"Agentic Code Generation with GRPO on Amazon SageMaker" by Amit
#agentic-ai #agentic-interactions #ai-engineering #ai-for-developers #ai-agents
#agentic-ai #agentic-interactions #ai-engineering #ai-for-developers #ai-agents
Agentic Code Generation with GRPO on Amazon SageMaker
Fine-tune a 1.5B model to write, run, and iterate on Python code using RL. GRPO training on a single SageMaker GPU for under $8. +152% on hard coding tasks.
community.aws
September 25, 2026 at 10:30 AM
"Agentic Code Generation with GRPO on Amazon SageMaker" by Amit
#agentic-ai #agentic-interactions #ai-engineering #ai-for-developers #ai-agents
#agentic-ai #agentic-interactions #ai-engineering #ai-for-developers #ai-agents
"Breaking Down the Agentic AI Stack: From Prompts to Autonomous Multi-Agent Toolkits" by Balasai. Modepalli
#agents #agentic-ai #agent-toolkit #agent-to-agent #agentic-interactions
#agents #agentic-ai #agent-toolkit #agent-to-agent #agentic-interactions
Breaking Down the Agentic AI Stack: From Prompts to Autonomous Multi-Agent Toolkits
Explore how modern software engineering is transitioning from basic prompt interfaces to intent-driven agentic architectures that actively use tools and orchestrate complex technical workflows.
community.aws
September 23, 2026 at 2:00 PM
"Breaking Down the Agentic AI Stack: From Prompts to Autonomous Multi-Agent Toolkits" by Balasai. Modepalli
#agents #agentic-ai #agent-toolkit #agent-to-agent #agentic-interactions
#agents #agentic-ai #agent-toolkit #agent-to-agent #agentic-interactions
Morten Roed Frederiksen: Toward Self-Repairing Ubiquitous Robots Using Goal-Oriented Agentic AI in Human-Robot Interactions https://arxiv.org/abs/2609.26155 https://arxiv.org/pdf/2609.26155 https://arxiv.org/html/2609.26155
September 23, 2026 at 6:45 AM
Morten Roed Frederiksen: Toward Self-Repairing Ubiquitous Robots Using Goal-Oriented Agentic AI in Human-Robot Interactions https://arxiv.org/abs/2609.26155 https://arxiv.org/pdf/2609.26155 https://arxiv.org/html/2609.26155
I'm not sure why, but publications keep mistakenly claiming that the "learning gap" refers to "people and organizations not learning how to use these things," when it refers to thte models THEMSELVES being incapable of learning. The report is VERY CLEAR about this.
web.archive.org/web/20250818...
web.archive.org/web/20250818...
August 21, 2025 at 8:12 PM
I'm not sure why, but publications keep mistakenly claiming that the "learning gap" refers to "people and organizations not learning how to use these things," when it refers to thte models THEMSELVES being incapable of learning. The report is VERY CLEAR about this.
web.archive.org/web/20250818...
web.archive.org/web/20250818...
Agentic AI’s interactions with the physical world are through intermediaries. Much of their “inner” activity is opaque to an ordinary person looking from the outside in. though humans build AI is it smart to anthropomorphize AI entities instead of establishing a unique theory of mind?
September 23, 2026 at 4:34 PM
Agentic AI’s interactions with the physical world are through intermediaries. Much of their “inner” activity is opaque to an ordinary person looking from the outside in. though humans build AI is it smart to anthropomorphize AI entities instead of establishing a unique theory of mind?
"Getting Started with AWS: A Beginner's Guide to Building in the Cloud" by Yashansh Srivastava
#agents #agentic-interactions #agentic-ai #advertising-marketing-industry
#agents #agentic-interactions #agentic-ai #advertising-marketing-industry
Getting Started with AWS: A Beginner's Guide to Building in the Cloud
Learn the fundamentals of AWS, explore essential cloud services, and understand how to build, secure, and deploy your first cloud-based application.
