Franchement oui… mais pas que. Réfléchir avant d’agir c’est la base.
Mais avec un LLM, t’es plus juste en train d’exécuter ou réfléchir solo. En vrai tu réfléchis avec lui, Et c’est là que ça change tout. Si t’as une idée floue il sort un truc moyen
Si t’es clair il t’emmène
PROMPT ENGINEERING
-
How an LLM changes the way you think with it
By
–
-
GPT-5.5 and GPT-Image-2 Combo for Web App Development
By
–
GPT-5.5 + GPT-Image-2 is becoming one of the best combos for building apps! @dkundel breaks down why it works so well. We built those learnings into the Build Web Apps plugin, so Codex can handle the design-to-app loop for you.
-
End of Prompting Era: Autonomous Agents Push Next
By
–
The age of prompting is ending.
— Replit ⠕ (@Replit) 29 avril 2026
What comes next: new interfaces and fully autonomous agents that push instead of pull.
Amjad on the post-prompting era, live with @southpkcommons ⠕
Full conversation below. pic.twitter.com/0vOzZLqZpLThe age of prompting is ending.
What comes next: new interfaces and fully autonomous agents that push instead of pull.
Amjad on the post-prompting era, live with @southpkcommons ⠕ Full conversation below. -
Practical Framework for AI Improvement Through Data Traces
By
–
Get traces Enrich them Improve from them Repeat Head of Product @samecrowder on how to do this in practice:
-
ChatGPT Integrates Model Switcher Into Prompt Field
By
–
ChatGPT's model switcher is now built directly into the Prompt field
-
GPT-Image-2 Used as Stop Motion Video Generator Frame by Frame
By
–
GPT-Image-2 can be a video-gen model if you want it to be!
— Matt Shumer (@mattshumer_) 29 avril 2026
Just ask ChatGPT to generate stop motion video, frame-by-frame.
It works shockingly well and is super controllable! pic.twitter.com/Q4GT6SXgj1GPT-Image-2 can be a video-gen model if you want it to be! Just ask ChatGPT to generate stop motion video, frame-by-frame. It works shockingly well and is super controllable!
-
Codex Automates Research, Spreadsheets, Decks and Summaries
By
–
Still wondering how you can use Codex for (almost) everything?
— OpenAI (@OpenAI) 29 avril 2026
Codex can help with more of the work that supports the work, from organizing research to making spreadsheets, decks, and summaries. pic.twitter.com/aoTXXbkinwStill wondering how you can use Codex for (almost) everything? Codex can help with more of the work that supports the work, from organizing research to making spreadsheets, decks, and summaries.
-
Two models with 1M context, near equal, model just 20% of result
By
–
And this is the part nobody is talking about:
Both models ship with 1M-token context. Both are within a few points of each other on most tasks. The gap between them is smaller than the gap between a good prompt and a bad one. The model is maybe 20% of your result. Your -
Start Small: Iterative Agent Development Best Practice
By
–
The useful version starts small. Do not let the agent rewrite everything. Let it improve one narrow part: one prompt one tool call one retrieval step one eval one memory rule one workflow
Then test the result against something real. -
Future AI Products: Beyond Models to Autonomous Improvement
By
–
That is the real lesson. The next wave of AI products will not just use better models. They will improve their own prompts, tools, memory, evals, and workflows. But the teams that win will not be the ones with the most autonomous agents. They will be the ones with the best