Asim Razzaq

Worth reading: Generative AI is not going to build your engineering team for you. So, so good - peppered with gem quotes and observations- chuckle. https://lnkd.in/gZBKtU4X Thanks to Eric Brooke for sharing.

16

If you are working with Docker... I highly recommend looking at the Slim toolkit. https://lnkd.in/gX_Gb9Kf Why? Slim allows developers to inspect, optimize, and debug their containers using its xray, lint, build, debug, run, images, merge, registry, vulnerability (and other) commands. It simplifies and improves your developer experience building, customizing and using containers. It makes your containers better, smaller and more secure while providing advanced visibility and improved usability working with the original and minified containers. Don't change anything in your container image; minify it by up to 30x to make it secure, too! Optimizing images isn't the only thing it can do, though. It can also help you understand and author better container images. Keep doing what you are doing. No need to change anything. Use the base image you want. Use the package manager you want. Don't worry about hand-optimizing your Dockerfile. You shouldn't have to throw away your tools and your workflow to have small container images. Node.js application images: from ubuntu:14.04 - 432MB => 14MB (minified by 30.85X) from debian:jessie - 406MB => 25.1MB (minified by 16.21X) from node:alpine - 66.7MB => 34.7MB (minified by 1.92X) from node:distroless - 72.7MB => 39.7MB (minified by 1.83X) Go application images: from golang:latest - 700MB => 1.56MB (minified by 448.76X) from ubuntu:14.04 - 531MB => 1.87MB (minified by 284.10X) from golang:alpine - 258MB => 1.56MB (minified by 165.61X) from centos:7 - 615MB => 1.87MB (minified by 329.14X) Rust application images: from rust:1.31 - 2GB => 14MB (minified by 147.16X) Java application images: from ubuntu:14.04 - 743.6 MB => 100.3 MB

4

And that was a wrap! As #apisummit24 completes with over 10,000 attendees from the API community - making it the largest API conference by far - with dozens of awesome product and partner launches to show what we can do with *the API platform for the AI era*... one fundamental question remains open: Are you on the right side of AI? One thing we know for sure... APIs are the common language of LLMs as we build apps and transform our business with {Gen} AI. In this post, I wrote a few thoughts from my opening keynote on the API market evolution that's ahead of us. Lmk what you think!

42

1 Comment

Excited to share my first blog post in a new series: "LLM Study Diary: A Comprehensive Review of LangChain — Part 1" After a brief hiatus of 6 months from LangChain, I found the landscape had changed significantly. This inspired me to revisit Greg Kamradt's excellent tutorial, but with a twist: In this post, I: - Walk through Kamradt's example codes - Update and correct parts that don't work with the latest libraries - Share insights and solutions for compatibility issues It's a practical guide for anyone looking to use LangChain with current versions. Read more: https://lnkd.in/gtbmetkH #AI #LangChain #LLM #Python #CodeTutorial Have you encountered similar update challenges? Share your experiences!

9

Nearly every great product company is a great infrastructure software company. Infrastructure enabled Google to deliver the most relevant search results and the fastest browser, Facebook to provide the most personalized social feed, Netflix to stream with the best viewer experience (minimal lag/interruption), Uber to determine the best real-time ride matches, etc. Infrastructure was key to helping these companies (and many others) win their markets. It’ll be the same in AI. The companies that leverage AI infrastructure in the smartest ways - figuring out the right breakdown and sequence of agentic tasks, utilizing data curation and RAG to get best-in-class model performance, managing multi-model and multi-modal complexity - will gain a strategic / competitive advantage. AI founders: invest in your infrastructure early.

123

9 Comments

I'm having enlightening convos with folks who deliver infra for others to run. It sounds like "runbooks/wiki docs" are a real problem from a handoff/support perspective. We have an elegant solution, when you deliver runbooks as "click to play/pre-configured" Notebooks, and a command fails, the user gets an `escalation button` that shares a link to the output/metadata into the shared Slack room. It's ideal for bridging the gap when there's a support relationship. 🤓 This sounds like a case study in the making.. anyone else struggling with this?

