Representante del futuro en esta tierra. Argentina, USA.
Joined October 2025
- Tweets2K
- Following629
- Followers66
- Likes2K
Gordo Polymath retweeted
today we are announcing openrouter for commerce: opencommerce.sh
a single endpoint that integrates 5k stores, including Doordash, Amazon and most shopify stores, with payments using Agentcard (Stripe Link and Shop coming soon).
we built opencommerce to solve 3 problems:
* coverage: one endpoint to integrate 5k stores. agentic purchasing is a core feature for most personal assistants, but not their main business. searching for products and buying on behalf of users shouldn’t be as painful as it is today (e.g. it shouldn’t involve browser automations or dealing with PSPs). opencommerce solves that: 1 tool, every online store.
* reliability: 100% uptime. the challenge with browser automations is that they fail (e.g. captchas, bot-detection, etc). we run thousands of tests every couple of hours on every one of the stores to guarantee that the integration works when your user tries to buy something.
* speed: responses in under 10s. consumers are used to Amazon speed, and agentic purchases have so far felt like a downgrade. most agents spend minutes finding products before they come back with results. we monitor speed and improve it constantly.
Gordo Polymath retweeted
UPDATE: I hired @Muse to sue someone on my behalf.
I won. Well, they caved.
Within 20 minutes of being served papers, the company offered a settlement.
Within ten days, they paid me *with additional compensation* for recovery expenses.
@Muse filed the motion to dismiss, which the court accepted yesterday.
To everyone who said I would fail, respectfully, you were wrong.
Read the Manifesto, It's even very conservative. We need to keep evolving.
we will need to rebuild and rewrite much of software to adapt to a new, faster pace.
code used to arrive one drop at a time. soon, if not already, code will be written as if it were a continuous stream, like a violent river twisting and turning as it pleases.
this is not a new thing: big tech cos have had to deal with this with the enormous scale of their engineering teams. but now ai has brought an incredibly elastic and capable workforce wielded by every engineer. this is your problem now, and the only way to adapt is to evolve your systems so agents - even and especially the ones with little context about the right way of doing things - can thrive. make the easy thing the right thing.
your codebase is becoming organic architecture. agent contributions grow around the constraints and guardrails you’ve designed. good software engineering matters even more now! and no, the continuous stream of code is not something you have to watch helplessly. be more ambitious and design systems, frameworks, and languages to control the chaos.
the time for mourning coding is long over
Gordo Polymath retweeted
By the way, in case anyone was still wondering whether they are completely useless, Binance holds SOC 2 Type 2, ISO 27001, and several other certifications.
Gordo Polymath retweeted
I mostly okay what @illyism is doing, but this is just dum dum.
He opened two issues today and instantly (3-4 minutes after) write a 💀 emoji post about how he vibe coded a thing that is good for him (and not the next person next to him), privately open-source it (to feel that you get something luxury) just to generate enhancement or idk.
You can use a vibe coded Coolify alternative, I really love that people self-host more and more things, because that was the whole point of me creating Coolify.
The fact that I made a business out of it was just a coincidence.
With Coolify, you get support from us indefinitely, even if you are self-hosting it for free, or pay for the cloud.
And this is true for all of our official things.
Everyone can vibe code anything but keep in mind that if the hype is over, you still need to maintain it.
As he said Coolify saved him $10k+, thats the whole point .
That is why Im doing the whole thing.
(btw, the two issues are enhancements, not bugs, and I fixed them between I was waiting & giving emotional support for my wife in the dentist and bought 🥔 at the local marketplace)
I think unfortunately @coolifyio is next on the chopping block 💀
I don't need 150,000 lines of PHP and 272 dashboard screens anymore, I just need a GitHub webhook, docker build, and an MCP tool for my agent
I would privately open-source this by invite only
lmk if u need 👇
Gordo Polymath retweeted
There are 20-year-old kids applying to 50 full-time jobs a day on Indeed w/ zero intention of showing up to work
When the boss gets them on Zoom for the job interview, they don't ask for the $65,000 salary
They screen-share a robot doing the whole job in 30 seconds & walk out w/ a $15,000 wire:
Try cold calling a $10M company today and see what happens
A receptionist blocks u, ur email goes to spam & ur DM sits in message requests for 6 months
But when that same company posts a job listing on Indeed for a $60,000/yr Operations Coordinator, Dispatcher, or Intake Specialist?
