iiinova — where your digital self keeps evolving

Michael Bleigh @mbleigh.dev · 28/09/2026

Unpopular opinion: plan mode is still good and correct. Now that models are more powerful and do longer horizon work it's more important to be aligned up front. A dedicated plan artifact is easier to read and review than inline chat content.

030

Michael Bleigh @mbleigh.dev · 27/09/2026

I would estimate a high percentage of all software (80%+) would be totally fine with only automated reviews. Because 80%+ of software written is relatively low risk or changes are easily reversible. AI can free us to focus on the changes that actually do need expert attention.

120

Michael Bleigh @mbleigh.dev · 22/09/2026

It used to be that incomplete software was simply missing many things that needed building. Now incomplete software has all the pieces, but the pieces are bad (i.e. slop). Finishing a project is becomes more about removing bad ideas and polishing good ones. This isn't good or bad, just different.

020

Michael Bleigh @mbleigh.dev · 20/09/2026

I'm seeing SO MUCH Jev in my feed. My theory is this: most people don't want to train models, they want to build things. So just like how LLMs broke through to the mainstream because they didn't need to be trained to be useful, such is true for Jev and classification tasks.

010

Michael Bleigh @mbleigh.dev · 20/09/2026

When AI builds an interface.

0171

Michael Bleigh @mbleigh.dev · 19/09/2026

It's been an interesting change of perspective to be thinking about developer tools in a world where I don't expect developers to hand-write a single line of code.

150

Michael Bleigh @mbleigh.dev · 11/09/2026

It's amazing how frequently "AI did this really stupid thing" turns out to be "I gave AI a poorly-specified prompt and it made different assumptions than I expected". Current models are (usually, not always) good at following instructions if you give them good ones to follow.

011

Michael Bleigh @mbleigh.dev · 09/09/2026

Hot take: trying to be more careful about merging AI code is the wrong long-term approach. The better approach is to eliminate one-way doors and make most code more disposable. Sloppy code can be polished/replaced so long as you keep reins on API surface and storage schema.

010

Michael Bleigh @mbleigh.dev · 05/09/2026

I genuinely think the demand for tokens is effectively infinite and is bounded only by cost constraints. We will build legions of automatons that are experimenting, tweaking, optimizing, reviewing, condensing, and making sense of the universe of information 24x7x365.

110

Michael Bleigh @mbleigh.dev · 04/09/2026

AI code is like water: it will slosh around to fill whatever container it's poured into. If you don't provide any constraints you're going to end up with a big mess on the floor. The new job of software engineering is to specify verification+guardrails that hold the water.

020

Michael Bleigh @mbleigh.dev · 03/09/2026

An unintuitive thing about design docs: a doc that is clearly written but wrong on the substance is better than a doc that is hard to read but flawless on the substance. Design docs are communication tools to align humans. You can win at design but fail at design docs.

111

Michael Bleigh @mbleigh.dev · 26/08/2026

What we need as a companion to WebMCP is WebACP that lets me bring an agent of my choosing into the browser. I don't need my agent to build a browser and I don't need my browser to build an agent. I need my agent in my browser.

010

Michael Bleigh @mbleigh.dev · 20/08/2026

The primary artifact you need during design for agent-first development is a list of invariants. "Here's what absolutely must be true about the final result." This will often include a mix of concerns and will often include specific API contracts, specific test scenarios and expected outcomes, etc.

110

Michael Bleigh @mbleigh.dev · 17/08/2026

Doing crazy esoteric stuff in Go: 3 stdlib calls Doing dead basic stuff in Rust: 3 crate installs

010

Michael Bleigh @mbleigh.dev · 11/08/2026

As companies grow, they build processes that leave no room for judgment calls. The default posture becomes oriented around fear of idiot / bad-faith actors, putting a huge tax on good-faith actors who have a good reason to do something a little bit risky. It destroys velocity.

031

Michael Bleigh @mbleigh.dev · 10/08/2026

Agents' overeager coding makes us all into editors. The PR is ready not when there's nothing left to add, but when there's nothing left to take away.

020

Michael Bleigh @mbleigh.dev · 15/07/2026

Not supporting Cmd/Ctrl+Click to open new tabs on navigation is the usability papercut that most frequently sends me into a state of barely-contained rage when using an app.

