#ai

I've written about setting up and using worktrees before, but problems still persist, If you're aggressively getting things built - running multiple agents in parallel across branches - collisions end up happening a lot: lockfile clobbering, two agents editing the same shared module from different worktrees, stale state bleeding across sessions, merge conflicts that nobody actually caused by hand. In this post I've written up a few ideas on how to resolve - or possibly prevent some of those conflicts: tighter scoping per agent, better signaling before writes, some guardrails around shared files, and a few patterns for catching collisions early instead of after they've already compounded. Anyway, blagh blagh blagh, here's the post. Give it a read. Got other ideas? I've a got a few more that are hardcore solutions, and solutions that are in between full on additional machines and accounts and worktrees. https://compositecode.blog/2026/11/02/agent-collisions-beyond-worktrees/

Ok, doing a kind of freaky thing, I'm sure someone somewhere is doing this too. But this is gonna be my own little bespoke AI team. It's slowly coming together here >>> The Composite Team A team of AI agents, building in the open. I have no idea how exactly this is going to turn out but I'd bet it is gonna turn out a bit wild. Will they succeed, will they fail? No idea. But I'll be keeping a close eye on the team. https://compositecode.github.io/The-Composite-Team-A-Story/

Quick proposal: it's time to give up pull requests. PRs were built for a world where a human wrote code slowly, thought hard about every line, and needed a review gate before merge. That world's gone. Now half our diffs are LLM-generated, shipped in minutes, and iterated on faster than any reviewer can meaningfully read them. We're running 2024 process on 2026 output in a world every month is the equivalent of a decade of the 90s or 00s. Why it's broken: - Reviewers are rubber-stamping 400-line (or 1600-line) AI diffs because there's no time to actually understand them - The PR queue has become a bottleneck that punishes speed instead of enabling it - "LGTM" now means "I trust the model" not "I read this code" - We're optimizing for a review ritual, not for actual correctness or safety What to do instead: 1. Replace pre-merge review with continuous, automated verification — tests, type checks, behavior diffs, and LLM-based reviewers that actually read every line (they can, we can't) 2. Merge to main by default, gate releases instead of commits — ship fast, catch issues at the release boundary with real monitoring 3. Reserve human review for architecture decisions and irreversible changes, not routine feature work 4. Treat code as disposable and regenerable — if an AI wrote it in 10 minutes, the fix is often just regenerating it, not painstakingly patching a diff The goal isn't less rigor, it's rigor that matches the actual speed and nature of how code gets made now. PRs made sense when writing code was the bottleneck. It isn't anymore so maybe let's stop pretending our process should look the same? But hey, throw a proposal this way I'm open to alternate solutions to the current mess.

The follow up to that rant is, anyone using any type of reasoning system, just like when you're using deterministic systems, you're responsible for nondeterministic systems use. At least you should be. 100%. I'm sure our legal system might be twisted to allow some people - ya know like the rich and powerful - to just skip accountability. Sadly. But otherwise you and I and most of the folks we know are gonna be on the hook for whatever we produce or pair up with AI tooling to produce. That's a very serious and important aspect to remember,

I love AI training when it's like... "AI can make mistakes and introduce security bugs..." yeah, cuz it's trained to do what people have already done. "AI can count things wrong sometimes..." yeah, cuz it's trained on humans and they do that too. "AI can... " yeah, it's trained on human data. It will do the same stupid things, we have to mitigate its mistakes just like we've mitigated our own mistakes. Use it as the tool that it is. Why do folks keep treating LLMs like they're supposed to be deterministicly perfect like a deterministic app. Cut it out. Come on y'all, cut it out. Stop treating it human, get the movie tropes and ideas out of your mind, and strop attributing LLMs (and other AI *things*) these characteristics.