The owner is literally begging strangers to get on a 30-minute Zoom call w/ him this week bc his staff is drowning and he already approved $60,000 in budget to fix it
A kid in our AI Frontrunners group realized this and completely stopped cold calling. Here is the Trojan Horse play he runs from his bedroom:
1. Filter Indeed & ZipRecruiter for "Copy-Paste" Desk Jobs
Look for boring roles paying $50,000 to $75,000/yr that have been sitting open for 14+ days:
Data Entry, Scheduling Coordinator, Claims Processor, Medical Intake, Freight Dispatcher
2. Turn the Job Post Into a Working Prototype in 20 Mins
The boss just handed u the exact blueprint of what his company sucks at doing under "Daily Responsibilities"
Copy the job description and paste it into Claude w/ this exact prompt before the interview:
"Break this job listing down into:
1) The 5 daily computer tasks taking 80% of this employee's week
2) The n8n + Claude API workflow that automates each task end-to-end
3) The 12-month payroll + tax savings if we replace this seat w/ an internal AI worker
4) A clickable dashboard layout I can build in Lovable in 15 minutes to demo live on Zoom"
3. The 5-Minute Zoom Interview Pivot (Word-for-Word)
Apply w/ a clean resume so the hiring manager books u onto a 15-minute Zoom interview. 5 minutes in, when the boss asks why u want the job, say this word for word:
"Full transparency John, I'm not looking for a $60k salary. I saw this listing has been open for 3 weeks, so I took the 8 daily tasks on ur job post and built an AI worker that does all of them in 12 seconds without taking sick days or asking for healthcare. Can I share my screen for 60 seconds?"
U aren't pitching a hypothetical idea anymore. He is watching a machine do the exact job he was about to pay $60,000 + payroll taxes + benefits for
(One of our guys also put $220 of tokens into a GrokBot + TryGTM agent that scrapes these open job listings and texts the CEOs automatically --- > booked 6 calls and closed 2 deals in his first week)
Charge the owner a $15,000 one-time setup fee (1/4th of the employee's first-year salary) to install it into his company
Then take $1,000 out of his Day-1 deposit, pay a cracked developer on Discord to wire the APIs into his software over the weekend, and pocket $14,000 profit
Don't hate the player, hate the game
Gordo Polymath retweeted
Someone built an entire game development studio inside Claude Code.
49 AI agents, 72 skills, and a full studio hierarchy working together to help you build games from scratch.
Get started in 3 steps:
* Download: Clone Claude Code Game Studios from GitHub
* Launch: Open the project in Claude Code
* Build: Describe your game and let specialized AI agents handle development
You don’t need a 50-person team to start building your dream game anymore
Repo: github.com/Donchitos/Claude-…
Gordo Polymath retweeted
Introducing *Switch*: a *harness framework* for *decision models* like Jev
I looked for this the other day and was surprised to not find anything like it
You obviously cannot use a decision model like an LLM in a coding agent harness like @pidotdev, because Jev cannot generate tool calls
But what if there was a framework that "generated the tool calls" for it programmatically, and Jev only had to pick out of that finite set of choices
That is what switch does. You pick a "domain" to implement the decision model in, and it provides a core API to define your state, and the functions that will derive decision model questions out of that state. Chess is a domain, as well as being a rubric judge for evals
It basically standardizes what I imagine a lot of people are already vibe-coding, to an abstract interface: calling a decision-model API through multiple steps, i.e. an agent loop over finite choices
Because of the finiteness of the output of a decision model, you cannot have a general pure decision model harness. Instead, you need to implement specific ones that generate the choices programmatically (or have an LLM generate the choices, but I find the former more interesting)
A primary use case I have for this is use as a judge in an eval. For example, At the end of a task run that involves a bunch of documents, most people currently follow this approach: extract text out of PDF/docx/md files, and dump them right into the context
But what if the visual formatting of the output is a judging criterion? Then you have to dump an image of every page in the input state. But what if you have 200 pages, and your question does not need looking at all of them? What if Jev could navigate through the haystack and find the info it needs?