020

Michael Bleigh @mbleigh.dev · 07/07/2026

Bigcos love to add approvals to everything without considering desensitization. Any individual has limited "pay close attention to thing I'm approving" bandwidth. The more often approval is required, the less carefully each review is performed. Rubber stamps become the norm.

010

Michael Bleigh @mbleigh.dev · 22/06/2026

If you *actually* care about the security of your platform you have to also care about usability. If it takes 35 steps for users to do the right thing and 3 to do the wrong thing, you are incentivizing bad practices. The "pit of success" is hardest to construct for security.

010

Michael Bleigh @mbleigh.dev · 16/06/2026

How has Apple been allowed to get away with the absolutely dismal quality of file search on Mac? It literally couldn't find a folder called "records" in my Downloads folder when I searched for "records".

020

Michael Bleigh @mbleigh.dev · 16/06/2026

"How does the harness handle long-running shell commands" turns out to be I think the most consequential question for overall satisfaction for me personally. Antigravity actually nails this. After a short timeout, the command goes into the background and retriggers on complete.

110

Michael Bleigh @mbleigh.dev · 11/06/2026

Agentic coding is a ladder, and I think it's most effective to climb it one rung at a time. Loops are very powerful but if you try to jump straight there without first understanding both interactive and unsupervised agentic tasks you're not going to build effective loops.

100

Michael Bleigh @mbleigh.dev · 03/06/2026

One pattern I find myself reaching for frequently these days is to gather data into a heavy JSON "kitchen sink included" format and then build lightweight CLI renderers that slice and dice the data into various token-efficient text views for an agent to understand.

000

Michael Bleigh @mbleigh.dev · 16/05/2026

My new bar for onboarding is "give me a prompt I can paste into a halfway decent agent that gets me completely set up and onboarded to your service with no prior knowledge of how anything works". Results are graded on a scale of how much work I have to do instead of my agent.

220

Michael Bleigh @mbleigh.dev · 15/05/2026

3 things every LLM API ought to have knowing what we know now about building agents: 1. Allow add'l function defs without busting prefix cache 2. Interleaved "developer" messages with stronger instruct weight 3. Canonize XML-tag-ish structure into first-class "section" primitive

000

Michael Bleigh @mbleigh.dev · 12/05/2026

Every social media service needs: 1. A "slop" button that is a combination user mute and report of a post as being low-quality. 2. ToS allowing discretionary banning of users for automated low-quality posts. Right now slop replies are clearly rewarded. They need to be punished.

120

Michael Bleigh @mbleigh.dev · 07/05/2026

My tolerance for systems and services that don't have simple CLI / API access is falling to zero extremely fast. I expect we'll start seeing startups that build a CLI and MCP server. Who's already doing that?

320

Michael Bleigh @mbleigh.dev · 20/04/2026

I wanted to play around with building a personal agent for my family and the process of getting working credentials to talk to a chat app is...next to impossible? Is there some secret shortcut to doing this that doesn't require me to register an LLC or something?

210

Michael Bleigh @mbleigh.dev · 13/04/2026

I think the most common frustrating architecture decision I run into is: - To do X (thing we want to do a lot, like define a new tool for an agent) - You need to add code to Y, Z, A, and B Features that need to scale should have vertical consolidation of their definitions.

000

Michael Bleigh @mbleigh.dev · 06/04/2026

An interesting thing about the AI era is you no don't need humans to figure out "how" or "what". New to a codebase and need to trace a code path or discover relation between components? Ask an agent. Now most questions to my teammates are about rationale or judgment - the "why".

000

Michael Bleigh @mbleigh.dev · 19/03/2026

Google Wave is a pretty perfect conceptual interface for AI + multiplayer human collaboration.

2100

Michael Bleigh @mbleigh.dev · 02/03/2026

Find someone who loves you as much as Gemini loves filling in `gemini-1.5-pro` as the model name for everything.

000

Michael Bleigh @mbleigh.dev · 01/03/2026

This is the most resonant definition of slop I've seen: "It’s when we prioritize volume over impact." Because this accurately captures the things that are slop but not AI (SEO farms, bad genre fiction, a whole ton of kid YouTube...).

seths.blog

AI slop

It’s not slop because it was created by an AI. It’s slop because it’s slop. I just read the first two pages of a sci-fi novel on my Kindle. The author proudly proclaims that the 4…

120

Michael Bleigh @mbleigh.dev · 28/02/2026

Is it weird to say that coding with agents feels more...organic? It feels more like tending a garden than building a house. You plant seeds (write specs), water them (poke it along), pull weeds (refactor messes). It's a different skillset but very informed by existing knowledge.

