Ilya Obshadko

Project update! My application tracking extension is now doing fuzzier matching and injecting new information into LinkedIn (and other sites) to keep me from doubling up on applications. Next up: local storage and bulk import/export operations...

12

2 Comments

Want a preview of what I'm going to be talking about in my keynote for RubyConf? You can catch a glimpse of it here!

10

We're in the pets phase of LLMs right now, but the cattle phase is coming and it'll change everything. Yes, again. What do you mean "pets" and "cattle"? Servers used to be our pets. We bought, named, cared for, and persisted them individually. If we wanted a new one, it was a big commitment. If one went down, it was a big loss. But then servers became cattle. Today we manage them as a group of commodity assets. We want one, we clone it. If one goes down, we replace it with another. This change delivered an era of distributed, high availability applications with limited downtime. Cheap storage, containers, cloud, clusters all met riding on top of Moore's law. And machine learning changed too. Computer vision was first. We went from small, neural networks running on CPUs via Matlab to a larger networks running in on GPUs via C++. AlexNet kicked off the deep learning revolution, eventually Transformers in NLP, and then ChatGPT. So, today we call our LLMs by name but this is just the start. There will be more LLMs variations than there are people on Earth.

25

1 Comment

A super clear, straight forward example of how to do cost effective RAG using LangChain for your document pipeline and Groq for compute resources. The code demonstrates how to speed up RAG and reduce costs using quantized embeddings (reducing 32 bit values to 8) Nice job Sahibpreet Singh! https://lnkd.in/gf5QMCKK

43

2 Comments

https://lnkd.in/gdGKdeAW - New project I built using a combination of Replit Agent, Perplexity search API using llama-3.1-sonar & OpenAI API Assistant. You're not sure how to vote on that? Take a quiz about your core values then this app will research it/them and help you decide.

5

Cortex Click's LLM-driven technical writing tools automatically search your docs, internal wikis and code examples to improve quality and style while you're writing. And now you can directly add private reference materials to an article - perfect for writing launch blogs and documentation for unreleased features 😉 👀

6

Embedded content is mind-blowing! 🤯 This #Pendo blog post shows how embedded content drives engagement & conversion. 🚀

2

The Smartling team couldn't be more excited to introduce the AI Translation Toolkit: a suite of AI translation features designed to reduce translation costs and improve linguist performance. This feature allows #localization teams to leverage AI to streamline translation processes, without sacrificing quality. Reach out to your Smartling Customer Success Manager to learn about how the AI Translation Toolkit can improve the performance of your translators. #aitranslation #smartling #l10n #ailocalization #translatortools

28

Alex Komoroske's writing is so fun to read and so easy to draw lines into our reality: "Sarumans can’t see the value of systems; it will seem too fuzzy and abstract; [...] For similar reasons, a Saruman is deeply skeptical of other people’s perspectives on what’s a constraint, because the only constraints that are real are physical constraints, and everything else is just a fiction in people’s minds that can be overcome with boldness. Sarumans are the kinds of people who build impressive, powerful cathedrals. When you’re building a cathedral, you can’t have naysayers pointing out imagined constraints. You need decisiveness. As they get more powerful, accumulating followers, capital, and respect, it becomes easier and easier to cast the naysayers away. [...] Radagasts intuitively understand the power of the swarm: the system, in its buzzing, blooming, emergent glory. Radagasts know how to let go and dance madly with the system. They don’t try to control the system and its components. They love the system and its components: a love borne out of respect." https://lnkd.in/e9TNgNXb

2

In the months leading up to the closing of InVision, I built a bulk export workflow for the V6 cloud product. This provided a way for users to export Prototypes and Boards as ZIP files (complete with both data and image files) for archival purposes. The ZIP files are designed to be consumed directly from the user's local file system. Which means, these ZIP files can also be used to host static sites on public URLs. As a final gesture of good will, I wanted to demonstrate (VIDEO) how InVision V6 users can upload those ZIP files—FOR FREE—to Cloudflare Pages. It's so freakin' easy - you don't even have to unzip the files (Cloudflare does that for you). Read more: https://bennadel.com/4749

29

4 Comments

The best use case for overseas development I've heard: We have customers in the eastern hemisphere. To support those customers better, we're standing up product, dev, and support teams to help serve those customers needs. Two key ingredients in making that successful: commensurate pay and the same level of performance and accountability as US peers. #software #international #teammanagement #overseasdevelopment #startup #leadership #coaching

6

I think this report is another confirmation of what many of us believe. People want immediate access to their earnings and cross border payments are hard. https://lnkd.in/g4UgvD7m As more work is (unfortunately) offshored, better solutions to some of these problems may enable businesses to create a differentiated experience for their customers. There's a few potential solutions with existing payment rails like issuing local debit cards for instant access to funds(EG I as a US entity issue cards in Brazil to freelancers and fund in USD). In addition I think Crypto has the right characteristics to be a reasonable solution. It's regulated, global, and cheap with accessible liquid markets. Businesses can easily convert from their local currency to BTC and instantly pay their offshore employees with the Lightning network. Imagine as a freelancer instead of waiting for a payout, you have instant access to funds as you complete work. I know that this is a bit of tooting our own horn, but I think it does enable a better experience. This is all a bit high level, if you want to dive into details, or if you're interested in learning more about Lightning, feel free to reach out, I'm always happy to chat and share what I've learned. You can also take a look at our docs at docs.lightspark.com. A bit sparse in content right now but I'm working on adding more!

8

The difference between a decision and a data-driven decision is like the difference between a shot in the dark and a carefully aimed arrow. Which decision do you want to make?

2

We've been making some cool examples of things that can be built with substrate.run lately. Here's a simple chatbot that can help you cook: https://lnkd.in/eEZm-nRJ If you're working on building a chatbot, take a look and see what it might look like to use Substrate 🧑‍🍳

19

2 Comments

Check out the latest in our "Debuggability" blog series! This blog is authored by Kevin Downey Jason Johl and me and talks about how we built a Debuggability Paved Road at Intuit using Ephemeral Containers and Argo Workflows. We'd love to hear your thoughts on the topic. Also, what tools do you build as-a-platform to help debug service, compute and network issues in Kubernetes at scale? #intuit #kubernetes #debug

23

I've just wrote a blog post on how I can see the AI moving forward next year, and how the Agent landscape will look like in the near future. The future with AI is wild. 🚀 https://lnkd.in/daHUYiBf

17