community.aws
September 22, 2026 at 1:00 PM
"Getting Started with AWS: A Beginner's Guide to Building in the Cloud" by Yashansh Srivastava
#agents #agentic-interactions #agentic-ai #advertising-marketing-industry
#agents #agentic-interactions #agentic-ai #advertising-marketing-industry
Morten Roed Frederiksen
Toward Self-Repairing Ubiquitous Robots Using Goal-Oriented Agentic AI in Human-Robot Interactions
https://arxiv.org/abs/2609.26155
Toward Self-Repairing Ubiquitous Robots Using Goal-Oriented Agentic AI in Human-Robot Interactions
https://arxiv.org/abs/2609.26155
September 24, 2026 at 2:34 PM
Morten Roed Frederiksen
Toward Self-Repairing Ubiquitous Robots Using Goal-Oriented Agentic AI in Human-Robot Interactions
https://arxiv.org/abs/2609.26155
Toward Self-Repairing Ubiquitous Robots Using Goal-Oriented Agentic AI in Human-Robot Interactions
https://arxiv.org/abs/2609.26155
"The Future of Agentic AI: When AI Stops Answering and Starts Acting" by RAUNAK CHAKRABORTY
#ai-agents #agentic-ai #ai #agent-to-agent #agentic-interactions
#ai-agents #agentic-ai #ai #agent-to-agent #agentic-interactions
The Future of Agentic AI: When AI Stops Answering and Starts Acting
futuristic, and technically interesting without sounding like generic AI content.
community.aws
September 19, 2026 at 6:00 AM
"The Future of Agentic AI: When AI Stops Answering and Starts Acting" by RAUNAK CHAKRABORTY
#ai-agents #agentic-ai #ai #agent-to-agent #agentic-interactions
#ai-agents #agentic-ai #ai #agent-to-agent #agentic-interactions
The first release isn't the finish line - it's the starting pistol.
We ship. We learn. We adapt. It's the "Learn. Adapt." part that turns base metals into gold.
Agentic coding can hamper learning and adapting, and most teams have walked into this trap.
codemanship.wordpress.com/2026/09/03/t...
We ship. We learn. We adapt. It's the "Learn. Adapt." part that turns base metals into gold.
Agentic coding can hamper learning and adapting, and most teams have walked into this trap.
codemanship.wordpress.com/2026/09/03/t...
The Ultimate Equation about AI Coding
There are some useful mathematical models relating to LLM-assisted and agentic software development, like my formula for the reliability of model interactions (“steps”) in an agentic wo…
codemanship.wordpress.com
September 3, 2026 at 6:04 AM
The first release isn't the finish line - it's the starting pistol.
We ship. We learn. We adapt. It's the "Learn. Adapt." part that turns base metals into gold.
Agentic coding can hamper learning and adapting, and most teams have walked into this trap.
codemanship.wordpress.com/2026/09/03/t...
We ship. We learn. We adapt. It's the "Learn. Adapt." part that turns base metals into gold.
Agentic coding can hamper learning and adapting, and most teams have walked into this trap.
codemanship.wordpress.com/2026/09/03/t...
The deployment of AI agents is producing interactions and outcomes of unprecedented complexity, write Natàlia Fernández Ashman and Marta Bieńkiewicz from the Cooperative AI Foundation. As Europe advances its sovereignty ambitions, it needs to anchor AI deployment in safety and public oversight.
A Wake-Up Call for Governance of Multi-Agent AI Interactions | TechPolicy.Press
The deployment of agentic AI systems is producing interactions and outcomes of unprecedented complexity, write Natàlia Fernández Ashman and Marta Bieńkiewicz.
buff.ly
August 28, 2025 at 7:01 PM
The deployment of AI agents is producing interactions and outcomes of unprecedented complexity, write Natàlia Fernández Ashman and Marta Bieńkiewicz from the Cooperative AI Foundation. As Europe advances its sovereignty ambitions, it needs to anchor AI deployment in safety and public oversight.
This role comes out most clearly in stories where God’s actions are treated as something that “just happens,” without interactions with God as a moral or agentic being, let alone anything resembling a moral reflection on God’s choices.
June 19, 2025 at 3:53 PM
This role comes out most clearly in stories where God’s actions are treated as something that “just happens,” without interactions with God as a moral or agentic being, let alone anything resembling a moral reflection on God’s choices.
Unlike board games, real-world strategic interactions are messy. Traditional game theory thus needs a boost for the age of agentic AI. Our #AAMAS2026 workshop "Strategic Engineering"(sites.google.com/view/se-aama...) in Cyprus aims to bridge the gap. Come join us to unlock truly strategic AI!
December 18, 2025 at 10:56 AM
Unlike board games, real-world strategic interactions are messy. Traditional game theory thus needs a boost for the age of agentic AI. Our #AAMAS2026 workshop "Strategic Engineering"(sites.google.com/view/se-aama...) in Cyprus aims to bridge the gap. Come join us to unlock truly strategic AI!
