adrianco,
@adrianco@mastodon.social avatar

I’m in Denver/Broomfield for a few days for the SW2con (used to be Gluecon) event. Giving a talk on Weds. meeting a bunch of old friends. https://www.sw2con.com/#agenda

adrianco,
@adrianco@mastodon.social avatar

started out with an excellent keynote from the analyst team, the intersection of developers and AI, how we got here and what are this issues. Some papers to read linked from the QR codes. /cc @CSLee @rstephensme

KFosterMarks,
@KFosterMarks@mastodon.social avatar

@adrianco @CSLee @rstephensme

Oh my gosh, love this! We are so proud of this work, and so eager to hear how it's helping out software engineering community! 😍

adrianco,
@adrianco@mastodon.social avatar

second keynote is Datastax CTO Jonathan Ellis talking about vector databases. Very deep dive into the tech. Great to see Jonathan again… he spent the last year building open source JVector https://github.com/jbellis/jvector

adrianco,
@adrianco@mastodon.social avatar

next keynote is a talk on GitHub Copilot, how it works, the development and tuning process behind getting it to work well, by Mario Rodriguez - Senior VP of Product at Microsoft.

adrianco,
@adrianco@mastodon.social avatar

Emily Johnson from IBM - first time speaker - doing a great job talking about observability with Instana and optimization with Turbonomic. I was an advisor to Instana when they started, and it’s good to see IBM developing and supporting the product after they acquired the team.

adrianco,
@adrianco@mastodon.social avatar

next up I’m in the Code-assists track hearing from Aso Kukic of Sourcegraph about their Cody tool. Start by defining levels of Code AI assist. Human-initiated, AI initiated, and AI led.

adrianco,
@adrianco@mastodon.social avatar

Dennis Pilarinos, CEO of Unblocked taking about security and trust for AI apps. Applying these patterns to the new AI apps.

adrianco,
@adrianco@mastodon.social avatar

good talk on what to think about when considering AI trust and security issues.

adrianco,
@adrianco@mastodon.social avatar

IBM Fellow Trent Grey-Donald talking in detail about how code assistants work. I was chatting to Trent last night and discovered we have a bunch of friends in common. The hallway track here is very good, I usually meet some new interesting people…

adrianco,
@adrianco@mastodon.social avatar

Intent matters a lot, the flow of how it works is shown… the IBM example was turning COBOL into Java, unlike the earlier GitHub examples in Python and Cody examples in JavaScript. They can all do most languages but for a specific use case and language one or the other products is likely to be better tuned.

adrianco,
@adrianco@mastodon.social avatar

Code Assistants - the road ahead. Measure user feedback, pick the right context, combine LLMs with established techniques, go beyond coding.

adrianco,
@adrianco@mastodon.social avatar

attending afternoon sessions related to RAG. First up: Building Something Real with Retrieval Augmented Generation (RAG) - Jon Bratseth, CEO, Vespa.ai

image/jpeg

adrianco,
@adrianco@mastodon.social avatar

more advice on RAG from Jon Bratseth - good level of detail on how they work and what’s important.

image/jpeg

adrianco,
@adrianco@mastodon.social avatar

Joe Shockman co-founder of Grounded AI up next. Goal of making today’s workloads more efficient and avoiding the pitfalls we’ve been seeing.

adrianco,
@adrianco@mastodon.social avatar

A Recipe for Fine-tuning with Direct Preference Optimization (DPO) - Jesse Kipp, Director of Engineering, Cloudflare - good reference to a recent paper http://arxiv.org/abs/2405.00732

adrianco,
@adrianco@mastodon.social avatar

when to do fine tuning vs RAG. Useful talk by Jesse Kipp on the differences and techniques.

image/jpeg
image/jpeg

adrianco,
@adrianco@mastodon.social avatar

I took a break to work on my talk for tomorrow (I’m the keynote before lunch) and now we are back for the final set of day 1 keynotes with: KAITO: Building an Open Source Platform for AI - Lachlan Evenson, Principal PDM Manager, Microsoft Azure. Good advice on how open models work, nice demo of Kubernetes deployment and some next steps.

image/jpeg

joy,
@joy@mastodon.social avatar

@adrianco “That event has a lot of AI-focused content for developers and other technical practitioners” says the AI marketer.

Is the crowd mostly outside of SF?

adrianco,
@adrianco@mastodon.social avatar

@joy The event is in Colorado, there are people from all over the place. Hawaii, West coast, a bunch of locals, Texas, East coast and I think some from Europe.

joy,
@joy@mastodon.social avatar

@adrianco Yeah, the data point I'm looking for is whether or not AI topics are a focus at technical conferences (non-data science) outside of the usual hubs, e.g. SF/NYC/Paris, etc.

adrianco,
@adrianco@mastodon.social avatar

@joy This conference is a deliberate outlier. It’s always been whatever is the latest stuff and it’s always been held here because it’s a long way from anywhere and that acts as a filter to make people engage more.

hazelweakly,
@hazelweakly@hachyderm.io avatar

@adrianco AI development conference, eh? Sounds interesting, at least :)

  • All
  • Subscribed
  • Moderated
  • Favorites
  • random
  • tacticalgear
  • DreamBathrooms
  • cisconetworking
  • khanakhh
  • mdbf
  • magazineikmin
  • modclub
  • InstantRegret
  • rosin
  • Youngstown
  • slotface
  • Durango
  • kavyap
  • ngwrru68w68
  • JUstTest
  • everett
  • tester
  • cubers
  • normalnudes
  • thenastyranch
  • osvaldo12
  • GTA5RPClips
  • ethstaker
  • Leos
  • provamag3
  • anitta
  • megavids
  • lostlight
  • All magazines