JPCreedon Profile Banner
JP Creedon Profile
JP Creedon

@JPCreedon

Followers
543
Following
110
Media
18
Statuses
866

AA3fsZjdLFfhoPvRDcjQuw86Vzo8hfVFgTGL6rcdYtij

Mars?
Joined March 2009
Don't wanna be here? Send us removal request.
@JPCreedon
JP Creedon
@JPCreedon
2 days
https://t.co/nNVa1jmXFE
Tweet card summary image
azure.microsoft.com
Learn how we're combining the power of SQL and Fabric to create a platform that unifies transactional, operational, and analytical data.
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
2 days
https://t.co/kOzDtH0G3y
Tweet card summary image
infoq.com
Joy Ebertz, Principal Engineer at Imprint, presented at QCon London 2026 a groundbreaking framework for prioritizing technical debt amidst rapid AI-driven code production. By challenging perfection...
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
10 days
https://t.co/IgPsWXMOtC
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
1 month
https://t.co/3K6N9lL0Hh
Tweet card summary image
xda-developers.com
No I don't know what I'm doing, but that's what Claude is for
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
2 months
https://t.co/X28v7o4uUb
Tweet card summary image
infoq.com
The Gradio team has released Daggr, a new open-source Python library designed to simplify the construction and debugging of multi-step AI workflows. Daggr allows developers to define workflows...
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
2 months
https://t.co/EB7i0J1ur5
Tweet card summary image
venturebeat.com
1,800 exposed instances leak API keys and credentials. Agents operate inside authorized permissions where firewalls can't see. Traditional security models weren't built for this. Your developers are...
1
0
0
@JPCreedon
JP Creedon
@JPCreedon
2 months
https://t.co/IqlTY4mSFg
1
0
1
@JPCreedon
JP Creedon
@JPCreedon
2 months
https://t.co/RPXQLjbDkw
Tweet card summary image
venturebeat.com
While standard models suffer from context rot as data grows, MIT’s new Recursive Language Model (RLM) framework treats prompts like code variables, unlocking infinite context without the retraining...
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
2 months
https://t.co/n7twBnnZAl
Tweet card summary image
kaggle.com
A Historical Timeline of the World's Most Influential Programming Languages
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
2 months
https://t.co/9fcqPPzXO9
Tweet card summary image
arxiv.org
When not using reasoning, repeating the input prompt improves performance for popular models (Gemini, GPT, Claude, and Deepseek) without increasing the number of generated tokens or latency.
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
2 months
https://t.co/Ey4lMAj08z
Tweet card summary image
marktechpost.com
Meta and Harvard Researchers Introduce the Confucius Code Agent (CCA): A Software Engineering Agent that can Operate at Large-Scale Codebases
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
3 months
https://t.co/IgkoKuSvYp
Tweet card summary image
infoq.com
IBM Research has released CUGA (Configurable Generalist Agent) on Hugging Face Spaces, making its enterprise-oriented agent framework easier to evaluate with open models and real workflows. The move...
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
3 months
https://t.co/MivQWZNjTw
Tweet card summary image
pub.towardsai.net
A Practical Guide to training Graph Neural Networks with Knowledge Graphs for extracting node embedding.
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
4 months
https://t.co/irhAgvrpHR
Tweet card summary image
towardsdatascience.com
This first day of the Advent Calendar introduces the k-NN regressor, the simplest distance-based model. Using Excel, we explore how predictions rely entirely on the closest observations, why feature...
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
4 months
Gemini 3.0 also very good.
0
0
0
@elonmusk
Elon Musk
@elonmusk
4 months
This is actually a major Grok upgrade, but we decided to release it quietly this time. Gave us time to smooth out the rough edges.
@MarioNawfal
Mario Nawfal
@MarioNawfal
4 months
GROK JUST GOT A WHOLE LOT SMARTER xAI quietly patched Grok-4-Fast... and the before/after is wild. “Reasoning” mode jumped from 77.5% to 94.1% complete responses. “Non-reasoning”? Up to a staggering 97.9%. All thanks to one thing: better injected system prompts. No press
7K
7K
59K
@JPCreedon
JP Creedon
@JPCreedon
5 months
https://t.co/Vs0bv24Hiv
Tweet card summary image
github.blog
At Universe 2025, GitHub's next evolution introduces a single, unified workflow for developers to be able to orchestrate any agent, any time, anywhere.
0
0
1
@JPCreedon
JP Creedon
@JPCreedon
5 months
https://t.co/fPQUXDSbgX
Tweet card summary image
chipsandcheese.com
Strix Halo is the codename for AMD’s highest end mobile chip, which is used in the Ryzen AI MAX series.
0
0
1
@JPCreedon
JP Creedon
@JPCreedon
5 months
https://t.co/KLe7IHms5A
nature.com
Scientific Reports - Multimodal prototypical network for interpretable sentiment classification
0
0
0
@JPCreedon
JP Creedon
@JPCreedon
5 months
https://t.co/JGdiW8u3AM
marktechpost.com
PokeeResearch-7B: An Open 7B deep-research agent trained with Reinforcement Learning from AI Feedback RLAIF and a robust reasoning scaffold
0
0
0