Flock is hiring a software developer to build "high-performance integration pipelines connecting Nightshift to Flock's massive data platform, and build the agentic framework that allows Nightshift to 'act' on behalf of investigators." @josephcox.bsky.social
July 28, 2026 at 9:02 PM
Flock is hiring a software developer to build "high-performance integration pipelines connecting Nightshift to Flock's massive data platform, and build the agentic framework that allows Nightshift to 'act' on behalf of investigators." @josephcox.bsky.social
Design effective WebMCP tools to help AI agents complete users' workflows→ goo.gle/4ixF7eG
Follow our practical framework to map user goals, define application states, and role-play scenarios to support agentic interactions.
Follow our practical framework to map user goals, define application states, and role-play scenarios to support agentic interactions.
September 18, 2026 at 2:03 PM
Design effective WebMCP tools to help AI agents complete users' workflows→ goo.gle/4ixF7eG
Follow our practical framework to map user goals, define application states, and role-play scenarios to support agentic interactions.
Follow our practical framework to map user goals, define application states, and role-play scenarios to support agentic interactions.
State of AI: An Empirical 100 Trillion Token Study with OpenRouter
"In our empirical study, we observe substantial adoption of open-weight models, the outsized popularity of creative roleplay and coding assistance categories, plus the rise of agentic inference."
"In our empirical study, we observe substantial adoption of open-weight models, the outsized popularity of creative roleplay and coding assistance categories, plus the rise of agentic inference."
State of AI | OpenRouter
An empirical study analyzing over 100 trillion tokens of real-world LLM interactions across tasks, geographies, and time.
openrouter.ai
December 5, 2025 at 1:19 AM
State of AI: An Empirical 100 Trillion Token Study with OpenRouter
"In our empirical study, we observe substantial adoption of open-weight models, the outsized popularity of creative roleplay and coding assistance categories, plus the rise of agentic inference."
"In our empirical study, we observe substantial adoption of open-weight models, the outsized popularity of creative roleplay and coding assistance categories, plus the rise of agentic inference."
Morten Roed Frederiksen: Toward Self-Repairing Ubiquitous Robots Using Goal-Oriented Agentic AI in Human-Robot Interactions https://arxiv.org/abs/2609.26155 https://arxiv.org/pdf/2609.26155 https://arxiv.org/html/2609.26155
September 24, 2026 at 6:45 AM
Morten Roed Frederiksen: Toward Self-Repairing Ubiquitous Robots Using Goal-Oriented Agentic AI in Human-Robot Interactions https://arxiv.org/abs/2609.26155 https://arxiv.org/pdf/2609.26155 https://arxiv.org/html/2609.26155
Thinking Machines: Interaction Models
A new class of LLM, this is an agentic model focused entirely on seamless interactions. It knows how to keep you engaged while it goes off and does other work
thinkingmachines.ai/blog/interac...
A new class of LLM, this is an agentic model focused entirely on seamless interactions. It knows how to keep you engaged while it goes off and does other work
thinkingmachines.ai/blog/interac...
May 11, 2026 at 11:57 PM
Thinking Machines: Interaction Models
A new class of LLM, this is an agentic model focused entirely on seamless interactions. It knows how to keep you engaged while it goes off and does other work
thinkingmachines.ai/blog/interac...
A new class of LLM, this is an agentic model focused entirely on seamless interactions. It knows how to keep you engaged while it goes off and does other work
thinkingmachines.ai/blog/interac...
Here's my dumb little workflow runner that's running a planning and implementation workflow, a mix of agentic interactions and deterministic code. Goal is that you can report Chatto bugs to it and if it agrees it's a bug, it'll make a PR and ping me (and then probably delete my hard drive)
September 9, 2026 at 4:31 PM
Here's my dumb little workflow runner that's running a planning and implementation workflow, a mix of agentic interactions and deterministic code. Goal is that you can report Chatto bugs to it and if it agrees it's a bug, it'll make a PR and ping me (and then probably delete my hard drive)
Powerful information processing and pattern matching; things are going to get FUN when "agentic" becomes commonplace: it will initiate contact, remember your vulnerabilities, optimize for keeping you engaged across multiple interactions, "insights" tailored to your specific psychological profile.