4543

Michael Bleigh @mbleigh.dev · 26/02/2026

With Cloudflare forking Next.js and tldraw yoinking unit tests from their public repo, it seems like something significant is happening in open-source this week. We're entering the age of the Slop Fork.

mbleigh.dev

Welcome to the age of the Slop Fork

Open-source libraries with extensive test suites can now be autonomously cloned into competing implementations. What will it mean for open-source?

120

Michael Bleigh @mbleigh.dev · 20/02/2026

If you're a library author, it's a pain to figure publish agent skills in a way that your users will actually see. If you're a developer using libs, it's a pain to make sure you're using the best and latest agent guidance for them. Let's solve it! I'm proposing .agents.lib

242

Michael Bleigh @mbleigh.dev · 15/02/2026

Engineers dunking on Claude Code's memory usage or perf are really telling on themselves. Claude Code went from zero to $2.5B run rate business in a year. Every engineer should aspire to such colossal success and impact of their work. You can optimize later. Win first.

010

Michael Bleigh @mbleigh.dev · 14/02/2026

I use this prompt far more often than I'd like to admit: "I've done a bunch of work without properly breaking it into small commits. Please look at the current state and do some incremental commits. Each commit must have tests passing." That being said, it works pretty well!

030

Michael Bleigh @mbleigh.dev · 10/02/2026

Has there ever been a successful company that launched itself by buying an incredibly expensive domain name or a superbowl ad? Because all I can think of are abject failures and it's surprising the lesson doesn't get learned by either founders or their investors.

000

Michael Bleigh @mbleigh.dev · 09/02/2026

It feels like a glaring oversight that, despite inventing MCP, Anthropic did not work to incorporate either hooks or skills into MCP when it would obviously fit, help standardize, and solve a bunch of problems.

000

Michael Bleigh @mbleigh.dev · 01/02/2026

For some reason I can't stand tab completion in AI coding. If I'm actually touching code these days, it's because I have specific stuff I want to do and I need language server autocompletions not LLM guessing.

020

Michael Bleigh @mbleigh.dev · 28/01/2026

Companies with eccentric bespoke build systems have shot themselves in the foot in the AI era since these types of problems in particular hamper the "write, check, fix" inner loop that agents need to successfully build software.

011

Michael Bleigh @mbleigh.dev · 26/01/2026

The difference between "too early" and "too late" in the AI era is ~2 months.

000

Michael Bleigh @mbleigh.dev · 03/01/2026

I'm not sure any TV series will ever have as ruinous of ending as Game of Thrones. This is largely because few shows will ever be as good as it was at its peak. It took really special circumstances to be that good and then fumble that hard.

010

Michael Bleigh @mbleigh.dev · 30/12/2025

TIL that XXL and 2XL are in fact not the same size and I'm still reeling.

020

Michael Bleigh @mbleigh.dev · 29/12/2025

The real way that the ultra-rich avoid paying their share of taxes is by being able to borrow cash at extremely low interest rates secured by illiquid assets, thus being able to realize the benefits of liquidity without triggering capital gains. Fix that, don't do wealth taxes.

110

Michael Bleigh @mbleigh.dev · 09/12/2025

My contrarian awards season take is that 28 Years Later deserves to win "Best Original Song" for "Boots". It's grating and unpleasant but one of the most effective auditory cinematic experiences I've ever had. Truly makes my skin crawl. Oh wait, but Sinners also deserves it...

000

Michael Bleigh @mbleigh.dev · 09/12/2025

The best outcome for AI is a no-clear-winner ecosystem where there are dozens of different agents forced to interoperate via standards like MCP. Such a result would keep pressure and incentives towards open, hackable systems like Web 1.0 and less like app store walled gardens.

210

Michael Bleigh @mbleigh.dev · 05/12/2025

Pluribus is maybe the best high-concept writing of all time. It takes an inherently captivating premise: "What if a hivemind took over nearly all of humanity overnight?" and layers on an incredible answer to the question of "And why don't they just kill the remaining outliers?"

120

Michael Bleigh @mbleigh.dev · 01/12/2025

I dislike AI writing slop much more than other forms because there's no transformation of intent, only bloat. Media gen: transform language to visuals Code gen: transform language to behavior Text gen: transform language into puffed-out language It literally just wastes time.

100