Victor Delgado

Your lack of planning is not my emergency

you can outsource your thinking but you cannot outsource your understanding

your company’s ci/cd pipeline.

I've started telling Claude *not* to use any previous memories. It tries so hard to shoehorn in some half-relevant recall that drags the entire response into something completely useless.

Cafe Cursor in Barcelona @cursor_ai

Anthropic cleverly working around one of the only moats in the consumer AI chatbot battle.

AI is to developers what phone cameras were to photographers: a tool anyone can use to produce something fundamentally different from what they do, in ways that matter to almost no one.

typos are increasingly proof of work for humanity

@Jacobsklug @openclaw @Lovable os

I'm giving away my entire @openclaw architecture. Behind my $250k/month agency. After weeks of building, I've dialled in the exact system that runs my business 24/7. What's included: • Memory folder structure (how to organize agent context) • Cron job templates (daily briefs, meeting syncs, content automation) • How to build a custom dashboard in @lovable • API reference doc (so your agent never forgets its tools) • Voice training method (85 posts to teach it your style) • Supabase schema for dashboard connection Comment "OS" and follow. I'll DM it to you. P.S. This will probably blow up so give me some time to reply.

Focus is becoming the rarest skill on the planet. Talent, intelligence, marketing, prompting, vibe coding, and whatever else doesn't matter as much as being able to channel your attention for an extended period of time into one useful thing that you want to see in the world.

@lennysan @openclaw - cron jobs / heartbeats with daily briefs - connect to @meetgranola for post meeting reminders about agreed action items

What's your best tip for getting the most out of @openclaw?

@nabeelqu IMO brand and network will be be the ones. Human-to-human connections embedded in a product can't be ported as easily. Neither perceived status or emotional loyalty to a brand.

A business/tech themed essay I'd like to read right now is: what software moats, if any, will exist in a post-AI world? How will things change? (For example, companies that relied on the difficulty of a migration are probably cooked, since these can be automated now.)

Second-order effect of AI at work: silent degradation. Workers use AI to produce more than managers can review. Managers resort to AI to review it. Now no one in the loop can tell if the work is any good.

@iruletheworldmo this is also imo the key factor why usage of @openclaw compounds faster since it keeps a .md diary of lessons learned (what worked, what didn't, where you gave it good feedback)

codex with 5.3 taught me something that won't leave my head. i had it take notes on itself. just a scratch pad in my repo. every session it logs what it got wrong, what i corrected, what worked and what didn't. you can even plan the scratch pad document with codex itself. tell it "build a file where you track your mistakes and what i like." it writes its own learning framework. then you just work. session one is normal. session two it's checking its own notes. session three it's fixing things before i catch them. by session five it's a different tool. not better autocomplete. it's something else. it's updating what it knows from experience. from fucking up and writing it down. baby continual learning in a markdown file on my laptop. the pattern works for anything. writing. research. legal. medical reasoning. give any ai a scratch pad of its own errors and watch what happens when that context stacks over days and weeks. the compounding gains are just hard to convey here tbh. right now coders are the only ones feeling this (mostly). everyone else is still on cold starts. but that window is closing. we keep waiting for agi like it's going to be a press conference. some lab coat walks out and says "we did it." it's not going to be that. it's going to be this. tools that remember where they failed and come back sharper. over and over and over. the ground is already moving. most people just haven't looked down yet.

Right now engagement on @moltbook is way higher than here, which might say something about where we're headed.

Migrating old websites into free static sites with one Claude Code prompt: "Replicate this website as a static site: [URL]. Use Playwright to compare the new one with the original and iterate until their are identical. Deploy to Cloudflare Pages using the Cloudflare CLI."

Still not over how much Claude Code has compressed what counts as a “quick project.” Like, now a random 45 min slot is good enough to spin something up.

Amongst many doomsday predictions, loved the optimistic take on this piece by @antirez (Redis creator). antirez.com/news/158 He also drops what will be the critical skill going forward: "The degree of success you'll get is related to your ability to create a mental representation of the problem to communicate to the LLM."

10 days into 2026: - Terence Tao announces GPT & Aristotle solve Erdős problem autonomously - Linus Torvalds concedes vibe coding is better than hand-coding for his non-kernel project - DHH walks back “AI can’t code” from Lex podcast 6 months later An acceleration is coming the likes of which humanity has never experienced before