#agentic — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #agentic, aggregated by home.social.
-
Tinkering with Pi in Docker – it’s surprisingly fun to build with your own agent!
This past month I've been diving head first into using a agentic coding harness and it's been a lot of fun! I decided to go trying out #pi from pi.dev for several reasons:
- I like the philosophy of building a coding agent the way *you* want it. Plus I love customization! 😁
- As a fellow tinkerer and builder I really like to understand how code and processes work behind the scenes; pi allows me to see the output as it builds.
- It's minimalistic. When you install it, it doesn't come with much of anything but a few basic tools. You can install (or even ask it to build!) the extensions, skills, prompts that you want. It also has significantly lower number system prompt tokens. compared to other popular coding agents too.
- You can use whatever models you want and as user of Local AI models I can easily hook up my models from llama.cpp.I'm really liking my experience with pi so far and I see why it's considered the *developer's* coding agent. If you are comfortable with code and the terminal, Pi is great tool to work with!
As I'm getting familar with coding using a coding agent harness like Pi, I got this running in a plain Docker container until I get use to it as I don't want to go accidently deleting important data or even my computer until I get the hang of it 😅
#ai #localai #pi #codingagent #buildinpublic #agentic #docker #llama #claude #codex #claudecode #coding #openclaw #agenticcoding
-
Tinkering with Pi in Docker – it’s surprisingly fun to build with your own agent!
This past month I've been diving head first into using a agentic coding harness and it's been a lot of fun! I decided to go trying out #pi from pi.dev for several reasons:
- I like the philosophy of building a coding agent the way *you* want it. Plus I love customization! 😁
- As a fellow tinkerer and builder I really like to understand how code and processes work behind the scenes; pi allows me to see the output as it builds.
- It's minimalistic. When you install it, it doesn't come with much of anything but a few basic tools. You can install (or even ask it to build!) the extensions, skills, prompts that you want. It also has significantly lower number system prompt tokens. compared to other popular coding agents too.
- You can use whatever models you want and as user of Local AI models I can easily hook up my models from llama.cpp.I'm really liking my experience with pi so far and I see why it's considered the *developer's* coding agent. If you are comfortable with code and the terminal, Pi is great tool to work with!
As I'm getting familar with coding using a coding agent harness like Pi, I got this running in a plain Docker container until I get use to it as I don't want to go accidently deleting important data or even my computer until I get the hang of it 😅
#ai #localai #pi #codingagent #buildinpublic #agentic #docker #llama #claude #codex #claudecode #coding #openclaw #agenticcoding
-
#Anthropic publishes a #CISO guide to #Agentic #AI! According to it the goal isn't zero risk, but making risk legible & bounded.
Evaluate agents by tracking untrusted content, identity, blast radius and observability.
Read the guide:
#AgenticAI
👇
https://claude.com/blog/ciso-guide-to-agentic-ai -
#Anthropic publishes a #CISO guide to #Agentic #AI! According to it the goal isn't zero risk, but making risk legible & bounded.
Evaluate agents by tracking untrusted content, identity, blast radius and observability.
Read the guide:
#AgenticAI
👇
https://claude.com/blog/ciso-guide-to-agentic-ai -
Just released: The Standard AI Agent Framework v0.9.0
The framework supports skills, memory, tools, gates, judges, streaming, logging, and multi-agent composition, with a clean open-source implementation for C#.
-
Just released: The Standard AI Agent Framework v0.9.0
The framework supports skills, memory, tools, gates, judges, streaming, logging, and multi-agent composition, with a clean open-source implementation for C#.
-
Varma Kunaparaju had a front-row seat to the first generations of #AIOps tools based on machine learning as the co-founder and CEO at OpsRamp, which was acquired by Hewlett Packard Enterprise (#HPE) in 2023. Now, he's an SVP & GM overseeing parts of HPE's #CloudOps Software Suite and GreenLake hybrid cloud platform. In this episode, Kunaparaju details the company's recent free licensing deal for #broadcomvmware refugees, the evolution of AIOps in the #agentic era, and HPE's broader ambitions in enterprise #AI infrastructure.
In today’s episode, we’ll cover…
- AIOps, #AgenticOps and the state of autonomous infrastructure management
- HPE Morpheus VME pricing after year 1
- How HPE's AI networking strategy will affect its #hybridCloud products
And more! Tune in here: https://www.youtube.com/watch?v=Kg2u_-oUAh4&list=PL5OdmBrO1LpmxpPIyWFvn7B9EOt-Ns-Rw&index=1
-
Varma Kunaparaju had a front-row seat to the first generations of #AIOps tools based on machine learning as the co-founder and CEO at OpsRamp, which was acquired by Hewlett Packard Enterprise (#HPE) in 2023. Now, he's an SVP & GM overseeing parts of HPE's #CloudOps Software Suite and GreenLake hybrid cloud platform. In this episode, Kunaparaju details the company's recent free licensing deal for #broadcomvmware refugees, the evolution of AIOps in the #agentic era, and HPE's broader ambitions in enterprise #AI infrastructure.
