Salvatore Raieli
@salvatoreraieli.bsky.social
Funny thing, being rude with AI improves performance
"Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts"
arxiv.org/pdf/2510.04950
"Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts"
arxiv.org/pdf/2510.04950
October 16, 2025 at 4:38 PM
Funny thing, being rude with AI improves performance
"Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts"
arxiv.org/pdf/2510.04950
"Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts"
arxiv.org/pdf/2510.04950
An interesting perspective by Nature
www.nature.com/articles/d41...
www.nature.com/articles/d41...
AI models that lie, cheat and plot murder: how dangerous are LLMs really?
Tests of large language models reveal that they can behave in deceptive and potentially harmful ways. What does this mean for the future?
www.nature.com
October 8, 2025 at 6:43 PM
An interesting perspective by Nature
www.nature.com/articles/d41...
www.nature.com/articles/d41...
#tabular data are everywhere (from medicine to finance). However, they have been neglected by the #AI revolution. In this review, we discuss why it is difficult to work with this data and which models to use (from #neuralnetwork to #LLM).
www.techrxiv.org/users/961472...
www.techrxiv.org/users/961472...
Tabular Deep Learning: A Survey from Small Neural Networks to Large Language Models
Tabular data are ubiquitous in several real-world domains, including finance, healthcare, cybersecurity, and ecommerce. In spite of the dominance of deep learning for homogeneous data (such as compute...
www.techrxiv.org
September 11, 2025 at 3:56 PM
#tabular data are everywhere (from medicine to finance). However, they have been neglected by the #AI revolution. In this review, we discuss why it is difficult to work with this data and which models to use (from #neuralnetwork to #LLM).
www.techrxiv.org/users/961472...
www.techrxiv.org/users/961472...
Researchers evaluated 19 language models on over 76,000 participants and discovered that specialized post-training methods increased persuasiveness by up to 51%.
But, the more persuasive the LLM, the less accurate is
arxiv.org/pdf/2507.13919
But, the more persuasive the LLM, the less accurate is
arxiv.org/pdf/2507.13919
arxiv.org
July 30, 2025 at 6:36 PM
Researchers evaluated 19 language models on over 76,000 participants and discovered that specialized post-training methods increased persuasiveness by up to 51%.
But, the more persuasive the LLM, the less accurate is
arxiv.org/pdf/2507.13919
But, the more persuasive the LLM, the less accurate is
arxiv.org/pdf/2507.13919
Reposted by Salvatore Raieli
@salvatoreraieli.bsky.social explores how meta-learning helps CNNs grasp abstract relationships like "same-different," bridging the gap between human and machine vision.
The Basis of Cognitive Complexity: Teaching CNNs to See Connections | Towards Data Science
Transforming CNNs: From task-specific learning to abstract generalization
towardsdatascience.com
May 23, 2025 at 3:47 PM
@salvatoreraieli.bsky.social explores how meta-learning helps CNNs grasp abstract relationships like "same-different," bridging the gap between human and machine vision.
Reposted by Salvatore Raieli
Can AI learn to think like us? @salvatoreraieli.bsky.social explores how meta-learning helps CNNs grasp abstract relationships like "same-different," bridging the gap between human and machine vision.
The Basis of Cognitive Complexity: Teaching CNNs to See Connections | Towards Data Science
Transforming CNNs: From task-specific learning to abstract generalization
towardsdatascience.com
May 21, 2025 at 4:23 PM
Can AI learn to think like us? @salvatoreraieli.bsky.social explores how meta-learning helps CNNs grasp abstract relationships like "same-different," bridging the gap between human and machine vision.
Reposted by Salvatore Raieli
Can AI learn to think like us? @salvatoreraieli.bsky.social explores how meta-learning helps CNNs grasp abstract relationships like "same-different," bridging the gap between human and machine vision.
The Basis of Cognitive Complexity: Teaching CNNs to See Connections | Towards Data Science
Transforming CNNs: From task-specific learning to abstract generalization
towardsdatascience.com
May 11, 2025 at 3:27 PM
Can AI learn to think like us? @salvatoreraieli.bsky.social explores how meta-learning helps CNNs grasp abstract relationships like "same-different," bridging the gap between human and machine vision.
This survey classifies LLM reasoning by when it occurs (inference or training) and system type (standalone or agentic), highlighting trends like learning-to-reason and agent-based workflows, with methods like prompt tuning, output refinement, and PPO.
arxiv.org/abs/2504.09037
arxiv.org/abs/2504.09037
A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems
Reasoning is a fundamental cognitive process that enables logical inference, problem-solving, and decision-making. With the rapid advancement of large language models (LLMs), reasoning has emerged as ...
arxiv.org
May 9, 2025 at 5:42 PM
This survey classifies LLM reasoning by when it occurs (inference or training) and system type (standalone or agentic), highlighting trends like learning-to-reason and agent-based workflows, with methods like prompt tuning, output refinement, and PPO.
arxiv.org/abs/2504.09037
arxiv.org/abs/2504.09037
Reposted by Salvatore Raieli
Can AI learn to think like us? 🤔 This new article by @salvatoreraieli.bsky.social explores how meta-learning helps CNNs grasp abstract relationships like "same-different," bridging the gap between human and machine vision.
