A few observations... 1. Muse, GrokBot and Dot feel very different a. Muse is dead simple to use, Grokbot gives the most control and each targeted fora different type of user. Feels like Dot is the middle ground. 2. The interface is starting to become confusing and fragmented. We've got Spaces, Dot, Live voice mode, a separate dot feature calling mode. I think OpenAi needs to spend some time consolidating. 3. I like the human and agent collaboration built into Dot, but unsure if a Google Docs/Notion canvas is the way to go. There must be a better/more innovative solution to this problem. 4. They are going to have to nail that pro-active agent that shows relevant information at the right time. Muse is getting really good at this.

Hahaha I am dying guys 💀💀💀

This is so true.

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…

The better AI agents get, the less I want to chat with them. Chat made AI accessible. But agents need a quieter interface: work in the background, bring the human back when judgment matters. bretthamlin.com/posts/ai-age…

Also known as tinkering. It's the combination of expertise with play, and it's euphoric. This is why Claude Code and similar are so addictive (in a good way). The distinction between vibe coding and hacking/building/etc. is just how much knowledge you have when playing.

24x7 even at 35,000 ft

LLM prompt tip: If you want strict execution → give only the exact step. “Run this command.” No extra context. If you want the model to find workarounds → give more details about the problem. Less context = follow instructions. More context = problem solve.

A statement from Anthropic CEO, Dario Amodei, on our discussions with the Department of War. anthropic.com/news/statement…

Don't think of LLMs as entities but as simulators. For example, when exploring a topic, don't ask: "What do you think about xyz"? There is no "you". Next time try: "What would be a good group of people to explore xyz? What would they say?" The LLM can channel/simulate many perspectives but it hasn't "thought about" xyz for a while and over time and formed its own opinions in the way we're used to. If you force it via the use of "you", it will give you something by adopting a personality embedding vector implied by the statistics of its finetuning data and then simulate that. It's fine to do, but there is a lot less mystique to it than I find people naively attribute to "asking an AI".

Vintage computer play area ✅

Dr. Shrimp Puerto Rico... AI Generated - First attempt, playing around with Midjourney. @Joe_Gatto @SalVulcano @BQQuinn @jamessmurray

Programming is an art – don't spend all your time sharpening your pencil when you should be drawing 🖼

Swift engineering speak for “Have you tried rebooting it?” 🤣 1. Clean build folder 2. Delete derived data 3. Pod deintegrate/pod install 4. Update to latest SPM

You think you're unique until you have to buy a domain for your startup.

Only a few days before WWDC, Apple has a major developer-relations problem. It isn’t the 30%, or the 15%, or the App Store rules. It’s what Apple’s leadership thinks of developers and our work. marco.org/2021/06/03/develop…

Hello, world. My first look at my forever home. #CountdownToMars

Reminder fo what capitol "security" in full military-grade riot gear looked like for Black Lives Matter protests this summer.

weekend reading forums.swift.org/t/swift-con…

Excited to announce my caching framework "CacheIt" has been open sourced! github.com/zillow/CacheIt