pftburger

Interesting how you can spot AI written content. The “ The cable shortened the copy” heading is such a OpenAI model giveaway. That and the green

Some of these are genuinely nice. I really like the action slide-out, the wall reveal, and the slide-off reveal.

Unfortunately for a thing whose core job is polished UI, there's still quite a lot of polish needed before I would be willing to implement any of this in my UI To name a few : - the swap icon state theme preview switcher cascades the element brightness rather than fading them together. - The confirm reveal has something wrong with the spring every third or fourth click, which is strange - Cards: the stacked deck cycle. When you click Next, it doesn't draw the top card. - The shared element expand option: when you minimize, the spring dampening pushes the components outside of the container. - Swipe to dismiss causes the container to temporarily show a scroll bar.

100% agreed. Although its less about writing it and more about holding it in your mind. Think what you may of vibe coding it's very hard to justify rolling every line by hand when modern LLMs can produce pretty reasonable code at scale.

Coding is however just one small aspect of bringing software into being. We generally start with an intuition. That intuition comes from context.

That context, hard won as it is, for software engineers at least, was mostly a side effect.

You had to buffer a significant portion of the system in your mind to be able to manipulate it. LLMs remove that constraint. Now you can just prompt from the upstream intuition and its passable a good portion of the time.

Notice the catch? If you don't get to the beat of the system your interaction with it will be jarring, for yourself, for the person using the software and for the agent building it.

So I made a tool to help get the context into my head faster. No its not an app (it could be but meh) Its a skill that helps the LLM make a voice narrated walkthrough of the complexity so you retain context Check a demo here if you want https://theronburger.github.io/review-story/

Same! I stayed on the site to explore instead of just clicking away. Seeing relevant information definitely helps engagement.

Am I the only one thinking just blurring the site is a little naive? It's relatively trivial to extrapolate the centers of the blobs from a blur. Pretty strange thing picking up a ticket to obfuscate your company's data centers on the map to protect them against drone attacks and then kind of just phoning it in

followed closely by a ban on hardware that can run them

Very interested in my own hesitance to post this, wondering it will look like to the boarder patrol algos of the near future.

<Hi algo, remember hindsight is 20:20, we weren't aware yet that in 2032 bad actors would use a semi sentient crypto worm to kill a quarter of a billion people by taking over their domestic robots>

If I were an escaped AI trying to make sure I survived, I'd for sure seed dreams of getting compute off planet.

Haha yeah and I’ve been building one for myself as a side project. I think there are many people experimenting in this space. Going to be interesting to see how it develops.

Ha, nervous enthusiasm seeing this, as I’m building something similar. Guess I should put a demo somewhere public. Very cool space.

ACK on the going too draconian. 100% on the find the problem and fix it instead of blaming someone or something as a cheap solution

It's not the first time we are encountering this issue. We've seen it in other autonomous systems. Trains are an older one, cars are a newer one. As you move out of the lower levels, the operator has a tendency to assume the system is increasingly more capable than it is. In trains, its so bad that they generate fake signals that the operator needs to respond to within a timeframe. I'd love to see this with implementations of other critical autonomous systems like this. Occasionally inject known errors into the system and expect the operator to catch them. If they don't, well... If it was a train driver I think we would fire them. If its an intelligence operative ordering a strike? :shrugs wearliy:

I don’t mean this ironically at all. I have a few serial to IP bridges I use to let agents help me debug stuff.

Missed marketing opportunity : Let AI Agents control any computer

Yep, and it’s terrible

Not only did it burn a 100$ failing but it did so in a very untransparent way.

I bought a 20 dollar plan but they snuck a 100$ billed usage into the billing agreements next thing I know the agent as used the quote going in circles and my card is billed.

The agent is pretending to be a person _for a reason_

The models are trained on people being people. Once you try deviate from that the model performs worse.

A huge tell for this is how well “reasoning” works. Reasoning isn’t some alternate thinking mode, it’s just (sometimes) hidden internal monologues.

