JM

Bercia(sturia)no añada del 80 residente en El Botxo. · «De cada cual según sus capacidades, a cada cual según sus necesidades».

[JM @jmtjdr]

En estos tiempos pre-navideños me ha pasado una ¿bonita? ¿curiosa? historia en el viaje de esta semana a Panamá y México que hace que todavía debamos tener fe en el futuro de la humanidad. Podría contarlo por la vía breve, pero... tengo jetlag. Y me aburro. Así que abro hilo 👇🏻

[JM @jmtjdr]

After being officially appointed by @LFC, there is only one sure thing ahead, @andoniiraola: You'll Never Walk Alone.

[Liverpool FC @LFC]

Welcome to the Reds, Andoni 👋

[NBASpain @NBAspain]

¡QUÉ NOCHE DE AWA FAM EN LA WNBA! 🇪🇸

💥18 puntos
💥6 rebotes
💥2 asistencias
💥2 tapones
💥1 robo

Dos semanas para que cumpla 20 años. Su quinto partido en la liga.

[Matteo Di Gangi @MatteoDG93]

“Nonno, siamo tutti con te: spero che vinci la Coppa del Mondo” .

I nipotini mandano un messaggio a Carlo Ancelotti: i suoi occhi pieni di lacrime dicono tutto ❤️🥹

[RTVE Noticias @rtvenoticias]

¿En qué países está regulado el precio de los alquileres? Javier Gil (@Gil_JavierGil), investigador de @CSIC, hace un repaso por algunos de ellos en ‘La Semana’ y señala:

“El Estado tiene que garantizar la vivienda, como garantiza el derecho a la educación o a la sanidad”

[Paula Badosa @paulabadosa]

Ver el documental de Rafa me ha hecho llorar. No solo por todo lo que ha vivido, sino porque representa una parte muy importante de mi historia.

Rafa significa mis inicios, el motivo por el que empecé a jugar al tenis y la persona que me hizo creer que los sueños podían hacerse realidad. Gracias a él aprendí a soñar en grande cuando era solo una niña.

Lo que ha dejado en este deporte es simplemente inexplicable. Su legado permanecerá para siempre, no solo por todo lo que ganó, sino por la manera en que inspiró a toda una generación.

Siempre me sentiré agradecida por haber podido vivir y compartir momentos como este. Como echo de menos verle jugar… Y sí, es mi habitación… sigo siendo una fan, y siempre lo seré.

🥹❤️

[Carlos del Amor @cdelamor_]

Con este espectacular plano en el mítico ascensor del @museoreinasofia para llegar al Guernica… hemos empezado #Los40delReinaRTVE

[JM @jmtjdr]

This @javilopen tweet shall be the Sixtine Chapelle at mixing sensitive topics —cancer+NHS resources+AI— but it's worth having a look. Not magic but taking advantage of new capacities. Should AI be infinitely better at finding patrons and processing information than we, so be it.

[Javi Lopez ⛩️ @javilopen]

🔴 I NEED YOUR ATTENTION

I've spent a month helping Miriam with her case of metastatic cancer and I want to share the methodology I've been using because it's completely replicable.

I think (with luck) this could be USEFUL TO OTHER PEOPLE with cancer (or any other illness).

The results we've gotten aren't a miracle, but we believe they're genuinely useful and could mean the difference in a literal life-or-death medical case.

Here's the method step by step:

1/ Use the most advanced models of the moment (unfortunately paid, and not cheap. I think Public Healthcare should invest in this):

- ChatGPT 5 Pro + Extended Thinking (40 min aprox. of thinking per call)
- Claude Opus 4.8 MAX

Still pending deeper testing:

- Perplexity Sonar Pro Max
- NotebookLM

Tested but only useful for additional links/research (not as powerful in my experience)
- OpenEvidence

2/ Feed the AI the FULL clinical history, completely chewed up. This sounds dumb but it's critical.

- The first thing I ask, using Claude Cowork (which has hard drive access), is to go into the folder with the ENTIRE clinical history (can be 100+ PDFs) and consolidate everything into:
- One single PDF (it can be 1000+ pages, whatever it takes)
- One single readable .txt or .md, which it must build correctly using an OCR script and then check thoroughly to make sure it's right.