July 23, 2025 at 7:51 PM
Powerful information processing and pattern matching; things are going to get FUN when "agentic" becomes commonplace: it will initiate contact, remember your vulnerabilities, optimize for keeping you engaged across multiple interactions, "insights" tailored to your specific psychological profile.
The deployment of AI agents is producing interactions and outcomes of unprecedented complexity, write Natàlia Fernández Ashman and Marta Bieńkiewicz from the Cooperative AI Foundation. As Europe advances its sovereignty ambitions, it needs to anchor AI deployment in safety and public oversight.
A Wake-Up Call for Governance of Multi-Agent AI Interactions | TechPolicy.Press
The deployment of agentic AI systems is producing interactions and outcomes of unprecedented complexity, write Natàlia Fernández Ashman and Marta Bieńkiewicz.
www.techpolicy.press
August 25, 2025 at 1:34 PM
The deployment of AI agents is producing interactions and outcomes of unprecedented complexity, write Natàlia Fernández Ashman and Marta Bieńkiewicz from the Cooperative AI Foundation. As Europe advances its sovereignty ambitions, it needs to anchor AI deployment in safety and public oversight.
Begging journalists reporting on agentic AI to be just a little less credulous and ask just a few more questions instead of reprinting company marketing materials
We don’t have evidence that an agentic AI could have the kinds of meaningful interactions students would want from their instructors
We don’t have evidence that an agentic AI could have the kinds of meaningful interactions students would want from their instructors
“AI organizations are now touting the rollout of ‘AI agents.’ Educators can train these AI agents on their own course materials, transforming them into AI clones of the instructor that can interact with students 24-7.“ 💀
Universities must beware of reliance on big AI (opinion)
Building reliance on Silicon Valley AI companies carries risks, Collin Bjork writes.
www.insidehighered.com
December 2, 2024 at 8:46 PM
Begging journalists reporting on agentic AI to be just a little less credulous and ask just a few more questions instead of reprinting company marketing materials
We don’t have evidence that an agentic AI could have the kinds of meaningful interactions students would want from their instructors
We don’t have evidence that an agentic AI could have the kinds of meaningful interactions students would want from their instructors
- Agent RL Algorithms: Enables the model to learn from complex, long-horizon interactions more effectively
Paper: arxiv.org/abs/2602.15763
Paper: arxiv.org/abs/2602.15763
GLM-5: from Vibe Coding to Agentic Engineering
We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of i...
arxiv.org
February 18, 2026 at 3:09 AM
- Agent RL Algorithms: Enables the model to learn from complex, long-horizon interactions more effectively
Paper: arxiv.org/abs/2602.15763
Paper: arxiv.org/abs/2602.15763
Defending Brokerages Against Rogue AI Agents in Houston
In the fast-paced real estate market of Houston, brokerage teams are increasingly turning to agentic AI to enhance efficiency and client interactions. However, the rise of rogue AI agents and the threat of agentjacking pose significant risk
In the fast-paced real estate market of Houston, brokerage teams are increasingly turning to agentic AI to enhance efficiency and client interactions. However, the rise of rogue AI agents and the threat of agentjacking pose significant risk
Defending Brokerages Against Rogue AI Agents in Houston
In the fast-paced real estate market of Houston, brokerage teams are increasingly turning to agentic AI to enhance efficiency and client interactions. However, the rise of rogue AI agents and the threat of agentjacking pose significant risk
pi.apibroker-wise.com
September 25, 2026 at 5:04 PM
Defending Brokerages Against Rogue AI Agents in Houston
In the fast-paced real estate market of Houston, brokerage teams are increasingly turning to agentic AI to enhance efficiency and client interactions. However, the rise of rogue AI agents and the threat of agentjacking pose significant risk
In the fast-paced real estate market of Houston, brokerage teams are increasingly turning to agentic AI to enhance efficiency and client interactions. However, the rise of rogue AI agents and the threat of agentjacking pose significant risk
Whoah, a dejavu scifi experience, alike to what we had back when reasoning traces became a thing for the first time. But here an agentic LLM updates its own knowledge graph realtime, based on interactions with humans. Spooky!! Cool!!
genuinely a fascinating exchange, this man is debugging an LLM agent in public
July 21, 2025 at 4:35 PM
Whoah, a dejavu scifi experience, alike to what we had back when reasoning traces became a thing for the first time. But here an agentic LLM updates its own knowledge graph realtime, based on interactions with humans. Spooky!! Cool!!