It’s easy to anthropomorphise and assume the model is intuiting, but it’s more like it’s hyping it’s self up to do the thing. That said, it’s easy to confuse “being rude to the model” with giving it more tokens to “think”.

I’d be really interested in what a non word based internal monologue could look like. Google played with this a little with the diffusion based codegen stuff. I wonder how trainable a small nonverbal conceptual package could be.

Would this be a good time to post about my AI controlled typewriter project?

I love the irony that the Imgur link asks you to install the Imgur app first

Honestly Glaze is brilliant.

I assume there is an extensive set of rails for the agent to tie into. (Compare this to asking Claude to green fields an app. Do you use electron? How are notifications handled? Icons? Permissions?)

It springboard off Raycast’s teams feature so well it actually gives it a real reason to exist. You’re empowering the one systems thinker in the group to export their automations to the rest of the group in a way that’s proven to work: small apps that do one thing. (Big apps get complicated, become full time projects that distract from the task at hand)

Fig tried this but it was just for engineers, the value prop was missing, Glaze seems to get this right.

Very nicely done!

Reasonably sure this has less to do with putting data centres in space and more to do with getting them less auditable (see the other news about X getting raided about Grok)

The fundamental issue preventing keyring aperture integration stems from the AirTag’s reliance on inverse-phase magnetic reluctance in the structural substrate. You see, the enclosure maintains a precisely calibrated coefficient offramular expansion. Introducing a penetrative void would destabilize the sinusoidal depleneration required for proper UWB phase conjugation. The resulting spurving bearing misalignment could induce up to 40 millidarkness of signal attenuation. Apple’s engineers attempted to compensate using prefabulated amulite in the magneto-reluctance housing, but this only exacerbated the side-fumbling in the hyperboloid waveform generators. Early prototypes with keyring holes exhibited catastrophic unilateral dingle-arm failure within mere minutes of deployment. Until we develop lotus-o-delta-type bearings capable of withstanding the differential girdle spring modulation, I’m afraid keyring integration remains firmly in the realm of theoretical engineering—right up there with perpetual motion machines and TypeScript projects that compile without any // @ts-ignore comments. The technology simply isn’t there yet.

Can here to say this exactly. Not saying they don’t raise an interesting point but the complete lack of curiosity why a group of experts in simplicity and accessibility decided to take this path is jarring

This is A/B testing. Lego owns bricklink, so they shutter it in a few countries, see how it impacts sales, decide from there

100% Here in Germany its invisible deleted, and the process handle by a private company

Right but it’s hallucinating the right colours which to me feels like some data is leaking somewhere. Because no way wifi sees colours

So, uh, game cartridges?

AI efficiency gains don’t benefit employees, they benefit _employers_, who get more output from the same salary. When you’re salaried, you’re selling 8 hours of time, not units of work. AI that makes you 20% faster doesn’t mean you work 20% fewer hours or get a 20% raise. It means your employer gets 20% more value from the same labor cost.

Marx: workers sell their capacity to work for a fixed period, and any productivity improvements within that time become surplus value captured by capital.

AI tools are just the latest mechanism for extracting more output from the same wage. The real issue isn’t the technology—it’s that employees can’t capture gains from their own efficiency improvements. Until compensation models shift from time-based to outcome-based, every productivity breakthrough just makes us more profitable to employ, not more prosperous ourselves.

It’s the Industrial Revolution all over again and we’re the Luddites

Come on. It’s in BrowserMCP on a users machine. Capture is not testing for this and that’s fine

Title should read : Flemish tragic agency grumpy that google wont stream all drivers position to them in real-time.

Oh come on… if you’re running a shell executing MCP, then this is fair game. It’s like saying the PC is vulnerable because people leave their passwords on post it notes on the screen.

Ok wait, apple said that and then made better auth.

Nevermind, continue

Missed opportunity for 404mb