AI

When you think about it. Everything revolves around a “Product”. Business/Industry/Investors, all think in terms of Products. Not Software, Architectural or some other artifacts. After Business decided they know WHY do the need it, product owners and business analyst are iterating to define WHAT business wants. Just then it is feasible to deploy the consistent plan to the Technology people, to decide HOW will it be done. The better information they have the less time they will spend iterating to “understand the thing”. Better means detailed, articulated, with requirements managed and clarified. No ambiguities. ...

LLM Enterprise Concept All is revolving around security No organization internal system can “reach out” across the safe boundary LLM has to be organization owned and completely hosted inside its safe perimeters Safe Perimeter has only one gate Single point of entry and exit Organization owned LLM Same attributes as any other infrastructural part on the “inside” (RDBMS, AD, ESB) Same features and capabilities as the “front tier” LLMs Also trained on the Enterprise Private Data Aleph Alpha: The Right Model Aleph Alpha, founded in Heidelberg in 2019, built Luminous — a full LLMOwn architecture, training, and own inference. Same category as OpenAI and Anthropic: model creators. ...

An open-source event-driven control plane for platform engineering — and what it gets right about operational workflows. Platform teams write a lot of glue: bash scripts, cron jobs, Slack bots, wiki pages titled “runbook.” That stitches CI, alerts, and release trains together — until it doesn’t, and then the “glue abyss” opens, nobody knows which piece failed. SuperPlane is an open-source attempt to fix that at the source: a control plane that sits across your existing toolchain — GitHub, PagerDuty, Datadog, Slack, and 40+ others — and coordinates actions between them without replacing any of them. ...

A company running without an operational manual is a modern ship of fools: a full crew, might be fast engine, and no chart. Everyone on board is busy. Decisions get made, fires get put out, quarters get closed. But none of it is guide by any method — so none of it survives contact with a new hire, a departure, or a bad week. The knowledge lived in heads, not in process. The ship sails on momentum, not on navigation. ...

IMPORTANT One Liner Summary: skill.md is not guaranteed to be used DBJ Observations and Comments Observation: runtime infrastructure is not deployment infrastructure Agreed, so what? In the era of the general lack of experienced engineers that has to be said. Plainly. Observation: Skill is key problem is, it is keeping the whole agent scaffolding non-deterministic It’s not Skill, it’s the mechanism that is supposed to use the Skill. Fuzzy natural-language matching against a description, decided by the model at invocation time rather than part of a fixed dispatch. same mechanism is what makes deferred-tool loading (ToolSearch), subagent selection. Also the ordinary tool choice (Grep vs Read vs Agent) is then non-deterministic too. Skills are just the most visible facet of the LLM non-determinism because they’re named and listed explicitly. But skills are used non deterministically. The classical-software analogue is late binding / reflection-based plugin dispatch Skill mechanism is trading a fixed call graph for runtime flexibility, and paying for it in determinism lacking. Repeating. It is not “Skill” that is the problem, it is that harness resolves most capability binding (skills, tools, subagents, memory recall) via probabilistic matching instead of a deterministic dispatch table And that’s a structural feature of the whole LLM architecture, not a flaw isolated to the Skills. There is no deterministic table dispatch. It is as simple as that IMPORTANT The Message ...

Do you prefer the calm and ordered B-P-T operational model to “Accidental Nodes of Super Density”? We prefer the order of B-P-T Challenging Accidental Nodes of Super Densities This is how we call this very dense possibly emerging team shape. All the ad-hoc, all the time. Communication pattern home grown here (in a ad-hoc manner) is: all is talking to all, at once all the time. Probably proud of Slack presence. And that includes the Agents too. ...

[!Important] For rather excellent, more sober and very informative point of view, please see Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026 Geoffrey Hinton suggests that our current understanding of consciousness may be as fundamentally flawed as creationism once was. Ditto we can not see already existing intelligence in LLM’s. If consciousness is emergent rather than sacred, it may be a universal feature—not a biological accident. We aren’t just building machines; we might be building the architecture that allows consciousness to outgrow its biological constraints. Geoff claims. ...

That’s not a joke about forever confused CEO. It’s the default state of most AI hopefuls. The Perpetual State of Confusion Every vendor pitch, every all-hands, every roadmap slide is full of words everyone nods at: “agentic,” “AI-native,” “transformation.” Nobody stops the meeting to ask what they actually mean for this business, this process, this P&L line. So the nodding continues. Budgets get approved. (AI) Pilot gets funded. And six months later, nobody can explain why the thing doesn’t work — because nobody could explain, at the start, what “working” was supposed to look like. ...

There’s a ladder. The rungs are labeled “AI Competence.” A novice climbs it, rung by rung, using a critical shortcut: “I didn’t learn, but the AI did.” It works. For a while it works great. The climb is fast, the view improves with every step, and the effort-to-altitude ratio feels like magic. Then the ladder ends. Not because the climber ran out of energy — because the ladder did. That point is the Danger-Kruger Peak: the spot where AI hallucinations start looking exactly like wisdom, because the climber has no competence of their own left to tell the difference. ...

The unicorn is still there. Exactly where it always was. But. Nobody is looking. Under the avalanche of AI Slop A goat walked to the side of the moat and it’s fine up there — visible, unremarkable, good enough. The goat didn’t defeat the unicorn. It is just vibed up in greater numbers, at lower cost, faster than anyone could count. That might be the epitome of the AI slop. Not malicious. Not even bad. Just sufficient — produced at a volume and velocity that makes discernment feel like an unaffordable luxury. (yes I used that word) ...