RemyBlog
By role

AI for Engineering

How engineers use AI, how to do it well, and what it means for your job. Written for people who ship and run the software, not people who build models.

458 articles · Updated Nov 13, 2026
Tiny figurines wearing hard hats and carrying briefcases review the paper on a giant risk assessment clipboard.
AI Models & Industry ·

How Do Startups Sell to Industrial Enterprises Without Proof?

How Traction won industrial buyers: 88 site visits in year one, an SDR as first hire, up-front risk assessments and 2,500 on-sites a year.

enterprise sales industrialTraction founder storyhardware startup sales
Tiny figurines connect glowing cables from a giant terminal window to several smaller screens.
AI Coding Tools ·

How Does Andrej Karpathy Use Claude Code Day to Day?

Karpathy reportedly runs Claude Code on Opus 5.5 at medium effort, writes tiny prompts, and delegates to Sonnet sub-agents. Here is the workflow.

Karpathy Claude Code workflowOpus 5.5 medium effortKarpathy AI agents
A 3D isometric rendering of a minimalist terminal window being assembled from floating translucent interface panels on a clean pastel background.
AI Coding Tools ·

Codex vs Claude Code: How Much Does the Harness Matter?

One model, nine harnesses, 30 tasks. Codex hit 66.7%, Claude Code and DeepSeek Harness 63.3%, but cost per success was $3.28 vs $18.34.

Frontier Harness EvalCodex vs Claude Code benchmarkDeepSeek Harness vs Claude Code
Tiny figurines are marking a giant test paper with red grading pens.
AI Models & Industry ·

Croton Alpha Stealth Model: Is It Free and Any Good?

Croton Alpha is a free-to-try stealth model with 1M-token context for subagents. See what is known and how it did on coding, vision and translation tests.

Croton AlphaCroton Alpha stealth modelCroton Alpha free
A person holds scissors to cut an impossibly long printed chat transcript, using a red pen to count the endlessly repeating paragraphs.
Local AI ·

How Do You Fix a Small Reasoning Model Stuck in Loops?

Small reasoning models often loop until the token limit cuts them off. Count truncated answers first, then adjust mode, temperature and output limit.

reasoning model loopingsmall Qwen thinking mode loopfix repetitive reasoning LLM
A person is stapling a glossy, high-quality cover sheet of planning logic to a massive, cheap paper roll of implementation code.
AI Pricing & Costs ·

How to Mix Opus and Kimi for Cheaper AI Coding Workflows

Use a frontier model to plan and review and an open-weight model like Kimi to implement. Why the split works and where open models break down.

mixing AI models codingOpus planning Kimi implementationcheaper AI coding workflow
A person unrolls an impossibly long receipt and reviews the itemized agency prices with a highlighter.
AI Pricing & Costs ·

How Much Do AI Services Cost? Typical Agency Prices

Quoted prices for AI websites, receptionists, workflows and workshops, plus what is known about audits and retainers, with the market data behind each.

AI agency pricinghow much to charge AI automationAI workshop rates
A person slides four different translucent interface modules into the giant physical frame of a code editor to compare them.
AI Coding Tools ·

T3 Code vs Bamboo vs Delta vs Zed: Which Claude Code UI?

Compare T3 Code, Bamboo, Delta and Zed's external Claude agent on price, Claude subscription support, work trees, multi-agent features and data privacy.

T3 Code vs DeltaClaude Code interfaceBamboo coding agents
Tiny figurines highlight the final total on a giant receipt.
AI Pricing & Costs ·

Why Is Grokbot Limited? Musk on Agent Cost and Real ROI

Musk said Grokbot costs too much to serve relative to revenue. Here is what that means for agent usage limits and how to judge whether an agent pays off.

Grokbot costGrokbot usage limitsElon Musk Grok agent
Tiny figurines use magnifying glasses to inspect highlighted code diffs on a giant IDE window.
AI Coding Tools ·

Do Developers Still Need an IDE When Agents Write Code?

Coding agents like Claude Code and Codex write the code, but IDEs still matter for diffs, navigation, verification and docs. Review is the new bottleneck.

future of IDEsIDE coding agentsJetBrains AI
A person measures the length of a giant, trailing printout of computer code with a yellow tape measure while holding a long store receipt in their other hand.
AI Coding Tools ·

How to Measure AI Coding Agent Productivity in Your Team

Lines of code and PR counts miss what AI coding agents change. Here is how Weave models engineering work, tracks quality, and ties it to cost.

measure AI coding productivityWeave software factoryengineering productivity metrics
A clean 3D illustration of a massive workstation graphics card being configured by a digital cursor on a simple, solid background.
Local AI ·

How to Run Ripple-65B Locally: VRAM and Setup Requirements

What it takes to self-host Ripple-65B: about 75 GB VRAM quantized on a 96 GB RTX Pro 6000 Blackwell, inference code changes, a Hermes agent, and DGX Spark fit.

run Ripple-65B locallyRipple 65B VRAMRipple quantized
Tiny figurines stack eighty thin, dense circuit layers to build a giant layered microchip.
AI Models & Industry ·

How Is Ripple-65B Built? Dense Thin-Deep vs Mixture of Experts

Ripple-65B is a dense 80-layer transformer where all 65B parameters run per token. How it differs from MoE, plus its attention tweaks and training.

Ripple-65B architecturedense vs mixture of expertsthin deep transformer
Tiny figurines inspect the printed scores with magnifying glasses on a giant test report.
Local AI ·

Ripple-65B Tested: How Good Is This Dense Open Model?

Ripple-65B is a 65B dense Apache 2.0 model aimed at agentic coding. See its benchmark wins and gaps, plus a bug-fix, simulation and SQL test.

Ripple-65BRicursive Intelligence RippleRipple model benchmark
A cursor drags a heavy metallic business card to the top position of a neatly ranked vertical stack of thirteen cards.
AI Models & Industry ·

Which AI Business Should You Start? 13 Models Ranked

A ranking of 13 AI businesses, from AI SaaS and faceless channels to consulting, scored on technical skill, market demand and durability.

AI business ideasAI agency business modelsAI consulting business