In today’s episode, we’ll cover…
- AIOps, #AgenticOps and the state of autonomous infrastructure management
- HPE Morpheus VME pricing after year 1
- How HPE's AI networking strategy will affect its #hybridCloud products
And more! Tune in here: https://www.youtube.com/watch?v=Kg2u_-oUAh4&list=PL5OdmBrO1LpmxpPIyWFvn7B9EOt-Ns-Rw&index=1
-
OWASP Cornucopia just released v3.3.1
github.com/OWASP/cornuc...
A Special thanks to Mayur Agnihotri for adding AISVS v1 “High-Impact Action Approval and Irreversibility Controls” and to Adarsh Kumar for continuing pushing out bug fixes. You both rock!
#appsec #security #aisvs #owasp #ai #agentic
Release Release v3.3.1 · OWASP... -
OWASP Cornucopia just released v3.3.1
github.com/OWASP/cornuc...
A Special thanks to Mayur Agnihotri for adding AISVS v1 “High-Impact Action Approval and Irreversibility Controls” and to Adarsh Kumar for continuing pushing out bug fixes. You both rock!
#appsec #security #aisvs #owasp #ai #agentic
Release Release v3.3.1 · OWASP... -
Friends, Romans and Country-folk, lend me your stars.
I’m trying to get my open source project picked up by more and more folks, a bigger community more testing and commits which in turn means a better product, its a great flywheel effect. One way to help me is to star the repository and you have two options:
- codeberg where the source lives: https://codeberg.org/ric_harvey/omnimem
- GitHub to help discoverability: https://github.com/richarvey/OmniMem -
Friends, Romans and Country-folk, lend me your stars.
I’m trying to get my open source project picked up by more and more folks, a bigger community more testing and commits which in turn means a better product, its a great flywheel effect. One way to help me is to star the repository and you have two options:
- codeberg where the source lives: https://codeberg.org/ric_harvey/omnimem
- GitHub to help discoverability: https://github.com/richarvey/OmniMem -
Open-source #software isn't free? 😂 Next, you'll tell us the Internet isn't made of cats! 🐱 #Thoughtworks boldly delves into the "agentic era" while failing to fix their own broken #JavaScript. 🙄🌍
https://www.thoughtworks.com/insights/blog/open-source/zero-cost-fallacy-open-source-agentic-era #open-source #agentic #era #cats #HackerNews #ngated -
Open-source #software isn't free? 😂 Next, you'll tell us the Internet isn't made of cats! 🐱 #Thoughtworks boldly delves into the "agentic era" while failing to fix their own broken #JavaScript. 🙄🌍
https://www.thoughtworks.com/insights/blog/open-source/zero-cost-fallacy-open-source-agentic-era #open-source #agentic #era #cats #HackerNews #ngated -
The zero-cost fallacy: open-source software in the agentic era
https://www.thoughtworks.com/insights/blog/open-source/zero-cost-fallacy-open-source-agentic-era
Comments: https://news.ycombinator.com/item?id=48865001
#HackerNews #zero-cost #fallacy #open-source #software #agentic #era #tech #insights
-
The zero-cost fallacy: open-source software in the agentic era
https://www.thoughtworks.com/insights/blog/open-source/zero-cost-fallacy-open-source-agentic-era
Comments: https://news.ycombinator.com/item?id=48865001
#HackerNews #zero-cost #fallacy #open-source #software #agentic #era #tech #insights
-
The zero-cost fallacy: open-source software in the agentic era
https://www.thoughtworks.com/insights/blog/open-source/zero-cost-fallacy-open-source-agentic-era
Comments: https://news.ycombinator.com/item?id=48865001
#HackerNews #zero-cost #fallacy #open-source #software #agentic #era #tech #insights
-
The zero-cost fallacy: open-source software in the agentic era
https://www.thoughtworks.com/insights/blog/open-source/zero-cost-fallacy-open-source-agentic-era
Comments: https://news.ycombinator.com/item?id=48865001
#HackerNews #zero-cost #fallacy #open-source #software #agentic #era #tech #insights
-
The zero-cost fallacy: open-source software in the agentic era
https://www.thoughtworks.com/insights/blog/open-source/zero-cost-fallacy-open-source-agentic-era
Comments: https://news.ycombinator.com/item?id=48865001
#HackerNews #zero-cost #fallacy #open-source #software #agentic #era #tech #insights
-
My experience of #agentic programming so far is that it works much better in #Ruby that it does in #Rstats.
