We're launching our first-ever workshop, and we have a lot more planned. If there's a topic you'd love us to cover, hit reply. First up: Harness Engineering. Prompt engineering taught us to write better inputs. Context engineering taught us to structure better information.
TOOLS
-
Replit Launches AI-Powered Slide Deck Generator for Core and Pro Users
By
–
Introducing Replit Slides!
— Replit ⠕ (@Replit) 30 avril 2026
Made an entire pitch deck in under a minute without touching a single slide. Just describe what you want, chat to iterate, and export to PowerPoint, Google Slides, or PDF (or publish a live URL). Slide Decks are available to Core and Pro users. 🎯 pic.twitter.com/Qe2f6y8g9cIntroducing Replit Slides! Made an entire pitch deck in under a minute without touching a single slide. Just describe what you want, chat to iterate, and export to PowerPoint, Google Slides, or PDF (or publish a live URL). Slide Decks are available to Core and Pro users.
-
Agentic Harness Boosts Coding Agents 10% Without Model Changes
By
–
You can now make coding agents 10% smarter without touching the model. Coding agents rely on a "harness" of prompts, tools, and configurations that shape how they work. Tuning this harness is usually manual, slow, and breaks easily. A new paper introduces Agentic Harness
-
Lovable Integrates with Databricks for Natural Language App Building
By
–
.@Lovable now integrates with Databricks, enabling teams to build apps on governed data using natural language!
— Databricks (@databricks) 30 avril 2026
Business users can create dashboards, operational tools, and internal chatbots in hours, with apps that read and write data directly in Databricks. Data remains in… pic.twitter.com/Xo2DXPmkpg.
@Lovable now integrates with Databricks, enabling teams to build apps on governed data using natural language! Business users can create dashboards, operational tools, and internal chatbots in hours, with apps that read and write data directly in Databricks. Data remains in -
alphaXiv Partners with OpenRouter for Direct Model Access
By
–
alphaXiv 🤝 OpenRouter
— alphaXiv (@askalphaxiv) 30 avril 2026
Excited to announce our partnership with @OpenRouter
You can now hover over any model name on any paper, and you’ll be directly connected to OpenRouter.
In the pop up window, you’ll be able to see the provider name, model name, description, and its top… pic.twitter.com/cwOC1Cd7fHalphaXiv OpenRouter Excited to announce our partnership with @OpenRouter You can now hover over any model name on any paper, and you’ll be directly connected to OpenRouter. In the pop up window, you’ll be able to see the provider name, model name, description, and its top
-
alphaXiv: Explore Academic Papers Online
By
–
Check it out by visiting any paper on http://
alphaXiv.org! -
Frontier Model APIs vs Native Apps: A Growing Capability Gap
By
–
Increasingly, I think, we will see a gap between what you can do with frontier model APIs & what you can do with the native apps from the frontier labs (Codex, Claude Code). Models developed and trained with their native harnesses in mind have more capabilities in their harnesses
-
Codex and GPT-5.5 Updates Incoming to Maximize Capabilities
By
–
love to see it, lots more updates enroute to help you maximise what you can do with Codex & GPT 5.5 if you have any feedback please do send it my way
-
Using Codex and Cora Inbox to Autonomously Handle Emails
By
–
my goal for this week is to have Codex + Cora Inbox do all of my emails autonomously so far it's working!
-
Sequential vs Batched Execution Trade-offs in LLM Ensembles
By
–
3/5 Execution policies help, too: you can see how sequential execution (vs. batched execution) saves spend but drives up latency for the same GPT-5 + MiniMax ensemble.