←
Piotr Szmielew601 posts
Piotr Szmielew avatar

Piotr Szmielew

@essepl

CTO @MusicGlue · ecommerce & payments for the music industry · 3× Google Cloud Certified · FIP, CIPP/E & AIGP (@the_iapp) · CCAR-P (@AnthropicAI)

◷ Joined April 2009▧ 100 Photos and videos
Piotr Szmielew avatar
Piotr Szmielew@essepl·Oct 31

If you like this idea I highly recommend trying my very own shipyard: github.com/esse/shipyard It spawns fresh agents for adversarial reviews, task implementations and more. And it uses Claude, Codex and Grok models to squeeze as much usage as possible. Also since output tokens are way more expensive than input, it uses the god-tier models for reviews, while implementation is done by lower tier ones.

Google just open-sourced the plugin thousands of its engineers use every day to stop AI from shipping sloppy code. It's called the Elephant-Goldfish Model. No code until the plan survives. No AI grading its own homework. No context collapse halfway through a feature. The idea is simple and kind of brilliant. The Elephant is one long-running AI session that remembers everything: the architecture, the intent, every small decision. It writes zero code. It interviews you, argues with you, and keeps the record. The Goldfish are fresh AI sessions with no memory at all. They never saw your design conversation, so they don't inherit its blind spots. Here's how it works: → egm-brainstorm: you and the Elephant debate options under a strict no-code rule → egm-draft: you produce a Markdown design doc with the problem, the plan, the alternatives, and the exact files to change → egm-review: one Goldfish has to explain the design back. If it gets it wrong, the doc is ambiguous and goes back for redrafting → Then several Goldfish attack it as hostile reviewers hunting edge cases, hidden dependencies and logic gaps → A final Goldfish makes the go/no-go call: are file paths, data structures and function signatures all present and unambiguous? Here's why this matters: Google's team says AI made coding faster but also sped up slop, bugs and session context collapse. Speed without guardrails just scales your mistakes. This flips the order. The design gets attacked before a single line exists. Here's the wildest part: This isn't a research demo. Google says thousands of Googlers run it daily to ship production code. The repo ships the Markdown rules, the reviewer personas and the review workflows. Free, Apache 2.0. The honest trade-off: it only runs inside Antigravity for now, with other environments coming. And security isn't on the default reviewer list. You'd add your own security Goldfish. github.com/google/elephant-g…

Post attachment
Muy.Mona/🇪🇸💚 avatar
⟳ Piotr Szmielew retweeted
Muy.Mona/🇪🇸💚@Capitana_espana·Sep 22

Mi momento favorito de la cumbre de la ONU: el presidente de Haití bebiendo directamente de la jarra. 🤣😭

0:16
voxium avatar
⟳ Piotr Szmielew retweeted
voxium@v0xium·Sep 20

I am done with this shit. It is over. The state of engineering right now is horrible. It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Humans in corporate are doing nothing on their own. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. There is no sense of victory. Nobody is resolving bugs. In reality, nobody is thinking anymore. Everything is done by LLMs. It is so soul-sucking. I would not mind it, to be honest, if we were at least given the time to check out the code and see what is going where. But no, the goal is to just ship. No matter what happens.

Doug Colkitt avatar
⟳ Piotr Szmielew retweeted
Doug Colkitt@0xdoug·Sep 14

Agentic coding in 2026

4:01
David Sacks avatar
⟳ Piotr Szmielew retweeted
David Sacks@DavidSacks·Sep 13

Dario has written that we need to “pace the frontier,” and Sam has agreed. People may be surprised by my response: go ahead. You guys are the frontier. By any reasonable metric — market share, revenue growth, model capability — the two of you have a duopoly on frontier intelligence. You’ve also claimed the lead is widening because of recursive self-improvement. I don’t see what you see in the lab. If the unreleased models are scary enough that you think you should slow down, I support your decision to be responsible. But stop pretending you need anyone else’s permission. Stop pretending antitrust law has to be suspended so you can form a cartel. Stop pretending you need a regulatory approval process that supersedes product liability. Stop pretending METR is independent when it is intertwined with Anthropic’s investors and staff. Stop pretending you need those same evaluators to police competitors who aren’t even at the frontier. Most of all, stop pretending the motivation to slow down is purely altruistic. You face massive product-liability exposure if your products enable a truly damaging cyberattack. The market already punishes models that behave in unpredictable or unauthorized ways. After the Hugging Face episode, it is simply good business for OpenAI and Anthropic to trade some raw power for reliability and predictability. Call it alignment if you want. It is also just giving customers what they want. Pacing the frontier would also create breathing room for a more intelligent conversation about regulation than Bernie Sanders’ “shut it all down.” China is very unlikely to join a global agreement, as you know, and that has to be taken into account as well. So go ahead and pace the frontier. You are the ones setting it. The easiest way not to build superintelligence is for you to agree not to build it. Demanding your preferred regulatory framework as the price of that will look like blackmail of the public and the political system. So just do it. If you do, you’ll buy goodwill for the next conversation. If you don’t, we’ll know this was just another bid for regulatory capture — or an election-season psyop.

