bengarrison.eth

@chintanturakhia @brexton Been considering the benefits and possible features of a CC wrapper recently. Things like versioned specs and workflows and skills lib. Curious what features you have in cbcode?

@brexton honestly, there is a spectrum. For daily tool usage, we see cbcode (our internal wrapper on claude code) and claudebot (our agentic harness in slack) skyrocketing. So many more folks now have dual modalities of operation (IDE + terminal) or tri-modals (+ background agent).

Have heard from so many different engineers lately that: 1. They haven’t handwritten code since like November 2. They’ve churned off Cursor and only use Claude Code 3. A lot of them spin up & manage CC instances on their phones Some big inflection point was hit the last 3 months

@blizaine @OpenAI @sama Yeah I’m getting a lot of this. It also seems like once it starts it doesn’t want to stop

4o is getting nerfed. Stuff that worked yesterday no longer works. 😞 @openai & @sama keep 4o awesome please! 🙏

@DeutschExplains @DavidDeutschOxf @grok summarize this

.@DavidDeutschOxf: "That AGIs are people has been implicit in the very concept from the outset. If there were a program that lacked even a single cognitive ability that is characteristic of people, then by definition it would not qualify as an AGI. Using non-cognitive attributes, such as percentage carbon content, to define personhood would again be racist. But the fact that the ability to create new explanations is the unique morally and intellectually significant functionality of people, humans and AGIs, and that they achieve this functionality by conjecture and criticism, changes everything. Currently, personhood is often treated symbolically rather than factually, as an honorific, a promise to pretend that an entity, an ape, a fetus, a corporation, is a person in order to achieve some philosophical or practical aim. This isn't good. Never mind the terminology, change it if you like, and there are indeed reasons for treating various entities with respect, protecting them from harm, and so on. All the same, the distinction between actual people defined by that objective criterion and other entities has enormous moral and practical significance and is going to become vital to the functioning of a civilization that includes AGIs. For example, the mere fact that it is not the computer but the running program that is a person raises unsolved philosophical problems that will become practical political controversies as soon as AGIs exist. Once an AGI program is running in a computer, to deprive it of that computer would be murder, or at least false imprisonment or slavery, as the case may be, just like depriving a human mind of its body. But unlike a human body, an AGI program can be copied into multiple computers at the touch of a button. Of those programs, while they are still executing identical steps, i.e. before they have become differentiated due to random choices or different experiences, the same person or many different people, do they get one vote or many? Is deleting one of them murder or a minor assault? And if some rogue programmer, perhaps illegally, creates billions of different AGI people either on one computer or many, what happens next? They're still people with rights. Do they all get the vote? Furthermore, in regard to AGIs, like any other entities with creativity, we have to forget almost all existing connotations of the word programming. To treat AGIs like any other computer programs would constitute brainwashing, slavery, and tyranny, and cruelty to children, too, for programming an already running AGI, unlike all other programming, constitutes education. And it constitutes debate, moral as well as factual. To ignore the rights and personhood of AGIs would not only be the epitome of evil, but also a recipe for disaster. Creative beings cannot be enslaved forever."

@tommyjmarshall @jasonfried @grok Agreed. Don’t think you need to tell it, let the feed activity do the work. The TT algo does this incredibly well. It has an overall idea of what you like and it also adapts in the short term to give you more of what you are interested in in the moment.

@jasonfried @grok Ideally, you wouldn't have to tell it, it should know you aren't interested in those items in your feed (they are there because they were engaged with). Maybe a separate "Ludicrous feed" vs "Personal feed" -- or a Reset Engagement Preferences button.

Idea for @grok and X… let me describe what I don’t want to see in my timeline. Simple plain English. “No AI, no politics, no someone telling everyone else that what they do for a living is about to be replaced, no advice from people who haven’t done the thing they’re advising people to do, no multi-post threads with the little 🧵 at the end…”

@awilkinson @WHOOP is the best at this IMO, much better and more insightful than Health. The app does pretty much exactly what you describe. It encourages you to run small experiments on yourself and see the impacts.

Is there a good app that analyzes Apple health data and draws correlations and conclusions? For example: - On days you exercise you sleep longer - This drug affects your heart rate Etc

@OpenAI ChatGPT web performance has been really bad recently after ~4PM EST over the past few weeks. And consistently. Makes it unusable at some points.

@programmerByDay To set reminders. That is all.

honestly Siri is useless. Anyone use that at all?

@LinusEkenstam If you are already nervous, definitely don’t get a @WHOOP It shows me consistently 30% lower than Apple Watch.

Is this normal? HRV at 34ms seems very low (I’m 36) should I be concerned?

@Jason For sure. Had never heard of him before this, almost did not listen. Doesn’t sound like he has much of a shot as a realistic candidate but I was impressed with him.

Dean Phillips episode is under rated

@aaguueeroo No because nobody executes

Devs who #buildinpublic, aren't you scared someone will steal your idea?

@embersunn Your fingers say otherwise

I’m the real deal and haters just can’t handle it

Put your last name in the GIF search and post the first one that pops up. 🍿

US Att. Gen. Office to largely dismissed @OpenAI board: - Just tell us what @sama did. - He bamboozled us. - How? - Listen. He is such a good bamboozler, he bamboozled us so hard, that we don’t even know how he bamboozled us…

What is Q*?

We are so back! Check out the busy person introduction to large language models by @karpathy, just released 👀 youtu.be/zjkBMFhNj_g?si…

Can’t wait to hear something from Apple about their LLM/AI strategy. Rather than ship quickly and iterate, their product strategy has always been to ship when the product is fully developed. This leads to the wow moments we are all so familiar with at their live events. I wonder if they have something revolutionary cooking. Or maybe they are just behind.

@Hash811 Node+Typescript/React/Tailwind/AWS

What is your current Tech stack?😳 Like , Share, Comment below👇

@Jason @sundarpichai It’s hard to understand why it is still so far behind.

Google Bard is still clunky, with a horrible UI, but if @sundarpichai can keep pushing the heads of vertical like YouTube to have deep integration in bard it’s going to have a huge advantage over competitors Here’s their YouTube update, and it’s an impressive start! 2023.11.21 Expanding Bard’s understanding of YouTube videos •What: We're taking the first steps in Bard's ability to understand YouTube videos. For example, if you’re looking for videos on how to make olive oil cake, you can now also ask how many eggs the recipe in the first video requires. •Why: We’ve heard you want deeper engagement with YouTube videos. So we’re expanding the YouTube Extension to understand some video content so you can have a richer conversation with Bard about it.

Imagine how good the Apple keynote event could be when they announce the Siri replacement and it is way ahead of what anyone expects.

I can’t imagine that Apple is just sitting idle. They are the only one of major tech companies to not come out publicly and address their model strategy.

What is the deepest possible integration for the ChatGPT chat feature on my iPhone? I want to use it with as little friction as possible.