I have noticed that Jev is not so good at chess nor being a Decision-Model-as-a-Judge. It sucks at chess, and it does not perform well enough to replace GPT 6.1 Sol as a judge in the domain I am working for
But switch is not only for Jev! It is for any decision model including the ones supported by the pi-ai package
So once you can generate enough data with a better model, you should be able to pick an open source one and fine-tune it on your use case to perform better! And the model should be trained in a harness like switch's to be especially performant and cost-efficient
I wanted to get this out because I find the idea very exciting, at least for benchmarking. Jev is currently not there, but decision models obviously will be there at some point, and we can take them there! There are also a lot of potential gains from picking a specific domain, and creating a looping agent that does a job for 100x cheaper!
Let me know if you have any ideas, I am quite keen to try this on new domains!
Repo: github.com/osolmaz/switch
Gordo Polymath retweeted
I've seen a few people struggling to manage multiple projects with Grok Bot.
Here's the setup I'd recommend after working through it with my Bot team.
The secret is to stop using chats as your project management system.
Instead, use Grok Bot's Pages feature.
One Page per project. One routine to keep it updated. Every Bot reads the Page before starting work and updates it when finished.
Here's the exact setup you can copy.
Paste this into your Chief of Staff:
"Set up a Page-based project management system for my Grok Bot team.
1: PROJECT PAGES - Create one Page for each project, containing its goal, current status, next actions, task owners, deadlines, decisions, blockers and an update log showing which Bot changed what.
2: MASTER INDEX - Create a Projects Page listing every active project, its status and the next action. This becomes my single place to see what's happening across all projects.
3: READ FIRST, UPDATE LAST - Every Bot must read the relevant project Page before starting work and update that same Page when finished. Never create duplicate Pages. Don't mark work complete without checking the actual result.
4: SHORT CHATS - Use fresh chats for individual tasks instead of maintaining one enormous project conversation. The Page holds the project history, decisions and context.
5: DAILY HEARTBEAT - Create one weekday routine per project. Check relevant sources such as email, GitHub, Notion or calendars, verify progress and update the project Page and master index.
6: EXCEPTION REPORTING - Only notify me when something is blocked, overdue, needs my decision or changes status. Otherwise, keep the Pages updated without interrupting me.
7: PROJECT CLOSURE - When a project finishes, mark it Closed, record the outcome and lessons learned, and pause its heartbeat routine.
Never send, purchase, publish or delete anything without my approval. Clearly flag anything unverified.
Before creating anything, show me the proposed projects, their information sources and the routines you'll establish. Wait for my approval."
My recommendation?
Start with one project for seven days.
If your Bots keep its Page current and you no longer need to dig through old conversations to understand what's happening, expand it to the rest.
Your chats are for doing the work. Your Pages are for remembering and managing it.