14

𝑳𝑳𝑴-𝒂𝒔-𝑱𝒖𝒅𝒈𝒆 🧑‍⚖️ 𝘓𝘓𝘔 𝘌𝘷𝘢𝘭𝘴 & 𝘵𝘩𝘦 𝘪𝘯𝘴𝘪𝘥𝘦 𝘴𝘵𝘰𝘳𝘺 𝘰𝘧 𝘩𝘰𝘸 Twilio Segment 𝘣𝘶𝘪𝘭𝘵 𝘊𝘋𝘗 𝘊𝘰𝘱𝘪𝘭𝘰𝘵 𝘵𝘰 𝘢𝘤𝘤𝘦𝘭𝘦𝘳𝘢𝘵𝘦 𝘮𝘢𝘳𝘬𝘦𝘵er 𝘸𝘰𝘳𝘬𝘧𝘭𝘰𝘸𝘴 3𝘹 These days I'm spending an irrational amount of time thinking about evals. It started with a conversation months ago with Jaimal Soni, when he was showing me an absolutely 🔥🔥 demo of what he's been building in stealth. I couldn't believe what I'd just seen. "What's one of the hardest problem you had to solve?" I asked. "Evals." Evals are the way to assess (ahem evaluate) LLMs and systems built with LLMs. In software engineering, you'll hear a lot about test coverage and unit tests — little tests to verify that your code is doing what you expect. But generative AI & LLMs are a little different: unlike your deterministic code, models are stochastic, meaning you never really know what the output will be until it's generated!Ask chatGPT the *same* question and you will get *different* answers. This is where LLMs get their magic, but also creates problems when you're asking an LLM to solve discrete tasks. As we've been building out CustomerAI & Generative Audiences, we needed to think about this problem from the start. Generative Audiences allows marketers to write natural language to generate new audiences, without having to navigate a sophisticated audience-building UI. We’ve been blown away by the results of – customers are experiencing a 3x improvement in median time-to-audience creation, and world-class feature retention rate IF the audience generation works on the first attempt. So evals are 🔑 Ankit Awasthi, Salman Ahmed, Alfredo Láinez Rodrigo, & James Zhu came up with a really clever solution to ensure that CDP Copilot is generating audiences that are accurate & represent the intent of the prompt. But it wasn't easy...and today we're sharing how we used synthetic data & LLM-as-Judge architecture to accelerate marketer workflows 3x.

90

8 Comments

"Former Facebook engineer says coding with an AI copilot is like working with a 'demigod'" says the title of an article by businessinsider.com LLMs are good, click-bait and overexcitement aren't. They create unrealistic expectations: VCs believe the N-times engineering multiplier story. Governments rush to regulate AGI Skynet. Workers suffer from FOBO (fear of becoming obsolete), etc. I get the excitement when Copilot generates 1.5 pages of code and it even works. Feels like magic. LLMs do help and get better fast. Yet it depends on the task, the code, the training dataset, the prompt, the context window, the temperature... you name it. One day a typical task matches dozens of known solutions from a training set, another day you waste time debugging a bug in generated concurrent code or discarding a hallucination reply to your carefully prepped prompt. You need concentration, good code review skills, and good engineering skills to adapt the result to your needs. Training sets define LLM quality. Good hard solutions are rare. Complex code tends to have bugs. Expect training sets to be uneven in quality and coverage. Simple common problems make LLMs shine. Guess what reviewer tries first and gets a magical result? Luckily the initial overexcitement is already being replaced with a healthier excitement, yet we still get the 'demigod' headers occasionally. #AI #LLM #Copilot #softwareengineering #softwaredevelopment #coding #programming #productivity #dev Enjoy the classic comic by T. Ryan