The Basis of Cognitive Complexity: Teaching CNNs to See Connections | Towards Data Science
Transforming CNNs: From task-specific learning to abstract generalization
towardsdatascience.com
April 12, 2025 at 3:27 PM
Can AI learn to think like us? 🤔 This new article by @salvatoreraieli.bsky.social explores how meta-learning helps CNNs grasp abstract relationships like "same-different," bridging the gap between human and machine vision.
The Basis of Cognitive Complexity: Teaching CNNs to See Connections
Transforming CNNs: From task-specific learning to abstract generalization
towardsdatascience.com/the-basis-of...
thanks @towardsdatascience.com to publish my latest article
Transforming CNNs: From task-specific learning to abstract generalization
towardsdatascience.com/the-basis-of...
thanks @towardsdatascience.com to publish my latest article
The Basis of Cognitive Complexity: Teaching CNNs to See Connections | Towards Data Science
Transforming CNNs: From task-specific learning to abstract generalization
towardsdatascience.com
April 11, 2025 at 4:45 PM
The Basis of Cognitive Complexity: Teaching CNNs to See Connections
Transforming CNNs: From task-specific learning to abstract generalization
towardsdatascience.com/the-basis-of...
thanks @towardsdatascience.com to publish my latest article
Transforming CNNs: From task-specific learning to abstract generalization
towardsdatascience.com/the-basis-of...
thanks @towardsdatascience.com to publish my latest article
Only the Beginning Matters: How the LLM Decides Where to Focus Attention
Understanding How the First Token Shapes LLM’s Focus and Responses
levelup.gitconnected.com/only-the-beg...
Understanding How the First Token Shapes LLM’s Focus and Responses
levelup.gitconnected.com/only-the-beg...
Only the Beginning Matters: How the LLM Decides Where to Focus Attention
Understanding How the First Token Shapes LLM’s Focus and Responses
levelup.gitconnected.com
April 11, 2025 at 4:44 PM
Only the Beginning Matters: How the LLM Decides Where to Focus Attention
Understanding How the First Token Shapes LLM’s Focus and Responses
levelup.gitconnected.com/only-the-beg...
Understanding How the First Token Shapes LLM’s Focus and Responses
levelup.gitconnected.com/only-the-beg...
Reposted by Salvatore Raieli
If you (like me) are brushing up on your #python plotting using #matplotlib or #seaborn, check out the python graph gallery by Yan Holtz: python-graph-gallery.com Being more versed in R, I've found it hard to find others using python (but the #PydyTuesday hash helps). 🙋🏻♀️ Say hi if that's you! #databs
Python Graph Gallery
The Python Graph Gallery displays hundreds of charts made with Python, always with explanation and reproduciible code
python-graph-gallery.com
April 10, 2025 at 5:23 PM
If you (like me) are brushing up on your #python plotting using #matplotlib or #seaborn, check out the python graph gallery by Yan Holtz: python-graph-gallery.com Being more versed in R, I've found it hard to find others using python (but the #PydyTuesday hash helps). 🙋🏻♀️ Say hi if that's you! #databs
Sadly realizing that the Italian expression "conosco i miei polli" ("I know who I'm dealing with", literal translation: "I know my chickens") cannot be used in English. is a pity because this expression conveys well how someone is expected to do something stupid
April 4, 2025 at 5:59 PM
Sadly realizing that the Italian expression "conosco i miei polli" ("I know who I'm dealing with", literal translation: "I know my chickens") cannot be used in English. is a pity because this expression conveys well how someone is expected to do something stupid
Thinking Machines: A Survey of LLM based Reasoning Strategies
This survey offers an overview and comparison of current reasoning techniques and presents a systematic review of reasoning-imbued language models.
arxiv.org/abs/2503.10814
This survey offers an overview and comparison of current reasoning techniques and presents a systematic review of reasoning-imbued language models.
arxiv.org/abs/2503.10814
Thinking Machines: A Survey of LLM based Reasoning Strategies
Large Language Models (LLMs) are highly proficient in language-based tasks. Their language capabilities have positioned them at the forefront of the future AGI (Artificial General Intelligence) race. ...
arxiv.org
April 1, 2025 at 11:57 AM
Thinking Machines: A Survey of LLM based Reasoning Strategies
This survey offers an overview and comparison of current reasoning techniques and presents a systematic review of reasoning-imbued language models.
arxiv.org/abs/2503.10814
This survey offers an overview and comparison of current reasoning techniques and presents a systematic review of reasoning-imbued language models.
arxiv.org/abs/2503.10814
Reposted by Salvatore Raieli
"Now that all mouths are burned, no one should be satiated. Let all lips be withdrawn and one last knowing grin remain for all after all vanities have evaporated."
