to more reliable systems Our papers at the conference show how to potentially make AI models stronger critical thinkers, more honest, & better at math
-
MIT Harvard Study AI Agents Critical Thinking Battleship
By
–
“Collaborative Battleship” MIT & Harvard developed a collaborative version of Battleship to see if AI agents are as good at asking questions as answering them. They found that many LMs struggle w/critical thinking, but Monte Carlo inference strategies can help even tiny
-
Building Apps with AI APIs in Minutes at Low Cost
By
–
It takes less than 10 minutes to make an app out of X over on @Pokee_AI. Which includes the X API for free in its low token costs.
— Robert Scoble (@Scobleizer) 22 avril 2026
I talk to @AndrewWarner about why this is so powerful.
And it is cheaper now to do the same with your OpenClaw or Hermes or Manus or almost any AI… https://t.co/fc8Fnhf0AzIt takes less than 10 minutes to make an app out of X over on @Pokee_AI
. Which includes the X API for free in its low token costs. I talk to @AndrewWarner about why this is so powerful. And it is cheaper now to do the same with your OpenClaw or Hermes or Manus or almost any AI