Gordo Polymath retweeted
PUEDES MONTAR UN CALL CENTER CON IA POR 0,06 $ EL MINUTO
Haz números:
→ Le montas el agente a una clínica, un ecommerce o una inmobiliaria
→ Le cobras 500 €/mes por tenerlo funcionando 24/7
→ Con 80 clientes son 40.000 €/mes
→ Y cada llamada de 3 minutos te cuesta 0,18 $
Hay agencias enteras montándose sobre esto ahora mismo
Y no uno cutre. Phonic-1 supera a OpenAI, xAI y Google en los benchmarks de agentes de voz
Las cuentas:
→ Una llamada de 3 minutos = 0,18 $
→ Atiende 24/7 en más de 50 idiomas
→ Responde en 0,61 s
La clave es que consulta tu sistema MIENTRAS el cliente habla. Con la misma llamada, GPT-Live tarda 15,7 s y Phonic-1 tarda 1,1 s
El workflow:
→ 1. Te registras y creas tu agente
→ 2. Le escribes las instrucciones: qué negocio es, cómo habla, qué puede hacer
→ 3. Conectas tu tienda, tu agenda o tu CRM
→ 4. Le asignas un número de teléfono
→ 5. Llamas tú 20 veces intentando romperlo
→ 6. Lo pones en producción
Sirve para casi cualquier negocio:
→ Ecommerce: busca pedidos, cambia direcciones, gestiona devoluciones
→ Clínicas: mueve citas y manda recordatorios
→ Restaurantes: reserva mesa y manda el SMS de confirmación
→ Inmobiliarias: filtra al cliente y le agenda la visita
Ahora te dan 250 $ en créditos si te registras antes del 31 de diciembre.
Son más de 4.000 minutos para validar tu idea gratis
Empieza hoy mismo: auth.phonic.ai
Introducing Phonic-1, the most advanced speech-to-speech model for agentic tasks — from @phonic_co, the speech-to-speech model company.
We’ve had a breakout year and raised a $27.5M Series A led by @firstround with participation from @Lux_Capital, @felicis, and Definition.
Gordo Polymath retweeted
🚨 Fallo crítico en el kernel de Linux: se puede atacar por red, sin login y sin necesidad de ninguna acción por parte del usuario.
CVE-2026-98432
➡️ CVSS 9.8 (crítico)
➡️ Afecta a la gestión de conexiones TCP/IPv4, el código que atiende cualquier conexión a tu servidor.
➡️ Ubuntu marca vulnerables desde la 16.04 hasta la 26.10, también los kernels de AWS, Azure, Google Cloud y Oracle.
➡️ La corrección todavía está «en preparación» en casi todas.
Si tienes un servidor o un VPS con Linux, sigue los avisos de tu distribución y actualiza el kernel (y reinicia) en cuanto salga el parche.
ubuntu.com/security/CVE-2026…
Gordo Polymath retweeted
the binance hacker just did something genius and it should scare you
tether froze $1.5 billion in stolen USDT. circle froze $800 million in USDC. everyone's celebrating like the problem is solved
meanwhile the hacker deposited the stolen USDT on aave, borrowed ETH against it, and walked away. because USDT can be frozen. ETH can't
he's never paying it back. he doesn't need to
tether and circle just proved they can freeze billions in seconds. and the hacker just proved that if you know how defi actually works, none of that matters
the freeze saved some of the money. but the smartest money was already gone before anyone pressed the button
Gordo Polymath retweeted
*ehm ehm* BIG ANNOUNCEMENTS DAY 📣
two new things cooking in herdr labs 🐏🧪
a brand new herdr-core, and a desktop app built on it. open source.
first, the app: software that fits you. every part of it is a file your agent can change. you just ask.
Gordo Polymath retweeted
Compaction is a mistake.
When an agent's context fills up, tools like Codex and Claude Code compact it:
1. The model prefills the entire session again
2. It writes a summary of everything so far
3. A new session starts from that summary
I measured this on a real ~400k-token session with Opus 5.5:
→ 38 s and $1.99 when the prompt cache has expired
→ 29 s and $0.17 when it hasn't
And the summary is lossy. The exact error message, the file path, the one number you needed is often gone.
So I do something new for Mainplane
Context retrieval works the other way around. Mainplane keeps the full record of every session as a file. When the context fills up, a new session starts right away with one instruction: "You are continuing session X. Retrieve key context from it as you go."
The agent searches the old session and copies the exact lines it needs, when it needs them.
Same session, same model: 15 s and $0.10 to get back to work. It does not depend on a cache hit, and nothing is paraphrased.
This is the bitter lesson applied to agent memory. Don't hand-design what the model should remember. Give it the full record and good tools, and let it decide.
Mainplane is open source (MIT). Link in the first comment.