Today on ergot.: 'Rye Dance' by Salvatore Raieli @salvatoreraieli.bsky.social
www.ergot.press/authors/Salv...
Today on ergot.: 'Rye Dance' by Salvatore Raieli @salvatoreraieli.bsky.social
www.ergot.press/authors/Salv...
ergot.
innovative + experimental horror
www.ergot.press
March 21, 2025 at 7:17 PM
"Now that all mouths are burned, no one should be satiated. Let all lips be withdrawn and one last knowing grin remain for all after all vanities have evaporated."
Today on ergot.: 'Rye Dance' by Salvatore Raieli @salvatoreraieli.bsky.social
www.ergot.press/authors/Salv...
Today on ergot.: 'Rye Dance' by Salvatore Raieli @salvatoreraieli.bsky.social
www.ergot.press/authors/Salv...
Thank you @ergot.bsky.social for publishing my work
"Take my hands as I stumble through the dress’ train, gather with me the ears of corn that gave us bread. Feel again the fragrance of rye as the clouds begin the dance."
Today on ergot.: 'Rye Dance' the fiction debut of Salvatore Raieli @salvatoreraieli.bsky.social
www.ergot.press/authors/Salv...
Today on ergot.: 'Rye Dance' the fiction debut of Salvatore Raieli @salvatoreraieli.bsky.social
www.ergot.press/authors/Salv...
ergot.
innovative + experimental horror
www.ergot.press
March 21, 2025 at 4:04 PM
Thank you @ergot.bsky.social for publishing my work
The Socratic AI: Knows Others, But Not Itself
How Language Models Excel at Prediction but Fail at Introspection
levelup.gitconnected.com/the-socratic...
How Language Models Excel at Prediction but Fail at Introspection
levelup.gitconnected.com/the-socratic...
The Socratic AI: Knows Others, But Not Itself
How Language Models Excel at Prediction but Fail at Introspection
levelup.gitconnected.com
March 21, 2025 at 11:54 AM
The Socratic AI: Knows Others, But Not Itself
How Language Models Excel at Prediction but Fail at Introspection
levelup.gitconnected.com/the-socratic...
How Language Models Excel at Prediction but Fail at Introspection
levelup.gitconnected.com/the-socratic...
5 Haikus of Artificial Intelligence
The inner poetry of artificial intelligence
medium.com/data-science...
The inner poetry of artificial intelligence
medium.com/data-science...
5 Haikus of Artificial Intelligence
The inner poetry of artificial intelligence
medium.com
March 21, 2025 at 11:53 AM
5 Haikus of Artificial Intelligence
The inner poetry of artificial intelligence
medium.com/data-science...
The inner poetry of artificial intelligence
medium.com/data-science...
Reposted by Salvatore Raieli
Tomorrow on ergot.: Seven new Rye Dances from Salvatore Raieli @salvatoreraieli.bsky.social, a debut fiction publication.
March 20, 2025 at 9:57 PM
Tomorrow on ergot.: Seven new Rye Dances from Salvatore Raieli @salvatoreraieli.bsky.social, a debut fiction publication.
TxAgent is an AI-driven system that assesses drug interactions, contraindications, and patient-specific data to create adaptive treatment plans.
zitniklab.hms.harvard.edu/TxAgent/
zitniklab.hms.harvard.edu/TxAgent/
TxAgent
An AI Agent for therapeutic reasoning across a universe of tools
zitniklab.hms.harvard.edu
March 18, 2025 at 2:01 PM
TxAgent is an AI-driven system that assesses drug interactions, contraindications, and patient-specific data to create adaptive treatment plans.
zitniklab.hms.harvard.edu/TxAgent/
zitniklab.hms.harvard.edu/TxAgent/
Are Open Models Really Open?
Many AI models labeled as "open" come with restrictive licensing terms. Google's new models and similar releases from Meta raise concerns about commercial limitations, which could affect smaller companies that depend on these technologies.
techcrunch.com/2025/03/14/o...
Many AI models labeled as "open" come with restrictive licensing terms. Google's new models and similar releases from Meta raise concerns about commercial limitations, which could affect smaller companies that depend on these technologies.
techcrunch.com/2025/03/14/o...
'Open' AI model licenses often carry concerning restrictions | TechCrunch
'Open' model releases from Google, Meta, and others have onerous terms that make some companies wary of using them.
techcrunch.com
March 17, 2025 at 1:59 PM
Are Open Models Really Open?
Many AI models labeled as "open" come with restrictive licensing terms. Google's new models and similar releases from Meta raise concerns about commercial limitations, which could affect smaller companies that depend on these technologies.
techcrunch.com/2025/03/14/o...
Many AI models labeled as "open" come with restrictive licensing terms. Google's new models and similar releases from Meta raise concerns about commercial limitations, which could affect smaller companies that depend on these technologies.
techcrunch.com/2025/03/14/o...