Is that because Ruby is (or was) a more popular and less niche language than R?
Or is it because I'm better at programming in R than in Ruby, so I'm noticing its mistakes more?
Or is it because I couldn't find a good set of starter skills for R, as I could for Ruby? (https://github.com/ThibautBaissac/rails_ai_agents)
So much subjectivity... I can really see why people's opinions on these tools is so varied.
-
My experience of #agentic programming so far is that it works much better in #Ruby that it does in #Rstats.
Is that because Ruby is (or was) a more popular and less niche language than R?
Or is it because I'm better at programming in R than in Ruby, so I'm noticing its mistakes more?
Or is it because I couldn't find a good set of starter skills for R, as I could for Ruby? (https://github.com/ThibautBaissac/rails_ai_agents)
So much subjectivity... I can really see why people's opinions on these tools is so varied.
-
Ah, yes, because what the world really needed was yet another tool promising to detect "agentic behavior"—whatever that means this week. 😏 #Cloudflare rolls out its shiny gadget, dubbed "Precursor," to engage in the eternal struggle of cat and mouse with #bots, while sales reps sharpen their knives for the inevitable "contact us" page. 💼🔍
https://blog.cloudflare.com/introducing-precursor/ #Precursor #agentic #behavior #tech #news #cybersecurity #HackerNews #ngated -
Ah, yes, because what the world really needed was yet another tool promising to detect "agentic behavior"—whatever that means this week. 😏 #Cloudflare rolls out its shiny gadget, dubbed "Precursor," to engage in the eternal struggle of cat and mouse with #bots, while sales reps sharpen their knives for the inevitable "contact us" page. 💼🔍
https://blog.cloudflare.com/introducing-precursor/ #Precursor #agentic #behavior #tech #news #cybersecurity #HackerNews #ngated -
Anyone else feeling like the top 10 or so of this times #hackthebox season (season of the punk) is basically ppl using automated #ai #agents ?
-
Anyone else feeling like the top 10 or so of this times #hackthebox season (season of the punk) is basically ppl using automated #ai #agents ?
-
@selfcare I am sick of AI tooling, and the requirement to use them. My company has enterprise #claude and #n8n licenses, and we are expected to use them for at least 50% of our work. I get #tokens, but all I can bring myself to do with it is to ask if this lib or that lib will work for my python apps, and write them myself.
Maybe, I occasionally ask AI if the code Ive written is sane....but can I really trust #agentic AI to tell me if my code works or not?
Who the fuck knows.
-
@selfcare I am sick of AI tooling, and the requirement to use them. My company has enterprise #claude and #n8n licenses, and we are expected to use them for at least 50% of our work. I get #tokens, but all I can bring myself to do with it is to ask if this lib or that lib will work for my python apps, and write them myself.
Maybe, I occasionally ask AI if the code Ive written is sane....but can I really trust #agentic AI to tell me if my code works or not?
Who the fuck knows.
-
HalluSquatting turns AI hallucinations into an automated botnet-building weapon
https://1ban.news/hallusquatting-ai-hallucination-agentic-exploit-2026/
#1ban #hallusquatting #hallucination #agentic #exploit #tech -
In today's episode of don't trust LLMs with your private data:
#GitLost: How We Tricked GitHub's AI Agent Into Leaking Private Repos
https://noma.security/blog/gitlost-how-we-tricked-githubs-ai-agent-into-leaking-private-repos/
#llm #ai #cybersecurity #promptinjection #github #agents #agent #agentic #agentic_ai
-
In today's episode of don't trust LLMs with your private data:
#GitLost: How We Tricked GitHub's AI Agent Into Leaking Private Repos
https://noma.security/blog/gitlost-how-we-tricked-githubs-ai-agent-into-leaking-private-repos/
#llm #ai #cybersecurity #promptinjection #github #agents #agent #agentic #agentic_ai
-
In today's episode of don't trust LLMs with your private data:
#GitLost: How We Tricked GitHub's AI Agent Into Leaking Private Repos
https://noma.security/blog/gitlost-how-we-tricked-githubs-ai-agent-into-leaking-private-repos/
#llm #ai #cybersecurity #promptinjection #github #agents #agent #agentic #agentic_ai
-
In today's episode of don't trust LLMs with your private data:
#GitLost: How We Tricked GitHub's AI Agent Into Leaking Private Repos
https://noma.security/blog/gitlost-how-we-tricked-githubs-ai-agent-into-leaking-private-repos/
#llm #ai #cybersecurity #promptinjection #github #agents #agent #agentic #agentic_ai
-
In today's episode of don't trust LLMs with your private data:
#GitLost: How We Tricked GitHub's AI Agent Into Leaking Private Repos
https://noma.security/blog/gitlost-how-we-tricked-githubs-ai-agent-into-leaking-private-repos/
#llm #ai #cybersecurity #promptinjection #github #agents #agent #agentic #agentic_ai
-
Agentic LLMs are now running full ransomware attacks. These attacks are self-correcting, which means that the skill ceiling is being lowered further. Additionally, the time we have to react to these types of attacks melts down.
