We tax cigarettes to reduce smoking. We tax alcohol to reduce drinking. We tax fuel to reduce driving. What do you think happens when you tax employing people and running a business? https://t.co/QoriJQ3rpr

.@weaviate_io is an AI-native vector database that allows you to store data objects and vector embeddings from your favorite machine learning models while scaling seamlessly into billions of data objects. AWS and @nvidia work together in an ecosystem to deliver cost performance and efficiency for Weaviate. Weaviate is available in AWS Marketplace, making deployment within an AWS environment straightforward and accessible.

How did 8.5 million people build software on @emergentlabs without writing code? The startup is taking a different approach to AI-powered coding, helping entrepreneurs and small business owners build apps without writing a single line of code. Working with AWS, Emergent has built the infrastructure needed to scale rapidly, supporting 8.5 million users across 190 countries.

@sarahtavel https://t.co/9kdpKCBx23

@ValsAI https://t.co/9kdpKCBx23

@VaibhavSisinty https://t.co/9kdpKCBx23

Claude Sonnet 5 just failed the AGI test 😭 https://t.co/yi8sfZ1F1c

The conversation around AI at work is starting to change. Companies like Ford, IBM and Commonwealth Bank are finding that replacing experience isn't as straightforward as many expected. The biggest opportunity may come from combining AI with human expertise, not choosing one over the other.

Orca The World is in Your Mind https://t.co/cGGby5MU8K

paper: https://t.co/gD6tgeLIOt

Grok Build just got another workflow-focused update, bringing smarter controls, improved reliability, and better performance. Release Notes: v0.2.80 — 2026-07-01 Features: • Command timeouts can now be configured per session with a foreground-only ceiling. • Background tasks and TODO lists now survive compaction and remain visible to the model. • Contextual hints can now be toggled individually for undo, plan mode, and image input. Bug Fixes: • Subagent dialogs now reliably show full transcripts on open and reopen. • Recap blocks now copy only the summary body, not the header label. • Vim navigation keys now type into dashboard prompts, and modals properly handle Esc/Left. Performance: • Network connections are now more resilient to proxy/load balancer drops.

Creating AI voice agents has become ridiculously easy xAI’s Grok Voice Agent Builder lets you deploy a human-like voice agent in under 2 minutes - no coding required It is currently in beta, but the stack is already powerful: • Natural real-time conversations • Sub-second latency • 25+ languages • Free phone number or bring your own • Build and deploy directly from your browser Combined with Grok’s industry-leading voice models, we are getting closer to AI voice agents that actually sound and respond like real humans Try it here: https://t.co/mwJm6GCTFz⁠

SAMUEL ADAMS: "It does not take a majority to prevail, but rather an irate, tireless minority, keen on setting brushfires of freedom in the minds of men." https://t.co/cnxIaIMK4a

Hermes Agent (@NousResearch) understands my weekly routine and picks up preference changes from my Notion dashboard. It suggested a better time for my weekly review without me asking, asked for approval before making the change, and improved its own workflow in the background. When set up correctly, small, thoughtful actions like this are what make an AI agent an actual assistant. Great work by the team @Teknium 🙏

A few tips for the /learn command in Hermes Agent that made it way cleaner for me. Keep a separate "classroom" directory. Just a plain folder where all your learning and skill-building lives, away from your actual project context. Inside it, keep a "textbook" file with the key paths and links you reuse: your Claude Code sessions folder, GitHub, folders full of papers, whatever. Then you can start a session, say "review the last Claude Code session, check the textbook," and it knows exactly where to look. That's the trick I like most. You can pull a whole Claude Code conversation into Hermes as a source (point it at the sessions folder, or copy a specific session ID and have it search just that one), then /learn it into a reusable skill. Doing it in the classroom instead of your project session means you can talk through exactly how you want the skill to look without muddying your project's context, and every skill you build lands in one folder you can go back to. I'll be having a full video on /learn next week, so be sure to subscribe to my YouTube channel!

Super proud to say that the team and I put almost all our effort into resolving every P0 and P1 issue and PR in the entire Hermes Agent repo over the last week and a half, and as of 5 minutes ago, after an all-nighter, we've resolved 100% of them all! Extremely special shoutout to @Kshitijjkapoor who's been burning them away with me day and night! We aim to keep all of them 0 forever from here 🫡🫡

+2 more

Woops mixed up one of the images lol, the final one https://t.co/6Ld0LvpXRA

@LLMJunky https://t.co/9kdpKCBx23

@hqmank https://t.co/9kdpKCBx23

@k_matsumaru https://t.co/9kdpKCBx23

@anujcodes_21 https://t.co/9kdpKCBx23

@cyrilXBT https://t.co/9kdpKCBx23

@cyrilXBT https://t.co/9kdpKCBx23

@Oluwaphilemon1 https://t.co/9kdpKCBx23

@stevibe https://t.co/9kdpKCBx23

@dedene https://t.co/9kdpKCBx23

@dotey https://t.co/9kdpKCBx23

@mikenevermiss https://t.co/9kdpKCBx23

@Jean_Maes_1994 @AnthropicAI https://t.co/9kdpKCBx23

@AndrewE_Dunn https://t.co/9kdpKCBx23

@VenkatBalakumar No worries, it's not a pre-requisite, but more of complementary resource: https://t.co/r59qByata3

Introducing SWE-Together: a multi-turn benchmark built from real user–agent coding sessions. Coding agents are often benchmarked like exam-takers: given the full spec up front, then graded on the final code. But real coding help is a conversation — users clarify goals, add constraints, and correct course along the way. SWE-Together turns real coding work into a reproducible, verifiable benchmark: 109 repo-level tasks curated from 11,260 recorded sessions, replayed with a reactive LLM user simulator that preserves the original user’s intent. We evaluate agents as collaborators, not just patch generators: final pass rate and how many user interventions were needed to get there. In this evaluation snapshot, claude-opus-4.8 currently leads among the 7 agents we tested — achieving the highest pass rate while requiring the fewest user interventions. 📄 Paper: https://t.co/Zp5BSPpLTJ 💻 Code: https://t.co/NPgxCMLdHi 🌐 Website: https://t.co/BK50zRGReE