Botanium

I made Say for Codex. Type `/say` after an answer and Codex reads it aloud locally on macOS. No API key. No sending text to a TTS model. No pasting long reports back into chat. Useful when you want to listen while reading, or review long agent output hands-free. Link below. skills.sh/botanium/say/s…

@isausmanov The hackathon just started

The agentic phone that won OpenAI Hackathon is replacing my iPhone feature by feature. Found Amjad Masad’s contact, emailed Paul Graham, and called on my behalf to reschedule a meeting. Its KPI is how little time I have to spend on it while getting more done.

@DavidOndrej1 check the bench marks, and try them in different use cases. I find them very useful, and some areas very bad.

GPT 5.6 Luna is trash

@steipete Idon't know how you do it, but I wish you could share a video about your actual workflow and how you manage all these works.

That's about as many sessions as my Mac Studio can take.

@nilbuild Nice, do you have it on GitHub?

Finally got this working the way I wanted. I've got so many ideas for where this can go. Excited!

@Sevenmoneymaker @sama We can all complain about Sam, but he did create the best product in Ai. You can't argue that.

Elon is right—you are the biggest con artist in the AI ​​world! An extreme profiteer! More and more people will see your true colors, anyone who still believes you is a fool. I’m waiting for your karma. Scam Altman and CloseAI are perfect match. #StopAIPaternalism #OpenSource4o #keep4o #BringBack4o

homeboy you're the one sellling public market investors on short-term space datacenters

@sama Wow, let's enjoy the show.

@trq212 I have always thought about my knows and unknows, but I could never articulate it that clearly. Your article is exactly what I was hoping to work on my projects. This clears all the thought fogs I had. Very clear and useful.

I have been testing GPT-5.6 Sol for the last 30 minutes. The difference is huge.

Grok 4.5 it is something else, it is exteamly good, especially when you set up with Codex for review.

@OpenAI How do I get a preview access?

GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday. We’re expanding preview access globally now.

@thsottiaux I am still waiting for it. Counting minutes.

Can't wait to see what people will do with GPT-5.6 Sol Ultra. Stash your hardest prompts somewhere.

@DavidOndrej1 They are trolling us

it's fucking 9.09pm here in Poland Fable nowhere to be found it's July 1st what the fuck Anthropic

@mattpocockuk Beautiful

Getting sick of setting up third-party services So I built a skill for it /wizard builds you an interactive CLI for the task you're currently doing, and takes as much work off your hands as possible #1 is how the agent described the wizard, #2-3 is what it looks like:

@AnthropicAI @boxmining Is it the actual Fable 5? Or the dumb version of Fable 5? Maybe it is Opus 4.8 dressed as Fable 5?

Claude Fable 5 will be available again globally tomorrow. After a series of productive conversations with the US government, we're redeploying the model with a new set of classifiers to target and block more cybersecurity tasks. In the near term, some routine tasks like coding and debugging will fall back to Opus 4.8. We’ll continue to refine these classifiers over the coming weeks to reduce false positives and better distinguish genuine misuse from legitimate requests. We’ve also begun drafting a consensus framework—with Amazon, Microsoft, Google, and other Glasswing partners—for assessing the severity of AI jailbreaks and how AI developers should respond to them. We invite other industry partners and model providers to join us in this effort. Finally, we’re scaling up our collaboration with the US government on model testing and safeguards. This will include pre-release access to models and safeguards for evaluation, information sharing on jailbreaks and misuse, and dedicated resources for joint research. Thank you to our users for your patience, and to our partners across the government, industry, and the research community who worked alongside us to make Fable 5 available again. Read our full blog: anthropic.com/news/redeployi…

@runfusion this doesn't support Openai Subscription? OAuth?

Your software factory is ready. Agent teams, group chat, observability. Missions. Planning mode. Kanban. Workflow engine. Ship faster, ship better. runfusion.ai

Very well done.

@rauchg I am going all in into EVE for interprice level agents.

The next hot programming language is… markdown. A minimal eve agent: 📂 𝚊𝚐𝚎𝚗𝚝/ 📄 𝚒𝚗𝚜𝚝𝚛𝚞𝚌𝚝𝚒𝚘𝚗𝚜.𝚖𝚍 📂 𝚜𝚔𝚒𝚕𝚕𝚜/ 📄 𝚢𝚘𝚞𝚛-𝚎𝚡𝚙𝚎𝚛𝚝𝚒𝚜𝚎.𝚖𝚍 Deployable in one command: 𝚟𝚎𝚛𝚌𝚎𝚕. It’s the most accessible programming has ever been. And likely will ever be, at least for the generation of software fully defined and controlled by us humans. (As a fun fact, one of the initial prototypes for eve was codenamed 𝚕𝚊𝚜𝚝 by @timolins, both in homage to ‘@nextjs for agents’ but also in recognition of how enduring eve’s design feels to us.)

@N01ennn these are neural networks not agents, your videois misleading @CommunityNotes

A 21-YEAR-OLD FROM CHINA RUNS 300 AI AGENTS AT ONCE. THE PART THAT MATTERS ISN'T THE SPEED, IT'S THAT NONE OF THEM CAN LIE TO HIM he opens the dashboard and shows the swarm live, 300 Kimi K2.6 agents firing in parallel, then Opus 4.8 checking every single output against its source. this is not just a faster swarm. it is a loop that refuses to stop while anything is still wrong he pointed it at 100 EV-market companies. first pass: 12 failed. wrong revenue, dead citations, empty fields. second pass: 3 failed. third pass: zero this is not another agent demo. it is a system that catches its own mistakes before he reads a single row

@mfpiccolo this is solving a lot of issues for developers.

The old paradigm of adding a new service and integrating it to all others is dead. Find out how iii killed it in 563 seconds.

@SenWarren Do you even realize that everyone knows you are a fraudster?

If Elon Musk paid my ultra-millionaire wealth tax, we could pay for child care for all three and four year olds in America.