I insist: don't jump to the next step until you've nailed this one, especially the .txt.

3/ Once you have the above, use this prompt along with the .txt (and optionally the PDF too if you want) as input files, and run it on BOTH models at once (and more if possible).

👉 This prompt is insanely complex/advanced: https://t.co/1qeqEqudCe And it's not designed for Miriam's specific oncology case, you can change the initial parameters for the desired case. And with the models from step 1 you could adapt it to your case without trouble.

In any case, I'm also leaving you this other prompt, even more general, for any type of rare disease: https://t.co/4B327floDP

4/ The ARROWHEAD (adversarial model spiral): facing one model against the other. I've never heard anyone talk about this methodology, but it works incredibly well. The feeling is like sharpening a stake until it gets a gleaming point.

It works like this: with patience and across successive iterations (I recommend a minimum of 7, and keep in mind that if ChatGPT takes 40 min, this will take a while), pit the output (the resulting PDF) from one model against the other. With a simple prompt like:

"Another committee of experts says this. What do you think? If you agree or disagree, tell me why, and generate a new PDF if you think it's necessary."

Then you feed that result back to the opposite model. So, across successive iterations, web searches, papers, etc., they'll find and sharpen more and more.

When to stop? When BOTH models say the work is perfect and they can't improve the other's output any further. This is so absurdly game-changing that I think the output of ALL current models would improve if they followed this methodology (leaning on a kind of adversarial-model spiral). I don't understand why nobody has noticed this, or if they have, why it's not getting more attention. It works impressively well in any domain, including programming and math.

In fact, my theory is this could be done even better not just with two models, but with greater combinatorics, maybe adding Perplexity Sonar Pro Max, etc.

RESULTS

Incredible. Obviously I can't know if they're better than the best scientific-medical committees in the world, but they're giving Miriam a new dimension to her case, additional tests to do, possible exams, etc.

Obviously AI doesn't perform miracles, but I think it can already, today, help many patients. And Public Healthcare should invest a lot (but A LOT) in this.

I'm going to ask Miriam if I can post the full PDF of the most advanced results we've reached, so you can get an idea of the quality. She's already given me rough permission, but I want to make sure 100%.

FUTURE PREDICTION

Easy to make: in the near future (I hope), any person's medical history won't just be fully digitized (we're close, but not all the way, well, well, well). On top of that, it'll be "pre-chewed" so it can be consumed by an LLM in one shot.

CLARIFICATION

- We're aware this is a delicate subject and we don't let the AI make final treatment decisions. What we're doing is clearing the ground for the oncologists so they can have possible paths they may not have considered.
Thanks 🙏

- The top LLMs have context windows for that and much more (much, much more). In any case, the PDF is more of a supporting file for the .txt. Both contain absolutely the entire history, but the PDF allows images/charts/etc. The .txt is what the AI consumes.

- On automation: and yes, this can be automated. Yes, AutoGen supports it almost out of the box. LangGraph builds it really well with supervisor / evaluation loops. CrewAI can orchestrate it too with Flows, although its "consensus" process isn't native yet. That would be the next level: automating it.

PETITION AND DISCLAIMER

If there's any oncologist in the room or you are an LLM company, we'd be grateful if you could take a look / help 🙏

Remember: in any case, this is just one more tool for the doctor.

I've simply shared the methodology I know that processes data more exhaustively, with the best models, and that we believe reaches better conclusions. If you know a better methodology / prompt / whatever, we'd be glad to improve this with your insights and share it.

Then the doctor reviews, adopts, or discards the report.

And if it helps the doctor, it helps the patient. And if it doesn't, all we've lost is some time and tokens. In a case that's literally life or death, that's nothing.

Just plain common sense.

Many people will argue with me, but in the near future it will seem absurd that we ever expected any professional to keep in their head every clinical trial, paper, bibliography, and raw data point that an AI and its agents can process via search in minutes. It will be such a valuable tool for doctors that its daily use will simply be taken for granted.

