You're in a Research Scientist interview at OpenAI. The interviewer asks: "How would you expand the context length of an LLM from 2K to 128K tokens?" You: "I will fine-tune the model on longer docs with 128K context." Interview over. Here's what you missed:
MACHINE LEARNING
-
Harvey’s LAB benchmark uses human-like verification with per-task criteria
By
–
.
@Harvey
’s LAB benchmark approaches verification like a human would. Every task in a dataset has criteria for the task to pass. Legal agents can have 50+, with each one having its own judge call. It’s easy to audit, but can be expensive at scale. LangChain Labs teamed up with -
Microsoft’s MAI-Image-2.5 takes #2 in Image Edit Arena
By
–
Microsoft just dropped MAI-Image-2.5 — and it immediately landed #2 in the Image Edit Arena (Single-Image-Edit) with a score of 1401. That's +10 pts over Nano Banana 2, Grok Imagine, and ChatGPT-Image-Latest-High Fidelity — and it pushes the Pareto frontier forward. Big W
-
SambaNova unveils disaggregated inference demo with 2x speedup
By
–
The first disaggregated inference demo for AI agents is now live. At #COMPUTEX2026, SambaNova demonstrated premium inference running in production at VC2 — using NVIDIA B200 GPUs for prefill and SambaNova RDUs for decode. The result: 2x faster inference than B200-only
-
Microsoft MAI Guide: 1T Model, 35B Active, No Synthetic Data
By
–
Fantastic in depth guide about Microsoft MAI by @eliebakouch tl;dr about the model: Respect where respect is due. -zero synthetic data or distillation from previous models.
-1T model with 35B active, trained on 33.5T tokens -
8 LLMs for Agentic AI: Reasoning, Perception, Planning, Action
By
–
8 types of LLMs used in AI agents GPT • MoE • LRM • VLM • SLM • LAM • HRM • LCM Different models for reasoning, perception, planning, and action — not just chat. Agentic AI = model orchestration. #AI #LLMs #AgenticAI #GenAI #MachineLearning
-
@alphasignalai — 2026-06-03
By
–
YES, the CVE run makes that concrete, 100% accuracy at 85.1% fewer tokens, while the other systems stayed under 25%. Only word to push back on is "unprecedented" though, CodeAct was doing code-as-actions back at ICML 2024.
-
LangSmith Sandbox Gateway Observability
By
–
langsmith! Sandbox: https://
docs.langchain.com/langsmith/sand
boxes
… Gateway: https://
docs.langchain.com/langsmith/llm-
gateway
… Observability: https://
docs.langchain.com/langsmith/obse
rvability
… -
SDPO explored in practical async setups praised
By
–
cool work folks – nice to see SDPO explored in practical/async setups!
-
GLM endpoint slow, mistakes help understanding, coding product fine
By
–
Yesterday evening GLM endpoint was slow, high traffic during U.S. working hours. Today it's making seemingly sillier mistakes, but every one it makes helps me understand the solution better — which has its benefits. Not perfect, but the subfrontier coding product is fine as-is.