Best Personal AI Agents in 2026: OpenClaw, Hermes Agent, Gemini Spark and More, Compared on Memory, Security and Cost
Hermes Agent, OpenClaw, Gemini Spark, OpenAI dots, Meta Muse and Perplexity Personal Computer ranked on memory, security defaults and real cost.
The post Best Personal AI Agents in 2026: OpenClaw, Hermes Agent, Gemini Spark and More, Compared on Memory, Security and Cost appeared first on MarkTechPo...
Google AI Previews Tool Retrieval in the Gemini API for Large Tool Libraries
Google launched Gemini API Tool Retrieval in preview. Agents keep a large tool library on standby and load each parameter schema only when needed, inside one Interactions API request.
The post Google AI Previews Tool Retrieval in the Gemini API for Large Tool Libraries appeared first on MarkTechPost...
A Team of Researchers from Columbia and CertiK Introduce TensorLean for Formal Verification of GPU Kernels
TensorLean, from Columbia University and CertiK, formally verifies production GPU kernels at the PTX level using Lean. It checked 149 kernel instances, proved 83 correct, and found 38 bugs in FlashAttention, DeepGEMM and more.
The post A Team of Researchers from Columbia and CertiK Introduce TensorL...
Meet Thinking Machines Inkling 2 Mini: 26B Looped MoE Runs on a 32GB Mac
Thinking Machines released Inkling 2 Mini, a 26.4B-parameter looped MoE transformer with 3.4B active parameters. It runs on a 32GB Mac or one DGX Spark and scores 79.2% on SWE-bench Verified.
The post Meet Thinking Machines Inkling 2 Mini: 26B Looped MoE Runs on a 32GB Mac appeared first on MarkTech...
Meta FAIR Self-Improving Memory Hits 56.0 on Continual Learning Bench
Meta FAIR’s Self-Improving Memory lets Kimi-K2.6 write its own LOAD and OFFLOAD memory prompts, then distills them into its weights. Optimized prompts score 56.0 versus 44.6 for the best hand-written harness on Continual Learning Bench.
The post Meta FAIR Self-Improving Memory Hits 56.0 on Continual...
13 Best Agent Gateways in 2026 for MCP, A2A and LLM Traffic: Kong, Bifrost, AgentCore, Arcade
We ranked the 13 best agent gateways of 2026 by how they govern model, MCP tool and agent-to-agent traffic, with verified pricing, deployment options and the trade-offs each vendor's marketing leaves out.
The post 13 Best Agent Gateways in 2026 for MCP, A2A and LLM Traffic: Kong, Bifrost, AgentCore,...
Best AI Video Generation Models in 2026: Elo, Price per Second, Open Weights
The AI video leaderboard looks very different from 12 months ago. Native audio is now table stakes. Clips run 15–30 seconds. And an open-weights model sits in the top 3. This ranking (as of Nov 13, 2026) uses one quality signal: blind human-preference Elo from the Artificial Analysis Video Arena. We...
IBM Announces IBM Quantum Nighthawk r3: A New Processor to Support 10k Quantum Operations on 520 Programmable Qubits
IBM announced Quantum Nighthawk r3, a 520-qubit processor designed for 10,000 quantum operations. 2 r3 chips will link into a 1,040-qubit system in 2027, while Nighthawk r2 already posts up to 19x speedups over Heron.
The post IBM Announces IBM Quantum Nighthawk r3: A New Processor to Support 10k Qu...
Meta FAIR Releases e-means: An Algorithm Beating k-means in 10x Fewer Epochs
Meta FAIR’s e-means is a mini-batch k-means replacement shipped in FAISS 1.16.0. It reaches Lloyd’s 25-epoch loss in 1.4 to 2.6 epochs, with 10-45x GPU speedups and no extra hyperparameters.
The post Meta FAIR Releases e-means: An Algorithm Beating k-means in 10x Fewer Epochs appeared first on MarkT...
Baidu’s ERNIE Evolve Automated Research System Beats NanoChat and NanoGPT Records
Baidu’s ERNIE Evolve is an automated research system that edits code, runs experiments and keeps only verified gains. It beat public bests on NanoChat and NanoGPT Speedrun and sped up ERNIE-5.5-Flash inference.
The post Baidu’s ERNIE Evolve Automated Research System Beats NanoChat and NanoGPT Record...
MoE routing strategies decide which experts process each token. This guide explains 7 methods, from Mixtral's top-2 softmax to DeepSeek-V4's hash routing, with the models that use each one.
The post MoE Routing Strategies Explained: Top-K, Expert-Choice, Sigmoid Gating and Dynamic Routing (2026 Guid...
Nous Research Releases Arete-27B that Cuts Qwen3.8-27B Propaganda From 22% to 0.9%
Nous Research released Arete-27B, an Apache 2.0 fine-tune of Qwen3.8-27B. On Nous’s 803-prompt eval, propaganda answers fell from 22% to 0.9% while Hermes Bench stayed flat at 65.60%.
The post Nous Research Releases Arete-27B that Cuts Qwen3.8-27B Propaganda From 22% to 0.9% appeared first on MarkTe...
