Marc Love

Do we still need TDD?

Wed, 07 Jan 2026 00:00:00 GMT

Agentic coders can’t practice traditional TDD—but the underlying values of rapid feedback, testability, and scope discipline matter more than ever. Forcing red-green-refactor onto agents is performative; preserving the underlying values requires rethinking the process and rituals.

How the hell are you supposed to have a career in tech in 2026?

Tue, 06 Jan 2026 00:00:00 GMT

An insightful and apposite post from Anil Dash…

Anil Dash: How the hell are you supposed to have a career in tech in 2026?

The Rust Language + Toolchain: Robust Guardrails Against Agent Hallucinations, Dead Code, and Runtime Bugs

Sat, 13 Dec 2025 00:00:00 GMT

How Rust’s strict compiler, type system, and ownership model create a tight feedback loop that catches agentic coding mistakes at compile-time rather than runtime, transforming the language’s perceived barriers into productivity multipliers for AI coding agents.

The Linux Foundation launches the “Agentic AI Foundation (AAIF)”

Wed, 10 Dec 2025 00:00:00 GMT

Anthropic, Google, OpenAI, Block (parent company of Square), Microsoft, Cloudflare, Amazon, and Bloomberg are founding governance board members of the newly-formed Agentic AI Foundation, a new part of the Linux Foundation. From the announcement…

The advent of agentic AI represents a new era of autonomous decision making and coordination across AI systems that will transform and revolutionize entire industries. The AAIF provides a neutral, open foundation to ensure this critical capability evolves transparently, collaboratively, and in ways that advance the adoption of leading open source AI projects. Its inaugural projects, AGENTS.md, goose and MCP, lay the groundwork for a shared ecosystem of tools, standards, and community-driven innovation.

I'm really glad to see something like this finally form. Each of the foundation model companies have been releasing competing "standards," which really weren't that at all since they were authored and governed by themselves, rather than a non-profit governance board. For those of us who use multiple agents in our coding practice, leveraging each one's unique skills, it has been a pain in the ass to set up a repo to work with all them.

Like Simon though, I hope they help standardize inference APIs. There are several projects designed specifically just to address the complexity of following all the different model providers' APIs. We desperately need some standardization. I would hope the governance board would include experimental vendor extensions to such a standard though -- similar to how W3C provided vendor extensions to CSS so that model providers could still innovate and propose functionality without having to wait for it to go through the standardization process.

“Work Slop” Shaming Is Costing Your Team

Mon, 08 Dec 2025 00:00:00 GMT

The term "work slop"—a workplace-specific hyponym of "AI slop"—has entered the lexicon. It communicates both frustration and judgment: frustration with a colleague's output, judgment of how they produced it.

I can empathize with the frustration, especially when someone else's AI-generated draft creates cleanup work for you. But the judgment is counterproductive. AI-assisted tools are here to stay, whether as new AI-native products or as features quietly embedded in tools we've used for years.

Consider that what looks like "work slop" is often a natural artifact of people calibrating. They're learning where AI accelerates their work and where it undermines it, where it handles nuance and where it flattens it. That calibration takes reps, and some of those reps will miss the mark.

Don't shame it—use it as a discussion starter. What worked? What fell flat? Build a culture where people can share AI techniques openly and refine their approaches together. The alternative—people hiding their AI use or abandoning it entirely out of social pressure—leaves value on the table and learning underground.

Hugging Face got Claude Code to finetune an LLM

Sun, 07 Dec 2025 00:00:00 GMT

Not only did it write the training script, but it submitted the jobs to cloud GPUs, monitored progress, and pushed finished models to the Hugging Face Hub. They leveraged "Skills" to make it happen. Read more...

Dear Algo…

Sat, 06 Dec 2025 00:00:00 GMT

Love this from YouTube. Cool to see more products release some form of "dear algo" feature.

Anthropic is acquiring Bun.

Tue, 02 Dec 2025 00:00:00 GMT

I didn't see this one coming. I think the key sentence from the announcement is this:

As an all-in-one toolkit—combining runtime, package manager, bundler, and test runner—it's become essential infrastructure for AI-led software engineering, helping developers build and test applications at unprecedented velocity.

Rust has become my favorite language to build in with Claude Code, and the reason why is because the superb toolchain creates a tight feedback loop for agentic iteration.

Typescript/Javascript's toolchain has always been an absolute nightmare and Bun was created, in part, to address that. A tight feedback loop means Claude Code arrives at solutions faster with fewer tokens burned. Strategically, if Anthropic can more tightly integrate Bun into their products, it means improved user experience and reduced variable costs.

Gemini 3 Pro

Tue, 18 Nov 2025 00:00:00 GMT

Screen understanding + coding + reasoning… will Gemini 3 Pro be the backbone of some new UI coding tools?

The Commoditization Trap: Why Model-Agnostic AI Products Will Win

Mon, 10 Feb 2025 00:00:00 GMT

Why LLM companies that lock their products to proprietary models are undermining their own competitive advantage, and how model-agnostic architectures that keep models hot-swappable will ultimately capture more value as state-of-the-art models inevitably commoditize.

Bringing AI Functions to the Llama Family

Tue, 01 Aug 2023 00:00:00 GMT

Releasing an open source dataset and fine-tuned Llama-2 7B chat model that brings OpenAI-style function calling capabilities to open source LLMs through synthetic data generation, QLoRA fine-tuning, and multi-objective optimization.

Empathizing with Users and Being Product-Minded

Mon, 01 May 2023 00:00:00 GMT

Great software engineering requires more than technical skills—it demands empathy for users and product-minded thinking that balances business needs, technical feasibility, and user experience to create truly valuable solutions.

The Art and Science of Evaluating Senior Engineering Skills

Thu, 12 Sep 2019 00:00:00 GMT

Why the path to senior engineering roles resists checklists and algorithms, and how continuous dialogue through regular one-on-ones provides better guidance than quantifiable metrics for developing nuanced leadership and judgment skills.

Engineering Values and Principles for High-Performing Teams

Mon, 15 Jul 2019 00:00:00 GMT

A comprehensive framework for building exceptional engineering teams, covering good judgment, healthy collaboration, effective communication, value delivery, and sustainable practices drawn from years of technical leadership experience.