Source: https://www.sysdig.com/blog/jadepuffer-agentic-ransomware-for-automated-database-extortion
#cybersecurity #security #infosec #ai #agentic #agenticai #llm #ransomware #extortion
-
Agentic LLMs are now running full ransomware attacks. These attacks are self-correcting, which means that the skill ceiling is being lowered further. Additionally, the time we have to react to these types of attacks melts down.
Source: https://www.sysdig.com/blog/jadepuffer-agentic-ransomware-for-automated-database-extortion
#cybersecurity #security #infosec #ai #agentic #agenticai #llm #ransomware #extortion
-
IDE with agentic support built using Flutter
-
IDE with agentic support built using Flutter
-
I think I finally figured out why I despise all of this "agentic" and "chat AI" based nonsense so much. It feels exactly like telephone tech support where you've to instruct someone to do something instead of just doing the thing yourself. A task that should take 5s can take minutes to hours and you never know what the other party actually does...
-
I think I finally figured out why I despise all of this "agentic" and "chat AI" based nonsense so much. It feels exactly like telephone tech support where you've to instruct someone to do something instead of just doing the thing yourself. A task that should take 5s can take minutes to hours and you never know what the other party actually does...
-
I think I finally figured out why I despise all of this "agentic" and "chat AI" based nonsense so much. It feels exactly like telephone tech support where you've to instruct someone to do something instead of just doing the thing yourself. A task that should take 5s can take minutes to hours and you never know what the other party actually does...
-
I think I finally figured out why I despise all of this "agentic" and "chat AI" based nonsense so much. It feels exactly like telephone tech support where you've to instruct someone to do something instead of just doing the thing yourself. A task that should take 5s can take minutes to hours and you never know what the other party actually does...
-
I think I finally figured out why I despise all of this "agentic" and "chat AI" based nonsense so much. It feels exactly like telephone tech support where you've to instruct someone to do something instead of just doing the thing yourself. A task that should take 5s can take minutes to hours and you never know what the other party actually does...
-
#MissKittyPolitics #AI vs #Humans
Let's talk the weakness of robots. Robots can't do asynchronicity. Humans can. #Asynchronicity will overwhelm #Agentic with enough participation. #AI cannot keep up with humans that are active. AI is actually a really stupid thing that's just fast. #DEFEND 🗽🗽🗽 -
#MissKittyPolitics #AI vs #Humans
Let's talk the weakness of robots. Robots can't do asynchronicity. Humans can. #Asynchronicity will overwhelm #Agentic with enough participation. #AI cannot keep up with humans that are active. AI is actually a really stupid thing that's just fast. #DEFEND 🗽🗽🗽 -
#MissKittyPolitics #AI vs #Humans
Let's talk the weakness of robots. Robots can't do asynchronicity. Humans can. #Asynchronicity will overwhelm #Agentic with enough participation. #AI cannot keep up with humans that are active. AI is actually a really stupid thing that's just fast. #DEFEND 🗽🗽🗽 -
Bots have now passed human traffic online,’ Cloudflare boss laments — says agentic traffic wasn’t expected to eclipse real people until next year
Bot (automated) vs. human HTTP requests are split 57.5 vs. 42.5 percent, according to the firm’s latest data
#bots #Agentic #AgenticTraffic #FuckAI #online #onlinetraffic #cloudfire #ai #bot
-
Bots have now passed human traffic online,’ Cloudflare boss laments — says agentic traffic wasn’t expected to eclipse real people until next year
Bot (automated) vs. human HTTP requests are split 57.5 vs. 42.5 percent, according to the firm’s latest data
#bots #Agentic #AgenticTraffic #FuckAI #online #onlinetraffic #cloudfire #ai #bot