How to Run NVIDIA Dory 4B with llama.cpp: Loop by Loop Guide
Explore a comprehensive coding guide for NVIDIA's Dory 1.0 4B looped language model. Learn how to build the pinned llama.cpp branch, analyze loop-by-loop compute costs, test memory caching, and run paired evaluations.
The post How to Run NVIDIA Dory 4B with llama.cpp: Loop by Loop Guide appeared fir...
Thinking Machines Releases Inkling 2 Small, a 594B MoE With 17B Active
Thinking Machines Lab released Inkling 2 Small, a 594B-parameter MoE with 17B active parameters. It scores 31 on the Artificial Analysis Intelligence Index and runs on Tinker, with Apache 2.0 weights planned.
The post Thinking Machines Releases Inkling 2 Small, a 594B MoE With 17B Active appeared fi...
Ricursive AI Releases Ripple-65B Preview: A 65B Dense Open-Weight Model Scoring 80.5 on Terminal-Bench 2.1
Ricursive Intelligence released Ripple-65B Preview, a 65B dense open-weight LLM under Apache 2.0. It scores 80.5 on Terminal-Bench 2.1, ahead of US open models up to 15x its size.
The post Ricursive AI Releases Ripple-65B Preview: A 65B Dense Open-Weight Model Scoring 80.5 on Terminal-Bench 2.1 appe...
NVIDIA Shows 3 Ways to Speed Up MoE Inference on DGX Spark, Lifting Ling-3.0-flash Throughput 42.5%
NVIDIA shows how 3 stacked optimizations speed up MoE inference on a single DGX Spark. On Ant Group inclusionAI's 124B Ling-3.0-flash, GSM8K decode throughput rose 42.5% with no detectable accuracy change.
The post NVIDIA Shows 3 Ways to Speed Up MoE Inference on DGX Spark, Lifting Ling-3.0-flash Th...
Prime Intellect Releases Prime Mega MoE: Trainable Fused MoE Kernel, 3.11x Faster Forward Pass
Prime Intellect released Prime Mega MoE, a backward pass for DeepSeek’s fused Mega MoE kernel. It makes the kernel trainable and speeds Qwen3 MoE training steps by up to 34% in prime-rl.
The post Prime Intellect Releases Prime Mega MoE: Trainable Fused MoE Kernel, 3.11x Faster Forward Pass appeared ...
Meet LEANN: An Open-Source Vector Index that Shrinks a 60M-Chunk RAG Index from 201 GB to 6 GB
UC Berkeley’s LEANN vector index stores a pruned graph and recomputes embeddings at query time. It matches HNSW accuracy at 90% recall using 4 GB instead of 188 GB, at the cost of seconds-level search.
The post Meet LEANN: An Open-Source Vector Index that Shrinks a 60M-Chunk RAG Index from 201 GB to...
How to Run Underdog Saluki 27B: 2-Bit Qwen3.8-27B Tool-Calling Guide
Explore a complete coding guide comparing Underdog Saluki 27B with ISTA's GSQ-RCO quantization, examining GGUF headers, memory usage, and BFCL tool-calling performance in stock llama.cpp
The post How to Run Underdog Saluki 27B: 2-Bit Qwen3.8-27B Tool-Calling Guide appeared first on MarkTechPost.
Cohere Releases Rerank 5 With Passage-Level Context Focus and Calibrated Scores
Cohere Rerank 5 ships in Pro and Fast tiers with a 32K context window, Context Focus passage extraction and calibrated relevance scores. Pro scores 82.2 on BRIGHT and costs $0.05 per 1M tokens.
The post Cohere Releases Rerank 5 With Passage-Level Context Focus and Calibrated Scores appeared first on...
A Developer’s Guide to OmniParseBench: Leaderboard Benchmarks and OCR Testing
Explore how to audit and rebuild Datalab's OmniParseBench, test parser ranking certainty with document-level bootstrapping, and evaluate Tesseract and Indra OCR performance on a custom sample.
The post A Developer’s Guide to OmniParseBench: Leaderboard Benchmarks and OCR Testing appeared first on Ma...
A Coding Guide to Cactus Whistle: Does a 16.9 MB Speech Model Hold Up Against Whisper Base? Word Error Rate, Speed, Streaming, Timestamps, Keywords, and Speech-to-Tool Calls on a CPU
Explore a comprehensive coding guide benchmarking Cactus Compute's 16.9 MB speech model against Whisper base. Learn about word error rates, CPU speed, streaming latency, and speech-to-tool integration.
The post A Coding Guide to Cactus Whistle: Does a 16.9 MB Speech Model Hold Up Against Whisper Bas...
NVIDIA Nsight Python Tutorial: How to Profile GPU Kernels
Discover NVIDIA Nsight Python, an open-source interface that allows developers to profile GPU kernels, analyze hardware metrics, evaluate cache and clock controls, and measure kernel fusion directly from Python code.
The post NVIDIA Nsight Python Tutorial: How to Profile GPU Kernels appeared first o...
Google Open-Sources TorchTPU, a Native PyTorch Backend for Cloud TPUs
Google and Meta open-sourced TorchTPU, a native PyTorch backend for Cloud TPUs. It runs eager by default, compiles through torch.compile and XLA, and replaces PyTorch/XLA for new workloads.
The post Google Open-Sources TorchTPU, a Native PyTorch Backend for Cloud TPUs appeared first on MarkTechPost....