LMs can struggle w/open-ended tasks that have constraints, such as advanced puzzles & math proofs. MIT’s "DisCIPL" uses an LLM to steer smaller LMs to collaborate on these prompts. It achieves accuracy & efficiency comparable to much leading models: https://
bit.ly/4rLcYmi
RESEARCH
-

MIT’s DisCIPL: Steering Smaller LMs for Complex Problem-Solving
By
–
-

Mixture-of-Agents Boosts Large Language Model Performance
By
–
Mixture-of-Agents Enhances Large Language Model Capabilities Wang et al.: https://
arxiv.org/abs/2406.04692 #ArtificialIntelligence #DeepLearning #MachineLearning -

Meta Research Challenges Chain-of-Thought Reasoning Approach
By
–
NEW Research from Meta Superintelligence Labs and collaborators. The default approach to improving LLM reasoning today remains extending chain-of-thought sequences. Longer reasoning traces aren't always better. Longer traces conflate reasoning depth with sequence length and
-
Meta Engineer Joins Anthropic: Journey Through Tech Leadership
By
–
Thanks for having me on Ryan! I had a blast talking about my journey from startups, to VC, to building product at Facebook and Instagram, to being responsible for code quality for all of Meta’s codebases, to joining Anthropic.
— Boris Cherny (@bcherny) 15 décembre 2025
This sequence of events is the reason Claude Code… https://t.co/XOxVH0rOWxThanks for having me on Ryan! I had a blast talking about my journey from startups, to VC, to building product at Facebook and Instagram, to being responsible for code quality for all of Meta’s codebases, to joining Anthropic. This sequence of events is the reason Claude Code
-
Humans and Machines Collaboratively Designing Future Systems
By
–
Humachineology studies show that humans and machines are designing, creating, and optimizing future systems.
→ View original post on X — @drhassanrashidi, 2025-12-15 13:52 UTC
-
Humachineology: Designing Human-Machine Integration Systems
By
–
Humachineology: Design Orientation and Systemic Implications A distinguishing feature of humachineology is its design-oriented approach to shaping the interaction and integration of humans and machines. This perspective views the future not as a deterministic outcome of
-

MIT’s Loop-Closure Grasping: Balancing Versatility and Strength in Robotics
By
–
Robotics just took a meaningful step forward by rethinking the shape of grasping, not just the force behind it. MIT researchers have introduced loop-closure grasping, a concept that elegantly solves one of robotics’ oldest tradeoffs: Versatile grasps are rarely strong.
-

New Research on Bounding Hallucinations in RAG Systems
By
–
This paper explains why RAG works in demos and breaks in production. The paper is “Bounding Hallucinations: Information-Theoretic Guarantees for RAG Systems via Merlin–Arthur Protocols.” And it attacks the hallucination problem from a direction almost nobody in applied AI is
-

DeepCode: Open Agentic Coding System by Li et al.
By
–
DeepCode: Open Agentic Coding Li et al.: https://
arxiv.org/abs/2512.07921 #ArtificialIntelligence #DeepLearning #MachineLearning -
Macaron focuses on smarter training over benchmark chasing
By
–
Most AI companies chase benchmarks nobody cares about. Macaron chases real intelligence that learns from actual experience. Research that ships: https://
macaron.im/mindlab
Product that works: https://
macaron.im Bigger models won't save you. Smarter training will.