[Javi Lopez ⛩️ @javilopen]

🔴 I NEED YOUR ATTENTION

I've spent a month helping Miriam with her case of metastatic cancer and I want to share the methodology I've been using because it's completely replicable.

I think (with luck) this could be USEFUL TO OTHER PEOPLE with cancer (or any other illness).

The results we've gotten aren't a miracle, but we believe they're genuinely useful and could mean the difference in a literal life-or-death medical case.

Here's the method step by step:

1/ Use the most advanced models of the moment (unfortunately paid, and not cheap. I think Public Healthcare should invest in this):

- ChatGPT 5 Pro + Extended Thinking (40 min aprox. of thinking per call)
- Claude Opus 4.8 MAX

Still pending deeper testing:

- Perplexity Sonar Pro Max
- NotebookLM

Tested but only useful for additional links/research (not as powerful in my experience)
- OpenEvidence

2/ Feed the AI the FULL clinical history, completely chewed up. This sounds dumb but it's critical.

- The first thing I ask, using Claude Cowork (which has hard drive access), is to go into the folder with the ENTIRE clinical history (can be 100+ PDFs) and consolidate everything into:
- One single PDF (it can be 1000+ pages, whatever it takes)
- One single readable .txt or .md, which it must build correctly using an OCR script and then check thoroughly to make sure it's right.

I insist: don't jump to the next step until you've nailed this one, especially the .txt.

3/ Once you have the above, use this prompt along with the .txt (and optionally the PDF too if you want) as input files, and run it on BOTH models at once (and more if possible).

👉 This prompt is insanely complex/advanced: https://t.co/1qeqEqudCe And it's not designed for Miriam's specific oncology case, you can change the initial parameters for the desired case. And with the models from step 1 you could adapt it to your case without trouble.

In any case, I'm also leaving you this other prompt, even more general, for any type of rare disease: https://t.co/4B327floDP

4/ The ARROWHEAD (adversarial model spiral): facing one model against the other. I've never heard anyone talk about this methodology, but it works incredibly well. The feeling is like sharpening a stake until it gets a gleaming point.

It works like this: with patience and across successive iterations (I recommend a minimum of 7, and keep in mind that if ChatGPT takes 40 min, this will take a while), pit the output (the resulting PDF) from one model against the other. With a simple prompt like:

"Another committee of experts says this. What do you think? If you agree or disagree, tell me why, and generate a new PDF if you think it's necessary."

Then you feed that result back to the opposite model. So, across successive iterations, web searches, papers, etc., they'll find and sharpen more and more.

When to stop? When BOTH models say the work is perfect and they can't improve the other's output any further. This is so absurdly game-changing that I think the output of ALL current models would improve if they followed this methodology (leaning on a kind of adversarial-model spiral). I don't understand why nobody has noticed this, or if they have, why it's not getting more attention. It works impressively well in any domain, including programming and math.

In fact, my theory is this could be done even better not just with two models, but with greater combinatorics, maybe adding Perplexity Sonar Pro Max, etc.

RESULTS

Incredible. Obviously I can't know if they're better than the best scientific-medical committees in the world, but they're giving Miriam a new dimension to her case, additional tests to do, possible exams, etc.

Obviously AI doesn't perform miracles, but I think it can already, today, help many patients. And Public Healthcare should invest a lot (but A LOT) in this.

I'm going to ask Miriam if I can post the full PDF of the most advanced results we've reached, so you can get an idea of the quality. She's already given me rough permission, but I want to make sure 100%.

FUTURE PREDICTION

Easy to make: in the near future (I hope), any person's medical history won't just be fully digitized (we're close, but not all the way, well, well, well). On top of that, it'll be "pre-chewed" so it can be consumed by an LLM in one shot.

CLARIFICATION

- We're aware this is a delicate subject and we don't let the AI make final treatment decisions. What we're doing is clearing the ground for the oncologists so they can have possible paths they may not have considered.
Thanks 🙏

- The top LLMs have context windows for that and much more (much, much more). In any case, the PDF is more of a supporting file for the .txt. Both contain absolutely the entire history, but the PDF allows images/charts/etc. The .txt is what the AI consumes.

