Keep it simple: a single orchestration thread that you ask it to orchestrate your tasks in dedicated threads. Works great. Keep giving it tasks as they come up!
Aaron retweeted
We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence.
block.xyz/dessa
Aaron retweeted
Today we announce 1Password for Agents platform, building with companies @Muse, SpaceX Super Intelligence Grok @Bot, @AnthropicAI’s @Claudeai, @OpenAI, @TownAI, @Browserbase, @Browser_use, @heydana_ai, Instinct, @usekernel, @Perplexity_ai, @tryramp, @Tomo, and @wajo_ai, with more integrations on the way. 🎉
We've heard from so many of our customers who want to use these new personal AI agents to help them get more done, but want more control over what the agent can access with the same trust and ease of use they get when using 1Password directly.
1Password for Agents gives your agents access without giving up your passwords. When an agent reaches a sign-in form, it requests a credential from your vault. If you approve the request, 1Password directly auto-fills the credential in the destination site so the agent can’t see or take possession of the credentials.
The agent gets the task done, but it doesn’t get your passwords..
You stay in control. 1Password for Agents free and optional for personal and family accounts. Unless you opt-in to an agent connector, agents cannot touch your vault.
➡️Learn more: bit.ly/487da6J
Aaron retweeted
Day 16/
You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.
Are we destined to have a fragmented landscape? I can't tell if this is good or bad. So long moving costs are negligible, this might be good - more innovation, more competition.
Cloudflare is collaborating on tsrs, a Rust port of TypeScript that is up to 8x faster and uses 70% less memory. cfl.re/3Whs9bC
I have obviously been using Dots wrong, or a recent update was made. Thank you for kinda solving passwords. Secure sign-in LFG.
One of the cool things we can do now with LLMs is make improvements on the small things as well as the big things, with little effort. Like keeping the image occupied space consistent even when images are hidden by default when reading emails.
Till this day, the quickest way I can improve a design for my POCs is with the line “You are an expert designer at vercel”. Opus or Sol, works great!
Because of computer use and the amazing capabilities of LLMs, creating Google CASA demo videos has never been easier.
Way back when Granola had first come out, I had really wanted an app that just ingested my conversations (Slack, Email, Transcripts, etc.) and detected new ideas, tracked, existing convos etc, and kept it updated.
I just got this going with Dots. Frickin sick.
