¡La nueva generación de tests para web y apps móviles!
El framework se llama "e2e" y es de código abierto
✓ Mezcla IA con pruebas deterministas
✓ Compatible con OpenAI, Claude y cualquier AI
✓ La misma API para web, iOS y Android
→ https://t.co/n09ldmz3PD
Este es el tipo de locuras que van a hacer que una empresa se coma a toda su competencia.
Detecta cuando un conductor va atrasado o si hay algún cambio de planes, y le consigue una ruta más rápida en tiempo real.
Esto es relativamente fácil de hacer.
Lo difícil es que el dueño de la empresa de transportes suelte el billete, nicho complicado, señores muy chapados a la antigua.
¿Cuál es el nicho más facil para venderle soluciones con IA?
Jev + Muse is the first AI agent system that actually automate 100% of my life
99% of people pay 200x more for slower AI agents - while 1% run this 2030 setup
just 5 min and setup is ready:
prompt → Muse → Jev decision → Muse execution → result
step 1 → create your Jev API key (typesafe website)
step 2 → clone and install the complete router from Github below
python3 -m venv .venv && .venv/bin/pip install -r requirements.txt && cp config.example.yaml config.yaml
step 3 → export the key before running anything: export TYPESAFE_API_KEY='YOUR_KEY'
add the same export to ~/.zshrc or ~/.bashrc if you want it to survive a new terminal session
step 4 → give your agent skill/jev-decision-layer.SKILL.md and connect it to src/router.py + recipes/ , raw Jev returns probabilities - the router converts them into executable actions
step 5 → test the entire chain, not the raw Jev API:
.venv/bin/python -m src.cli '{"goal":"what is 2+2?","kind":"chat"}'
the final JSON should contain action, reason, mode, jev_used and confidence details
step 6 → keep mode: shadow for 20–50 real decisions: the agent works normally while Jev’s routes are logged and checked; promote only reliable question packs
step 7 → switch to mode: active with hard confidence gates: ≥0.80 act automatically, 0.50–0.79 advisory only, <0.50 escalate to the human
the result: Jev + Muse is a system that decides what to do, what to skip and when to bring in - I’ve tested it across my daily workflows, and it’s the best setup I’ve found for automating routine
Take the exact stack I built, run it yourself from the repo - then read the full Jev architecture behind it ↓
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
Sabo Elbaf 5-0 cueva roja.
(no he ganado ningún dado)
1- Mihawk op14
2- Shanks op17
3- Kaido op17
4- Law op14
5- Rocks op17
La final como casi todos los domingos contra @KDZMILLAN 🫡
Dejo la lista por aquí por si algún curioso quiere probarla!
Created a cheat sheet for turn picks for Sabo and BLuffy.
Note: This is based on the sim stats. These are the turns where these leaders got a HIGHER win rate.
Here are the currently confirmed reprints for SD01 Set Sail Deck Set.
There could be additional unknown cards included in each deck. Actual quantities are unknown.
🇺🇸: September 18, 2026
#OnePiece#OnePieceCardGame
[Utrecht Regional]
Deck used : Boa
Swiss:
Mihawk 🟩
Moria 🟩
Mihawk 🟩
Mihawk 🟩
Mihawk 🟩
Boa 🟩
Boa 🟩
Ace 🟩
Sabo 🟥
Mihawk 🟩
Top32:
Mihawk 1-0
Robin 2-0
Luffy 1-1?2?
What do I do when we start last game with a 5 life leader against a 4? Do we call it a game?
This is the Kaido decklist I used for Flame Flame and Finals! 🐉💜
The deck was built together with @FedePingu94, who was the one that got me into Kaido.
We both didn’t want to play Mihawk because neither of us really enjoys playing the mirror match, and I’m VERY thankful for that, everyone in the room has been complaining about it 😂
The game plan is to remove as many characters as possible every turn before Shanks comes down, so that you can go into Big Mom and heal back the life you lost to Shanks and you end up taking it out as well.
With Yasopp being the real threat to our Big Mom, we want to make sure we can remove it with 7c Kaido, Lightning, or 10c Kaido.
7c Kaido also prevents us from getting KO’d by Decken and can only really get punished by Luna.
In most cases, Luna gets discarded earlier by Kinemon because it’s “theoretically” useless against Kaido. The standard version only plays the big 10 costs bodies, so stunning a King with Luna just isn’t good enough in most scenarios.
Having a 7 9000 rush that could cheat dons out alongiside King/Blocker Kaido is always a very strong play, no matter what match up.
We were on 3 of them but decided to swap 1 for 1 10C kill Kaido for variance, it’s better into Mirror match - Purple decks overall, so going into such a big tournament we preferred having a searchable good card (vs Mihawk you can still go kill Kaido + Lightning if you do have a Blocker Kaido already established)
Best curve vs Mihawk usually is something like:
Queen - Ramp - King - 10C Blocker + Gum Lightining - 7C Kaido + Law
My losses were to little missplays that cost me the game in the end or just total brick (played vs @ChrisSokTCG , missed King AND 10 cost body and went for double Law🫠).
The deck is very difficult to play at its best, it’s easy to go for Ramp + King + 10 cost but especially in the late game things get tricky and you have to learn every single spot in the matchups. Just 1 more DON can either win or lose you the game.
Very happy with how many good feedbacks I’ve received, be always the guy that want to bring their favorite deck and don’t feel forced to play whatever the T1 is.
You will always have a better experience with a deck you’re comfortable with or you enjoy playing.
Maybe I’ll try my best to drop some content regarding this deck!
Had as always a great time meeting you all, biggest shoutout goes to @FedePingu94 for the amazing journey prepping the deck, to @project7x_ and to the goat @LukaTCG for winning it all, totally deserved.