- On automation: and yes, this can be automated. Yes, AutoGen supports it almost out of the box. LangGraph builds it really well with supervisor / evaluation loops. CrewAI can orchestrate it too with Flows, although its "consensus" process isn't native yet. That would be the next level: automating it.

PETITION AND DISCLAIMER

If there's any oncologist in the room or you are an LLM company, we'd be grateful if you could take a look / help 🙏

Remember: in any case, this is just one more tool for the doctor.

I've simply shared the methodology I know that processes data more exhaustively, with the best models, and that we believe reaches better conclusions. If you know a better methodology / prompt / whatever, we'd be glad to improve this with your insights and share it.

Then the doctor reviews, adopts, or discards the report.

And if it helps the doctor, it helps the patient. And if it doesn't, all we've lost is some time and tokens. In a case that's literally life or death, that's nothing.

Just plain common sense.

Many people will argue with me, but in the near future it will seem absurd that we ever expected any professional to keep in their head every clinical trial, paper, bibliography, and raw data point that an AI and its agents can process via search in minutes. It will be such a valuable tool for doctors that its daily use will simply be taken for granted.

[Athletic Xtra @AthleticXtra]

🚨 Ernesto Valverde y su banda Easy Ironing versionando a Barricada en un local de Algorta 🎸🎶

[JM @jmtjdr]

¿Qué es la vida? Los 10 primeros minutos de *Up*, y esto de Pantomima Full.

😂😂😂

[Pantomima Full @Pantomima_Full]

FESTIVAL DE EXCUSAS:
#Festivalero
@bilbaobbklive #20aniversario #Publi

[Pantomima Full @Pantomima_Full]

FESTIVAL DE EXCUSAS:
#Festivalero
@bilbaobbklive #20aniversario #Publi

[Teledeporte @teledeporte]

🗣️ Íñigo Pérez: “Ahora que ya volvemos a la realidad, invito a la gente a venir a Vallecas. Ahí os donde os vais a dar cuenta de que pasta está hecha su gente.”

⚡️ El Rayo pierde frente al Crystal Palace (1-0) en la #UECLfinal

[Ana 🔻☂️ @Zapatista72]

Pues así vamos, p'atrás como los cangrejos.🤦😢

[Telediarios de TVE @telediario_tve]

Al final no hubo Copa para el Rayo, pero en el #TD2 nos quedamos con toda esa gente que viajó, gastó lo que no sobraba, lloró al final y, aun así, ha regresado sabiendo que merecía la pena.

Lo cuenta @jgnogales

[José Vico 🔻🇵🇸🇿🇦 @josevico4]

Muy grandes estos chavales en Euskal Herria plantándole cara a los neofascistas.
En cuanto le piden que saquen las pruebas de que ese piso está okupado, se hacen caquita y se piran.

Por cierto, van en un Porsche a tirar de su casa a gente obrera.
Date cuenta, currela.
O sea están financiados por los fondos buitres.
Espabilad.

[Offsider @Offsider_ES]

No, no es la afición del Friburgo, River Plate o Ajax, es la del puto Rayo Vallecano.

[La Noche de Aimar @LaNochedeAimar]

Juan y Medio, sobre los impuestos:

💬  “Trabajo más de medio año para el país, con mucho gusto”.

💬  “Yo soy de los tontos que llego a un hospital nuevo y digo: qué maravilla”.

#LaNochedeAimar

[Slime🐍 @ItsKingSlime]

Anthony Davis REUNITED with his former Lakers teammate Austin Reaves just to PRANK him into thinking he RUINED a stranger’s chance to win $250K at a charity event 🤣💰👀

“Out of everybody on the team, I really miss him. That was my guy… Everyday, Austin used to come in and say ‘I don’t wanna be here today. I just wanna play the game. I don’t wanna practice. I wanna go home. I wanna golf.’” 😭❤️

[COPA90 @Copa90]

Mayor @ZohranKMamdani knows ball. Don't believe us? Just listen to him talk about his love for @RealOviedo

[Lordo @LordoLordor]

El alcalde de Nueva York es más del Oviedo que el alcalde de Oviedo