Funny, I was testing the Horizon Alpha model on @FeatureCrewPod
's maze tool. In the regular chat mode it was always just responding instantly without thinking and failing. But when I clicked the 'app' button on open router, it took time to think and create an app that actually
LLMS
-
Horizon Alpha Model Shows Better Performance With Extended Thinking
By
–
-
Open Source GPT: Jimbo Discovers Interesting Leaks
By
–
Open Source GPT – the legendary jimbo found interesting leaks.
-
Zuckerberg Confirms Major AI Infrastructure Push at Meta
By
–
Mark Zuckerberg, a investi plus de 70 milliards de dollars dans sa nouvelle infrastructure IA, débauché les meilleurs talents d’Apple et d’OpenAI, et a accéléré à une vitesse que personne n’avait anticipée. Dans une nouvelle note interne, Zuck confirme que les systèmes d’IA de
-
GPT-5 Launch Expected to Drive Rapid AI Transformation
By
–
Getting ready for GPT-5. Re-subscribed to ChatGPT Pro. If it’s even half as good as I’ve heard, things are about to change fast.
-
JSON Prompting vs Classic Prompts for Better AI Results
By
–
Pensez-y de cette façon : Prompt classique : " Peut-tu écrire un tweet sur la dopamine detox ?" Version JSON :
{ "task": "écrire un tweet", "topic": "dopamine detox", "style": "viral", "length": "moins de 280 caractères"
}
Vous voyez la différence ? ça marche -
JSON Prompt Writing: Structuring Prompts for Better AI Results
By
–
D’abord… c’est quoi le JSON prompt writing ? C’est simplement le fait de mettre ton prompt dans un format structuré.
Comme ceci : { "task": "résumer cet article", "audience": "étudiants à l’université", "length": "100 mots", "tone": "curieux"
} -
JSON Prompting as a Cheat Code for GPT-4 Claude Gemini
By
–
Wow…. Nobody is talking about JSON prompting, but it's literally the cheat code to unlock top-tier results with GPT-4, Claude, or Gemini. (and even grok) Here's how it works (with copy-paste model prompts in comments):
-
LLMs Hallucinate APIs Zero-Shot Distance Minimization
By
–
Have LLMs hallucinate an API to your library zero-shot and try to minimize the distance.
-
GPT-5 Documentation Spotted Online as Release Anticipation Grows
By
–
La documentation de GPT-5 a été spotted en ligne sur leur site.
OpenAI : sortez-le une bonne fois pour toutes.
Arrêtez de jouer et Lâchez la bête
On a assez attendu. -
Local Coding Model Performance Review and Assessment
By
–
Not as good, but it's also not useless which is saying a lot for a local coding model