HM Godoy

Video by TWiT Tech Podcast Network via YouTube

SpaceX Starship V3 is stepping onto the world stage with epic upgrades, new engines, and slick design changes. Rod Pyle and Tariq Malik breaks down what’s different and why everyone’s watching on This Week in Space!

You can find more about TWiT and subscribe to our full shows at https://podcasts.twit.tv
Subscribe: https://twit.tv/subscribe

Products we recommend: https://www.amazon.com/shop/twitnetcastnetwork
TWiT may earn commissions on certain products.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free shows, a members-only Discord, and behind-the-scenes access.
Join today: https://twit.tv/clubtwit

Join our TWiT Community on Discourse: https://www.twit.community/

Follow us:
– Bluesky: https://bsky.app/profile/twit.tv
– X: https://x.com/twit
– Mastodon: https://mastodon.social/@twit
– Facebook: https://www.facebook.com/TWiTNetwork
– Instagram: https://www.instagram.com/twit.tv
– TikTok: https://www.tiktok.com/@twittok
– LinkedIn: https://www.linkedin.com/company/twit-llc

About us:
TWiT.tv is a technology podcasting network located in the San Francisco Bay Area with the #1 ranked technology podcast This Week in Tech hosted by Leo Laporte. Every week we produce over 30 hours of content on a variety of programs including Tech News Weekly, MacBreak Weekly, Windows Weekly, Security Now, Intelligent Machines, and more.

Source

Video by Meta Developers via YouTube

Embedded signup v2/v3 deprecating Oct 15, 2026.
✅ One flow for WhatsApp, Instagram & Messenger APIs
✅ Fewer onboarding screens for your customers
✅ Upgrade takes less than one week
Full migration tutorial → https://bit.ly/4dvLuuM
Developer docs → https://bit.ly/4957smT
#MetaForDevelopers #BusinessMessaging #WhatsAppAPI #Shorts #DeveloperTools

Source

Video by Rasa via YouTube

In this clip from The Dialogue Architects, Eugenia Zeibig, a marketing AI leader in pharma, shares why enterprise AI only becomes useful when it understands the nuance of the business it serves — and why trustworthy outputs matter more than abundant ones.

Watch the full episode: From Reports to Responses: AI in Pharma Marketing

Views shared are Eugenia Zeibig’s own.

#EnterpriseAI #ConversationalAI #PharmaMarketing #AIInnovation #MarketingAI #HealthcareAI #Rasa

Source

Video by OpenSource via YouTube

POV: You spent 4 years studying computer science… then AI replaces entry-level jobs.

This graduate’s answer shocked everyone 😳

Do you think AI will make degrees useless or create new opportunities?

#computerscience #ai #programming #softwareengineer #kenya #graduates #artificialintelligence #coding #tech #shorts

Source

Video by OpenAI via YouTube

Codex began as a tool for developers. Today, people are using it for much more: research, planning, file organization, automation, data analysis, presentations, and other everyday knowledge work.

In this OpenAI Forum conversation, Chris Nicholson of OpenAI Global Affairs speaks with Thibault Sottiaux, Head of Codex, about how Codex is evolving beyond software engineering and what that shift means for workers, teams, and organizations.

Source

Video by H2O.ai via YouTube

Catch the recording to explore TabH2O, H2O.ai’s foundation model for tabular machine learning.

In this session, you’ll learn how tabular foundation models work and see live how TabH2O delivers predictions in seconds.

Source

Video by MLflow via YouTube

In the eighth installment of Mastering MLflow for GenAI, Jules Damji shows how to go beyond manual prompt iteration (covered in Notebook 1.5 / Episode 5) and use GEPA (Genetic‑Pareto) prompt optimization in MLflow to automatically evolve a baseline prompt into a stronger variant—while keeping everything versioned in the Prompt Registry and measurable with a clear before vs after comparison.

This episode uses a deliberately simple benchmark style inspired by short‑answer QA (similar in spirit to HotpotQA‑style “single token / one‑to‑two word” expectations): the model must stop being verbose and return only the expected short answer so an exact‑match scorer can fire cheaply (pure Python, no LLM calls in the scorer for this demo).

What you’ll learn
🔹 Automated prompt optimization with GEPA using MLflow’s integrated API: mlflow.genai.optimize_prompts
🔹 How to wire the three required pieces: training examples (input + expected output), a predict function (load prompt from registry → fill template → call LLM), and scorers (here: a @scorer exact‑match judge for fast iteration)
🔹 How GEPA’s loop works in practice: Evaluate → Reflect → Improve → Select → Repeat until convergence/budget
🔹 What “budget” means in this context (metric calls / iterations, not “dollars”), plus early stopping when improvements stall ( max_iterations_without_improvement in the walkthrough)
🔹 How optimization produces a new Prompt Registry version (baseline vs optimized), and how to read the run comparison from a weak baseline score to a strong post‑optimization score on the toy setup

Key takeaways
🔹 Scorer design is the product decision: exact match is great for crisp targets; LLM judges are for semantic nuance—but they change cost/latency inside optimization loops.
🔹 Prompt Registry + optimization is the scalable combo: treat optimized prompts as versioned artifacts, not one‑off string edits.
🔹 GEPA is meant to reduce the human “try prompt v17” grind by making improvement systematic—while MLflow keeps the evidence in traces/runs/metrics you can audit.

Resources
🔗 Notebook 1.8: https://github.com/dmatrix/mlflow-genai-tutorials/blob/main/08_prompt_optimization.ipynb
🎥 Full series playlist: https://youtube.com/playlist?list=PLaoPu6xpLk9EI99TuOjSgy-UuDWowJ_mR
📚 MLflow prompt optimization docs: https://mlflow.org/docs/latest/genai/prompt-registry/optimize-prompts/

Source