ElevenLabs just dropped Eleven v4, and this whole voiceover is v4 🤯
Whispers, laughs, accents and sound effects, all from simple tags. 90+ languages, and v4 Turbo starts talking in ~150 ms. Ranked #1 on Artificial Analysis.
#elevenlabs #aivoice #texttospeech #aitools #ai
2
18
39 terminals is an orchestra. gave it a downbeat 🔊
i have 30 AI subscriptions:
- 17 @ChatGPT Pro 20X
- 7 @DevinAI Max
- 5 @claudeai Max
- 1 @cursor_ai Ultra (via @bot)
i'm rocking 39 terminals today in @zeddotdev
- 28 Devin with SWE-2 (free+unlimited on the Max plan)
- 11 Claude Code with Opus 5.5
- (many subagents inside each)
hope you're having a great weekend too
14
quest accepted
The best way to make friends as an adult: Sign up for a new side quest. It could be a race or competition. Maybe a hiking adventure. Or some new creative hobby. Really whatever. It opens your life to an entirely new community of people. People you’d probably never have met or interacted with otherwise. Suddenly you have a shared mission. Group chats form. Daily texts start flying. Regular get togethers happen. Tons of new energy breathed into your life. I think we all need some Side Quest Friends. Sign up for that thing that scares you a little bit. Watch your whole life improve.
2
14
employee of the month. every month
Tag writes >50% of my PRs every day. It also does ~100% of my data analysis, and fixes most of our product feedback + bugs.
It's not like a regular Slack bot. It is proactive, programmable, it has memory, it has access to your connectors. With Opus 5.5 and Fable 5.1, it has strong judgement.
Example prompts I use:
- "@Claude react to threads in this channel with ✅ when resolved"
- "@Claude from now on, attempt to repro every bug in this channel end to end, running the full app. once you reproduce the bug, put up a pr to fix it and tag the right team for code review"
- "@Claude brainstorm ~100 hypotheses for what could explain this weird data, use a workflow to in/validate. spend 10m tokens or so digging very deep. draw a chart with the result."
- "@Claude make me an interactive game explaining how this part of the code works, then make a slide deck explaining it for others on the team"
claude.com/product/tag
1
22
switching models empties the cache. jev-router just turns the effort knob instead. animated how it works
Introducing typesafe/jev-router: a cache-aware model router powered by Jev and @typesafeai
The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost.
Here's how it works 👇🏻
2
53
the 1 thing a week, handled. made your escalate button into a little concept film
Every personal agent right now is fully AI. Muse, Instinct, all of them.
Here's what I want from a personal agent: an escalate button.
These apps handle almost everything, and then there's the 1 thing a week that needs an actual person. Right now I'm the person. I'd pay real money for a button that hands the job to a human who finishes it and reports back.
Meta tried this in 2015 with M and shut it down in 2018 because the human trainers ended up doing most of the work. Humans did 90 and the AI did 10, so every user cost a fortune. That ratio is flipped now.
Instinct is worth $10B and it never hands anything to a person. I'd love to know what the version that actually finishes the job is worth! I think it's an interesting startup idea.
At the very least, I'd download it.
26
the shortest commute in software
cut off mid-edit vs a graceful stop. animated the change in EndFrame, which runs on the Claude subscription you already have
Claude Code will now try to find a graceful stopping point when you hit your 5-hour limit mid-task, instead of cutting off mid-edit. It gets a small, fixed allowance pulled from your weekly limit to wrap up what it can.
2
43




