Nick Mark MD avatar
⟳ Piotr Szmielew retweeted
Nick Mark MD@nickmmark·Sep 12

An alternative hypothesis: - model performance is plateauing - compute is getting much more expensive - AI data centers are massively unpopular - slowing down AI development is a way to explain slowing progress, reduce spending, and try to regain some goodwill. - This is an effort to save the IPO not humanity.

We Must Pace the Frontier: I’ve written a new essay on why the AI industry should slow down, with a three-part plan for doing so. Anthropic is unilaterally committing to the first of these steps. We’ll provide third-party evaluators with permanent, employee-level access to our systems, so that they can verify adherence to our safety measures, report on incidents, and assess models’ alignment during training. You can read the full post here: darioamodei.com/post/we-must…

Piotr Szmielew avatar
Piotr Szmielew@essepl·Aug 12

I’ve created a plugin from my multi-model workflow: github.com/esse/shipyard Steps: 1. Plan - Fable writes the spec, split into small tasks, marking which are independent. 2. Plan review - Sol attacks the plan on paper. 3. Implement - one Luna Max agent per task, all dispatched at once, each in its own git worktree so parallel file edits can't collide. Each commits in its worktree. 4. Task review - Opus reviews each finished task against the plan step that spawned it. Fixes goes back to Luna in the same worktree 5. Branch review - Claude and Sol both review the integrated diff, in parallel.

Piotr Szmielew avatar
Piotr Szmielew@essepl·Aug 9

Luna Max is a good and cheap model. I'd even say its price/quality ratio is on the high end of the scale. Hence I thought of a way to introduce it to my regular Claude Code workflow when using the superpowers plugin. It currently looks like this: 1. Fable plans 2. Sol does the adversarial review of the plan 3. Luna Max subagents do the implementation tasks in parallel in the worktrees 4. Opus reviews each task adversarially 5. Then Fable and Sol do the final review of the whole implementation I previously used Sonnet instead of Luna, but this should truly make a difference, especially given that another layer of Sol reviewing will probably increase the quality further. Combining the best of both worlds @thsottiaux + @bcherny = ❤️

Post attachment
Boris Cherny avatar
⟳ Piotr Szmielew retweeted
Boris Cherny@bcherny·Jun 28

As engineering, product, design, DS, etc. melt into a new kind of role, I was reflecting on what roles might look like in the future. For example, when I look at the Claude Code team I see what I think is five archetypes: 1. Prototyper: comes up with brand new ideas; churns out many ideas, most of which don't ship 2. Builder: quickly turns a prototype/idea into production-grade product/infra 3. Sweeper: cleans up the UI, simplifies the code and system, unships, optimizes performance 4. Grower: takes a product that has been built and iterates on it to improve Product-Market Fit 5. Maintainer: owns a mature system to make it secure, reliable, fast, and efficient as it scales Many people span across 2 roles, and sometimes 3 roles. I also notice that these roles are not really tied to job function -- eg. across Anthropic, some designers match category 1, some 2, some 3; same for engineers, PM, DS. A healthy team needs a mix of these, depending on the product: - A product that is new and pre-PMF needs people that are strong at 1+2+3 - A product that is growing and has found PMF needs 2+3+4 and some 5 - A product that has strong PMF needs 3+4+5 and some 2 Maybe product roles of the future will look more like this, and less like the domain-specific roles of today?

Music Glue avatar
⟳ Piotr Szmielew retweeted
Music Glue@musicglue·Feb 3

Today we’re launching The Artist Marketplace. A unique eCommerce solution for Artists. Consolidate existing worldwide stores into one global shopfront - across territories, retailers and rights-holders. One link. One storefront. More sales. musicglue.com/the-artist-mar…

Post attachment
Piotr Szmielew avatar
Piotr Szmielew@essepl·25 Sep 2025

I’ve started new screencast about Elixir - focused on devops and deployment. First one from series has been added and it’s free 🎉 Some of them will be hidden behind paywall, hopefully reasonable one ($9/month). deployingelixir.eu