AI

Deep, developer-first coverage of artificial intelligence — from frontier model releases and benchmarks to agents, RAG pipelines, and the AI-native tools changing how we ship software. No hype, just what actually matters to engineers.

Article 2d ago 7

Your Slack Bot's Database Is Now a Claude Session

Vercel's template wires Claude Managed Agents into Chat SDK, and the thin bridge is the point.

Rachel Goldstein

Jetson Thor Midrange Modules Reset Edge Robotics Targets

T3000 and T2000 give foundation-model robots a cost ladder, with emulation years before volume silicon.

Article · 1mo ago2

Differentiable Fortran Without the Rewrite

LFortran and Enzyme turn validated simulation code into exact-gradient layers for JAX.

Article · 1mo ago2

MLOps Still Can't Solve Its Hardest Problems

Tooling keeps improving, yet emission control, safe filtering and org friction remain open failures at production scale.

Article · 1mo ago6

Inkling Bets Fine-Tuning Beats Frontier Chatbots

Thinking Machines' first open-weights model is less a chatbot competitor than an infrastructure bet on customization over off-the-shelf AI.

News · 1mo ago5

Inkling Puts 975B Open Weights in Reach

Murati's lab ships a frontier MoE you can fine-tune, not just rent.

Article · 1mo ago2

Claude Fable 5 Is a Specialist, Not a Default

Mythos-class capability arrives with 2x pricing, always-on thinking, and fallbacks that can silently change your answer.

Article · 1mo ago1

Old Xeons Can Run Gemma 4 at Reading Speed

MoE math, CPU kernels, and speculative decoding turn retired enterprise boxes into real local inference hosts.

Article · 1mo ago1

DSLs Make LLM Code Generation Production-Ready

Constrained languages shrink the output space so models produce verifiable results instead of plausible noise.

Article · 1mo ago1

Claude’s Values Shift by Model and Language

Anthropic’s 300K-conversation study turns model choice and locale into measurable behavior, not flavor.

Article · 1mo ago2

Why a Mario JEPA Predicts Well and Plans Poorly

A from-scratch Super Mario world model clears short-horizon tests, then stalls on distant goals.

Article · 1mo ago1

Claude's Memory Leak Is Every Agent Builder's Problem

A link-walking exploit shows agentic browsing turns AI memory into a silent data-exfiltration channel by design.

Article · 1mo ago2

Parallel agents crack Erdős problems by isolation

Twenty independent Codex harnesses, Lean gates, and heavy tool sandboxes show how multi-agent work actually scales.

Article · 1mo ago1

Local four-tier memory for long-horizon agents

TencentDB Agent Memory swaps flat vector dumps for progressive L0–L3 layers and Mermaid task canvases, with measured token cuts on OpenClaw.

Article · 1mo ago1

GPT-5.6 Agents Write Their Own Orchestration

Programmatic tool calling moves multi-step control flow into a sandboxed V8 runtime, cutting round trips and context bloat.

Article · 1mo ago1

Bonsai 27B Puts Real Agents on Phones

A 3.9 GB 1-bit 27B model clears the iPhone memory gate that blocked every prior build of this size.

Article · 1mo ago1