CD

Shipping code of varying quality and varying levels of review isn't a new problem, any large enough company has had to deal with this for years already At this point maybe we treat coding agents like teams of mixed ability engineers working under aggressive deadlines

The people I want to hear from right now are the security teams at large companies who have to try and keep systems secure when dozens of teams of engineers of varying levels of experience are constantly shipping new features

@cgidubai I am an Indian national currently stranded in Dubai due to flight disruptions. I am unable to access the consulate registration website due to a technical error. please advise an alternate way to register or get guidance? I’m happy to share details via DM.

some thoughts on agentic AI, convenience and security tradeoffs we’re already making. medium.com/p/agentic-conv…

I have been developing Agentic Systems for the past few years and the same patterns keep emerging. 👇 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 𝗗𝗿𝗶𝘃𝗲𝗻 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 is the most reliable way to be successful in building your 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 - here is my template. Let’s zoom in: 𝟭. Define a problem you want to solve: is GenAI even needed? 𝟮. Build a Prototype: figure out if the solution is feasible. 𝟯. Define Performance Metrics: you must have output metrics defined for how you will measure success of your application. 𝟰. Define Evals: split the above into smaller input metrics that can move the key metrics forward. Decompose them into tasks that could be automated and move the given input metrics. Define Evals for each. Store the Evals in your Observability Platform. ℹ️ Steps 𝟭. - 𝟰. are where AI Product Managers can help, but can also be handled by AI Engineers. 𝟱. Build a PoC: it can be simple (excel sheet) or more complex (user facing UI). Regardless of what it is, expose it to the users for feedback as soon as possible. 𝟲. Instrument your application: gather traces and human feedback and store it in an Observability Platform next to previously stored Evals. 𝟳. Run Evals on traced data: traces contain inputs and outputs of your application, run evals on top of them. 𝟴. Analyse Failing Evals and negative user feedback: this data is gold as it specifically pinpoints where the Agentic System needs improvement. 𝟵. Use data from the previous step to improve your application - prompt engineer, improve AI system topology, finetune models etc. Make sure that the changes move Evals into the right direction. 𝟭𝟬. Build and expose the improved application to the users. 𝟭𝟭. Monitor the application in production: this comes out of the box - you have implemented evaluations and traces for development purposes, they can be reused for monitoring. Configure specific alerting thresholds and enjoy the peace of mind. ✅ 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝗼𝘂𝘀 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 𝗼𝗳 𝘆𝗼𝘂𝗿 𝗮𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻: ➡️ Run steps 𝟲. - 𝟭𝟬. to continuously improve and evolve your application. ➡️ As you build up in complexity, new requirements can be added to the same application, this includes running steps 𝟭. - 𝟱. and attaching the new logic as routes to your Agentic System. ➡️ You start off with a simple Chatbot and add a route that can classify user intent to take action (e.g. add items to a shopping cart). What is your experience in evolving Agentic Systems? Let me know in the comments 👇 #LLM #AI #MachineLearning

The Agentic AI Security Scoping Matrix: A framework for securing autonomous AI systems aws.amazon.com/blogs/security… via @awscloud

@teneikaask_you @SaveToNotion #thread

Here's a few FREE courses and resources that you can use to become a Product Manager. This study plan is focused on creating a portfolio, building and retaining the skills needed to land a PM job🧵

Hello, guys 👋 I have made a GitHub Repository to help the community to get a road map on How to start #Android #Pentesting by following these Free Resources, which will take you from Basic level to intermediate level. Github Repo: github.com/dn0m1n8tor/And… #infosec #bugbounty

link.medium.com/N4P1IhnEwjb this is an excellent read!

The @OWASP Top 10 team is extremely proud to share the draft OWASP Top 10 2021 for peer review, comment, translation, and suggestions for improvements. We are working on a graphic redesign and a surprise extra for the 20th Anniversary on September 24! owasp.org/Top10/

It turns out that wireless charging leaks private data. It leaks information about websites visited by the user. " allows accurate website fingerprinting on a charging smartphone". Information leaked depends on the battery level. Cool work! #GDPR #ePrivacy arxiv.org/pdf/2105.12266…

This was a proud moment for me last year. I was admittedly not that active in the community last year (hello pandemic) but super eager to regain momentum this year. Happy international women's day ☺️

Pls stop. It's a movie on zombies and human emotions. It transcends language already. Just turn on subtitles if you really need to read the roars in english.

I'd assume Go packages are not affected...If using athens?

Gentle reminder - not only do I have a namesake in this world, I have a doppelganger out there too. Watch the video in the link below and you'll see twitter.com/nailainayat/st…

@NarayanGowraj @loom

My last day at Lyft was last Friday. Had a great experience with some amazing colleagues. I am excited for my next role at @loom as a Security Engineer to build robust & scalable security functionalities 😎

I got into Cybersecurity when I had the realization that my natural paranoia and distrust of things was a career path 😉

I didn’t come home if I got a 92

💯 true. Thank you tech fair and conferences 🙏

Thanks for organizing a great virtual conference. I am honored to have presented this year and hope to attend next year in person 🌺🌴