Insights for AI builders
Tutorials, product updates, and ideas to help you build and ship AI applications faster.
Subscribe via RSS
Why Do AI Agents Forget Decisions You Already Made?
A practical guide to structuring context, decisions, and skills as a repo so AI agents can handle long runs without repeating mistakes.

What a Riemann Hypothesis Proof Claim Means for AI Self-Improvement
A mathematician says Claude helped crack the Riemann hypothesis. Here's why that claim matters for AI accelerating its own research.

ChatGPT's Dictation, Dots, and Credit Card Features, Explained
ChatGPT is quietly rolling out visible dictation transcripts, an expanding 'dots' voice interface, and card-saving tools. Here's what's actually changing.

Did Claude Really Solve the Riemann Hypothesis? What We Know
Levent Alpoge says he and Claude proved the Riemann Hypothesis in six weeks. Here's the claim, the evidence, and what's still unverified.

How to Become a Forward Deployed Engineer: 2027 Career Roadmap
A practical roadmap to becoming a forward deployed engineer, covering the skills, salary range, hiring companies, and steps to land the role.

Forward Deployed Engineer Salary: What OpenAI, Anthropic & Others Pay
Forward deployed engineer salary data from 200 job postings at 24 AI companies, including OpenAI's $325K base and typical total pay ranges.

Hy4 Flash: Inside Tencent's 220B MoE Model Built for Cheap Speed
Tencent's Hy4 Flash pairs a 220B-parameter MoE design with Engram embeddings and DFly2 decoding to cut inference cost sharply.

Hy4 Flash API Pricing: What Tencent's Model Actually Costs
Hy4 Flash API pricing explained: per-token rates, the half-price Cloud Token Hub promo through year-end, and how it stacks up on cost per task.

Inkling 2 Mini Benchmarks: How It Stacks Up Against Rivals
Inkling 2 Mini's SWEBench, Terminal Bench and FrontierCode scores compared against Gemma 4 31B, Qwen3.8-27B and Nemotron 3.5.

Inkling 2 Mini Benchmarks: How Thinking Machines' Open Model Scores
Inkling 2 Mini posts strong SWE-Bench and coding scores for a 26B MoE model. Here's how it stacks up against Gemma 4, Qwen, and Nemotron.

Inkling 2 Mini: Run Thinking Machines' Open Model Locally
Inkling 2 Mini is a 26.4B-parameter open-weight multimodal model from Thinking Machines Lab, runnable locally on a 32GB Mac or DGX Spark.

How to Run Inkling 2 Mini Locally on a Mac or DGX Spark
Inkling 2 Mini is a 26B-parameter open-weight model that fits in 20GB. Here's how to run it locally on Mac, DGX Spark, or GPU.

Microsoft Aion 1.0 Instruct: The Small Language Model Headed to Windows
Microsoft released Aion 1.0 Instruct, a 2.3B-parameter on-device model set to become the Windows OS SLM by January 2027. Here's what's inside.

Microsoft Aion 1.0 Instruct: Run Windows' Future SLM Locally Today
Microsoft's 2.3B-parameter Aion 1.0 Instruct model previews Windows' on-device AI. Here are its specs, benchmarks, and how to run it now.

Microsoft Aion 1.0 Instruct: A 2.3B On-Device Model Built for Windows
Microsoft's Aion 1.0 Instruct is a 2.3B parameter on-device model with 32K context, built to become the next Windows OS SLM.

Microsoft Decision 1.1: A Gemma Fine-Tune Microsoft Didn't Mention On Stage
Microsoft's Decision 1.1 model beats Google on decision benchmarks, but it's quietly fine-tuned on Google's own Gemma 4 model.

Microsoft Ignite 2026: Why the Copilot Harness Beats the Models
Microsoft Ignite's models grabbed headlines, but the real story is Copilot Fusion's router and Foundry's harness strategy outshining them.

MiniCPM M1 1105: Does a 350M Model's Thinking Dial Actually Work?
A 229MB reasoning model with five thinking levels was tested locally on sarcasm, texting, and battery math. Here's what the dial actually changed.

MongoDB Atlas Agent Engine: Guardrails, Memory, Observability Explained
MongoDB Atlas agent engine bundles permissions, human-in-the-loop, network limits, memory and observability for LangGraph agents in one deploy.

Shared Skills Repos: How Multi-Agent Teams Avoid AI Merge Conflicts
Why teams should store AI skills and project knowledge in a shared repo instead of letting each person build their own agent setup from scratch.

Compactify API Pricing: Running GLM 5.3 and Quasar for Less
How Multiverse Computing's Compactify API prices GLM 5.3 and its Quasar model, and what that means for agent running costs.

Google Project Genie: What Is the AI World Model and How to Try It
Google's Project Genie turns text prompts into playable 3D worlds generated in real time. Here's what it is and how to access it.

Project Genie Pricing: What It Costs to Access Google's World Model
Project Genie requires a Google AI Ultra subscription near $100/month plus regional access via labs.google/fx. Here's what that gets you.

PxPipe: How Turning Context Into Images Cuts Coding Agent Costs
PxPipe is an open-source proxy that renders coding agent context as images to cut input token bills, but only some models can actually read the pages.