9

4 Comments

Excited to announce that Enkrypt AI was selected to present at the upcoming #AWSreInvent on Dec 3rd in Vegas! 🚀 We'll be diving into the vital challenges enterprises face when bringing Generative AI into production. Don’t miss out on key insights that could redefine your approach to AI in business. #AI #EnterpriseAI #Innovation

37

2 Comments

For building a high-performing software engineering organization, ACCELERATE by Nicole Forsgren, Jez Humble, and Gene Kim suggests using the four DORA KPIs and these 24 capabilities: CONTINUOUS DELIVERY 1. Use version control for code, configurations, and scripts. 2. Automate deployments to speed up releases and reduce errors. 3. Continuously integrate code with automated tests to catch issues early. 4. Adopt trunk-based development with short-lived branches. 5. Automate testing throughout development for speed and accuracy. 6. Ensure robust test data management for reliable testing. 7. Shift security left by integrating pre-approved security checks early. 8. Keep software in a deployable state for quick, confident releases. ARCHITECTURE 9. Build loosely coupled architectures so teams can test and deploy independently. 10. Allow teams to select the best tools for their tasks to drive innovation. PRODUCT 11. Gather early customer feedback to guide better decisions. 12. Visualize the flow of work to identify bottlenecks and improve delivery. 13. Work in small batches to reduce risk and iterate faster. 14. Encourage experimentation to promote innovation and agility. LEAN MANAGEMENT 15. Implement lightweight change approvals for faster decision-making. 16. Monitor systems to inform decisions and ensure stability. 17. Proactively check system health to prevent issues. 18. Limit work-in-progress to boost focus and productivity. 19. Use dashboards to visualize progress and maintain quality. CULTURE 20. Foster a generative culture with trust, collaboration, and open communication. 21. Support continuous learning to keep teams growing and evolving. 22. Break down silos to encourage cross-team collaboration. 23. Provide meaningful tools and resources for impactful work. 24. Lead with vision, inspiration, and personal recognition. The book is a great read and highly recommended!

1

I like this idea of "technical taste". It gets into where software engineering is as much creative art as it is science. Four great takeaways (IMHO) for software devs in this era in particular: 1. Aspiring engineers should cultivate a sense of curiosity, experiment with different tools and technologies, and embrace a mindset of continuous learning. 2. AI has the potential to streamline processes and enhance productivity for engineers, but it may also lead to disruptions in traditional software development workflows. 3. Developing technical taste and judgment is essential for making informed decisions about which technologies and approaches to pursue. 4. Collaboration and open-mindedness are key to leveraging the full potential of AI and staying ahead of technological advancements. I also really liked these two quotes from Sam Schillace: 1. "The right time to do something is when you have that feeling in the pit of your stomach that's like, 'oh, this is a great idea and it's going to suck to build because nothing's ready yet.'" 2. "Technical taste is like, 'how well have you consolidated that set of experiences and heuristics into judgment that you can apply accurately when you see new things?'" 3. "It may be the case that very small teams can do very large projects, or like we were talking about before, it may be the case we're just going to get really ambitious about what we try to do with the same size of teams, which is kind of where I would put my money." Great job on continuing to put out great episodes, Brett Berson and team First Round Capital! #ai #engineering #softwaredevelopment

5

🍜Anybody up for some ramen? I am excited to share that I am back in the garage, building again (it’s actually a house in the Berkeley Hills). We are taking the wraps off of Supercog AI, a new startup focused on solving Application Integration using LLM powered agents. My co-founder in this new venture is a great friend of mine (and a former co-founder partner), Alex Osborne. Alex and I have worked around the application integration space for a long time, and we are unrealistically excited about applying the GenAI stack to this problem. Not many people relish the task to get some bits to move from system A to system B. But it’s a critical job to be done, and that’s led to a lot of brittle scripts, a myriad of inflexible “no code” tools, and a lot of hand crafted SQL. But the power of the Large Language Model, trained on a huge corpus of information, offers a remarkable tool to solve this problem. The LLM you use today already knows the APIs of hundreds of popular systems. It knows the SQL dialects of every major database. It understands the semantics and data schemas of many popular SaaS systems. It understands much of the specific domain in which your business operates. I like to call the AI revolution “the last platform shift”. That may turn out to be hyperbole, but I definitely believe we are in the very early stages of seeing what this new stack can enable. I know we are hardly the first folks to claim that “amazing stuff is coming!”. But this is why Alex and I have decided to focus on a real and hard problem. If we can prove that LLMs can power a new way to solve this problem, it will be the first successful *new* approach in 15 years.. We will have much more to share about this new platform soon. In the meantime, if you’re interested in getting a peek - or even better if you have application or data integration tasks that you would like some help with - please reach out because we want to help. #genai #startups #backinthegarage

