cackerman21

🏔️⛷️🎸 Encryption, Data Science, Linux, OSINT, RedTeam, SysAdmin, Energy, view not my own-ish, sui ipsius doctrine

[cackerman21 @cackerman21]

MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use

https://t.co/2D5P0ajoI0

#LLM

[cackerman21 @cackerman21]

Large Language Models and How To Use Them

https://t.co/tsh3bV60BJ

[cackerman21 @cackerman21]

Apple trained a large language model to efficiently understand long-form video

https://t.co/naai4HiORv

[cackerman21 @cackerman21]

Estimating the historical impact of outbreak response immunisation programmes across 210 outbreaks in low and middle-income countries

https://t.co/nl7tiEk4RH

https://t.co/wRV9BGdOiy

[cackerman21 @cackerman21]

Using ai (wav2vec) to revived a dying language

https://t.co/YWpCozX8Ce

https://t.co/wOJQI99sCO

[cackerman21 @cackerman21]

Journalism, media, and technology trends and predictions 2025

https://t.co/G3NGrIm7pE

[cackerman21 @cackerman21]

Looming Commercial Real Estate (CRE) Exposure Debt Crisis 2025-27 - Maturity Wall

Dime Bank: CRE exposure equal to 602% of its equity
Eagle: 571%
OZK: 566%
Live Oak: 550%
Merchants: 539%
Flagstar: 539%
ServisFirst: 538%
First Foundation: 513%
Provident: 488%
First United: 478%

[cackerman21 @cackerman21]

Three Pointers for Effective and Accurate LLM Integration

https://t.co/O5zZ8ZD3hB

[cackerman21 @cackerman21]

Off-the-Shelf Large Language Models Are Unreliable Judges

https://t.co/coimlWoK8N

[cackerman21 @cackerman21]

Poster: Leveraging Large Language Models for Detecting OS-level Ransomware

https://t.co/Aqq4wFjXHS

[cackerman21 @cackerman21]

Table meets LLM: Can Large Language Models Understand
Empirical Study Structured Table Data?

A Benchmark and Empirical Study

https://t.co/bzjjbCorg3

[cackerman21 @cackerman21]

Replication for Language Models

Problems, Principles, and Best Practices for Political Science

https://t.co/T0ekU9sSTx

[cackerman21 @cackerman21]

Red Hat AI Inference Server 3.0

LLM Compressor

Compressing large language models with the LLM Compressor library

https://t.co/xOTprGChoC

[cackerman21 @cackerman21]

Balancing Innovation and Rigor: Guidance for the Thoughtful
Integration of Artificial Intelligence for Evaluation

https://t.co/XPx5CQcY3f

[cackerman21 @cackerman21]

Tele-LLMs: A Series of Specialized Large Language Models for Telecommunications

https://t.co/HLO8Wjc9Ce

[cackerman21 @cackerman21]

DCE-LLM: Dead Code Elimination with Large Language Models

https://t.co/yYDaCHZPrg

[cackerman21 @cackerman21]

HealthBench: Evaluating Large Language Models Towards Improved Human Health

https://t.co/tRAUf78m3a

[cackerman21 @cackerman21]

Do Large Language Models (Really) Need Statistical Foundations?

https://t.co/zuCwEy6yQF

[cackerman21 @cackerman21]

BankGPT: the use of Large Language Models in official
communications

https://t.co/yaVoxUy5Dd

[cackerman21 @cackerman21]

Soft Prompting for Unlearning in Large Language Models

https://t.co/9ojmhsHHDf