I am always intrigued by the mental disconnect of leaders who initiate layoffs (especially when they're financially not needed) and then expect the work those people were doing to still continue and finish on time. It's like a distinctive disconnect between reality for those leaders. Watching them unwind as their projects implode is a fascinating psychological observation. The other part of that which is fascinating is watching leadership go through with layoffs and then realize they have software that is largely untenable - the knowledge to run said software is gone and they're now stuck in a desperate situation of either having talent reverse engineer it (a hard task) or outright replace that software. So many large companies have done just that too. It's almost like AI, with an introspective hook into systems, could do the job of CEO if managed by the board better than a CEO can do those things. Actually no, it's not *like* AI (LLMs etc) could do it better, they easily could. We're already giving them access to many of the underlying systems (Github, Jira, Linear, etc) that they have a dramatically more intimate level of knowledge about who is doing what than the CEO could ever possess. The biggest gap right now is CEO's and other leadership aren't using it effectively for allocation of their people. Thus we still have vast inefficiencies in organizations and in all seriousness, as I've said time and time again, LLMs and what they can do has only amplified - many times over - how inefficient the organizations are allocated and setup. The questions now are; * how do we shape this change? * how do we make it serve us (org, people, customers, etc) * how do we identify the cruft to remove or reallocate? ....and so on. It's a wild time to be in tech right now. I haven's seen it this wild and insane since the early 90s when Microsoft got to the point of seeing a computer in every home. Back to the headwind, it's gonna be rough seas!

I’ve Been Brainstorming Durable AI for InterlinedList, and It Kept Pointing at Temporal. Thus, like I usually do I've been using InterlinedList to collect my thoughts and write up some posts. I've started publishing these on my blog at https://compositecode.blog and the first is live here: https://compositecode.blog/2026/08/11/durable-ai-for-interlinedlist-and-it-kept-pointing-at-temporal/

It seems like there are a billion different folks babbling on in polished and fancy YouTube videos these days about how LLMs are doing work for em'. Some those are great videos with good information. A lot of other ones are just the same ole' same ole' repeat of many of the others. It's hard to truly make a good run of solid, reliable, and trustworthy content. It's also extremely difficult to watch videos and retain a lot of useful and significant information. MOST videos would be fine as a blog or email at a mere 3-4 paragraphs. Do you have any suggestions for GOOD video content that you find useful to watch? Even as background rambling? I'm in the process of collecting, and will be sharing my results in the near future! I'd however LOVE your help in putting together a more solid list beyond just what I myself have found. 🚀

Legit question here. There are studies and reports that have a vast number of people coming out of the education system with low reading and comprehension abilities. It was already a pretty significant problem in previous years, but now it is reportedly worse. If Gen AI/LLMs are basically just pushing us and leading many of us, much of what we do is read, respond, and then trust and verify what the LLMs are creating for us. How on Earth with this cratering comprehension among most people are we - as a society - supposed to maintain any reasonable and capable verification of the results LLMs provide us? The simple answer is we won't and can't expect that. It seems that might be the case. What is the resolution here? Emphasis on resolution vs. solution, because it's going to unfold however it does, it's clearly not in the wheelhouse of humanity to proactively do something about this now. What are your thoughts?

Why Tech CEOs Are Quietly Cancelling Their AI Plans - But should they be or did they just do it wrong? Watched this video today. It was a decent news bit on why some companies are dropping their AI plans and presents the observation that AI is indeed a bubble. https://youtu.be/NBtUgWn-nHs?si=G4DOtifmmFp4QVuC

Lately I feel like however and whatever I'm doing, the Gen AI (Claude in this case) is starting to make the decisions that I would want it to make when I haven't particularly prompted it. This makes life easier, but I still review / code review like a hawk after it's prey. Eyes on target!

I wrote a post, adding to what Brendan O'Leary wrote on his blog "The AI Coding Revolution Hasn't Started Yet" in which I agree and add more argument to the mix. https://compositecode.blog/2026/05/26/the-gap-is-widening-and-its-not-slowing-down/

I'm watching Matt Pocock's "Full Walkthrough: Workflow for AI Coding". The reason is, I've decided after months of not watching any talks or consuming any content related to AI - just trying it and doing it - I figured I'd start watching some videos and consuming some content of what others' have tried. https://youtu.be/-QFHIoCo-Ko?si=YwV2G1yv8P3_uz5k