cfalguiere
@cfalguiere.bsky.social
AI Engineering Principal • GenAI • MLOps • AWS • Data Science • Learning
L'autonomie des IA expliquée aux humains
YouTube video by Monsieur Phi
youtube.com
November 15, 2025 at 4:02 PM
Pourquoi CE LIVRE coûte si cher ?
YouTube video by Jeannot se livre
youtube.com
November 2, 2025 at 2:48 PM
I'm Sorry...This New Artist Completely Sucks
YouTube video by Rick Beato
youtube.com
August 3, 2025 at 1:42 PM
How BCI (Brain Computer Interface) technologies and market evolve
youtube.com/watch?v=CGSF...
youtube.com/watch?v=CGSF...
The Race to Control Our Brains Is Heating Up
YouTube video by ColdFusion
youtube.com
July 23, 2025 at 3:07 PM
How BCI (Brain Computer Interface) technologies and market evolve
youtube.com/watch?v=CGSF...
youtube.com/watch?v=CGSF...
Interesting disvussion with authors aboit the matrix product algorithm Alpha Evolve found and how the evolutionary algorithm works.
youtube.com/watch?v=vC9n...
youtube.com/watch?v=vC9n...
Wild breakthrough on Math after 56 years... [Exclusive]
YouTube video by Machine Learning Street Talk
youtube.com
May 18, 2025 at 6:48 PM
Interesting disvussion with authors aboit the matrix product algorithm Alpha Evolve found and how the evolutionary algorithm works.
youtube.com/watch?v=vC9n...
youtube.com/watch?v=vC9n...
An interesting analysis of LLM's creativy and understanding, and ultimately what is philosophie and what do we expect from LLMs.
youtube.com/watch?v=n2A-...
youtube.com/watch?v=n2A-...
Can ChatGPT actually do Philosophy? (Featuring Alex O’Connor)
YouTube video by Unsolicited advice
youtube.com
May 18, 2025 at 7:16 AM
An interesting analysis of LLM's creativy and understanding, and ultimately what is philosophie and what do we expect from LLMs.
youtube.com/watch?v=n2A-...
youtube.com/watch?v=n2A-...
L'histoire de Hitchbot et une experience de robot social en milieu hospitalier :
February 16, 2025 at 7:24 PM
L'histoire de Hitchbot et une experience de robot social en milieu hospitalier :
An article about codemods, a way to automate code refactoring. It achieves better results than string replacement by using AST (Abstract Syntax Tree). Examples for JavaScript and tasks like removing featute toggle or API changes.
NEW POST
Libraries often need to evolve APIs for new usage patterns, but risk breaking changes disrupting users' workflow. Juntao Qiu begins his explanation of how codemods - automated code transformations - can modify client codebases
martinfowler.com/articles/cod...
Libraries often need to evolve APIs for new usage patterns, but risk breaking changes disrupting users' workflow. Juntao Qiu begins his explanation of how codemods - automated code transformations - can modify client codebases
martinfowler.com/articles/cod...
Refactoring with Codemods to Automate API Changes
Using codemods to upgrade client code on API changes
martinfowler.com
January 7, 2025 at 6:07 PM
An article about codemods, a way to automate code refactoring. It achieves better results than string replacement by using AST (Abstract Syntax Tree). Examples for JavaScript and tasks like removing featute toggle or API changes.
Easy to read paper on how beginner coders use LLMs and often fail getting the expected result. 2 hypothesis that may explain why the LLM does not output the correct piece of code: 1) users lack technical vocabulary 2) users omit important clues.
The author suggests 2) is more significant.
The author suggests 2) is more significant.
"This paper explores two competing hypotheses about the cause of student-LLM miscommunication: (1) students simply lack the technical vocabulary needed to write good prompts, and (2) students do not understand the extent of information that LLMs need to solve code generation tasks."
Substance Beats Style: Why Beginning Students Fail to Code with LLMs
Although LLMs are increasing the productivity of professional programmers, existing work shows that beginners struggle to prompt LLMs to solve text-to-code tasks. Why is this the case? This paper expl...
arxiv.org
January 3, 2025 at 10:52 AM
Easy to read paper on how beginner coders use LLMs and often fail getting the expected result. 2 hypothesis that may explain why the LLM does not output the correct piece of code: 1) users lack technical vocabulary 2) users omit important clues.
The author suggests 2) is more significant.
The author suggests 2) is more significant.