163

37 Comments

Exciting news for teams leveraging monorepos! Coherence now supports glob patterns for selective build configuration, bringing unprecedented efficiency to your development pipeline. 🔧 Technical Highlights: • Granular control over build and deploy processes • Intelligent file change detection • Seamless integration with existing CI/CD workflows 💡 Key Advantages: 1. Dramatic reduction in build and deploy times 2. Optimized resource allocation 3. Precision targeting of updates for changed code only 🏗️ Real-world Impact: • Accelerated development cycles • Enhanced productivity for large-scale projects • Significant cost savings on computational resources This feature empowers you to fine-tune your build process, ensuring only necessary services are built and deployed based on actual code changes. It's a game-changer for maintaining velocity in complex, multi-service architectures. Ready to supercharge your monorepo? Dive into our comprehensive documentation to implement selective builds and experience the future of efficient development.

6

AI and ML are changing the way Software companies work. I strongly suggest upskilling the technical team so they can use these AI and ML techniques and focus on delivering solutions rather than on coding. This is what I learned from this AI training.

30

1 Comment

Task-specific models and routing architectures are the future. Robert Nishihara, co-founder and CEO of Anyscale, is seeing hybrid strategies emerge, where businesses are evaluating different types of models for different use cases. With the rapid advancement of AI tech, it won't be long before open-source models are "good enough" for the majority of business tasks. The natural progression from here is to develop smaller, task-focused models using proprietary company data. As Robert puts it: "You're going to need small, fast models. And task-specific models have a huge advantage when it comes to cost and speed because you can achieve the same quality with a smaller model if it's specialized." Another interesting development: the growing use of routing architectures. Imagine a classifier as a kind of traffic controller for your AI queries. It assesses the complexity of each query and directs it to the most suitable model: simpler requests are handled by smaller models, while complex ones are passed on to larger, more sophisticated models. “If you do it right,” Robert says, “you can achieve something like the cost of the smaller model with the quality of the more advanced model.” Dive deeper into AI architecture trends in my full discussion with Robert on the B2BaCEO podcast here: https://lnkd.in/ghigvERn

46

3 Comments

Interesting read from DC Palter. Thoughts? ===== "Every founder thinks they want as much cash as they can get, but if they haven’t found product-market fit (and by definition, a pre-revenue company hasn’t found PMF) they’re going to need to pivot at least three times before they get rolling. The more they spend now on what will turn out to be a dead end, the harder it will be to pivot. Attempting to fly before you can crawl is a recipe for crashing." An Open Letter to VCs: Please Get Out of Pre-Seed Investing https://lnkd.in/gzC7HtZ8

7

Similarweb acquires 42Matters- an app intelligence data company. Smart acquisition and I would expect Similarweb to use their public stock to acquire aggressively. Lots of data and data technology would make sense as part of their company. 42matters' expertise in app store, engagement, and mobile SDK data promises to deliver more in-depth insights into app performance and user engagement. The integration of these advanced solutions is expected to benefit app owners by providing a clearer view of their apps' positioning against competitors and user interaction. The 42matters' dataset includes information from 12 app store platforms, over 2.1 million publishers, more than 2,600 SDKs, and upwards of 20 million apps. The combination of these two companies should benefit from the Similarweb distribution.

38

1 Comment