inerte

Oh so Flock doesn't just record / monitor stuff, but while doing so, it proactively tells the police a car worth stopping is on the street? How did the cop know how to stop the car?

Plus Stack Overflow was gamified. "Nothing to gain" except 12 different artifacts showing how awesome you are.

> Then maybe the need for your site is gone.

Oh yeah, and I am not mourning or anything like that. And I do want the human touch, because AI can't. But humans, at least over the internet, can send their agents, or companies can run agents and I won't know from my site if it's an actual human, or some AI fabricated interaction (can't even trust an image it uploads).

When AI first showed up a few years ago, I thought about opening an actual physical cocktail bar. Hypothesizing humans will be tired after a long day of their agents talking to other agents, they would crave for actual humans. I would ban electronics inside - no distractions. Maybe one day I will go for that...

I've been struggling with that.

I built https://gallotails.com/ because I am a cocktail enthusiast. First commit, March 6th 2019. One of the features I am proud is which cocktails you can build based on your ingredients, and I was smart, the bar ignores garnishes and can suggest cocktails you're one ingredient away. But you have to add the ingredients. And interpret the bar screen.

And here's what I did with ChatGPT a few days ago: https://chatgpt.com/share/6ab59877-4b74-83e8-8da5-966d9f3a38...

Clicked the microphone icon and rambled for a few seconds (could have just taken a picture too I guess). Nudged ChatGPT to only give me simple cocktails I can stir instead of using a mixer. Said I could buy a lime, sure. Then asked how to keep the ginger beer fresh.

There is NO WAY I can code all of that in my little gallotails.com - a single chat window has entirely replaced my site. And that's my pet little project I do it on weekends, mostly to keep my tech skills sharp. I can only imagine what the biggest cocktails website, actual companies, are going / will go through once more and more people just realize the chat tab is enough. And I am not talking about purely content, ChatGPT can do everything my site does, and more, into any direction, in an instant.

Which left me with the question, then what should my site be? Community? To be taken over by agents?

Currently munching on what sites like mine should do, and what they should be.

We can definitively punish bigger companies. The issue is the geopolitical positioning, and basically agreeing that we accept smaller companies in our country / society while another country might develop bigger companies, and in theory have more power. Maybe more actual military power.

So unless it's a worldwide agreement, really hard to make this happen.

This is a good resource https://howborisusesclaudecode.com/

My best takeaway from the site was: Every time you see Claude Code / Codex doing something you don't want, ask it to add to AGENTS.md. Specially if they churn a lot doing something, and eventually find a way. I ask it to store the way it made something work. It's a constant gardening of AGENTS.md and it has really working well.

Also likely, devs took shortcuts to deliver fast. Now to make the button blue they need to differentiate primary buttons from others.

Simple, right? But design guidelines prevent one offs, and no !important. So you create a CSS class, but you discover another element on the header declared itself as primary (the search icon or the sign in button). You talk to that team and they decided to scope what’s primary according to their component. To change the sign in button to grey now you need to talk with the growth team. Growth team wants to run an experiment but they’re backlogged, only next quarter. They say you can innersource, just need VP approval. VP says blue matches a marketing campaign that is about to go out, agency has already been hired. You can’t talk to the agency unless Legal approves.

So you leave the button gray, to revisit decision next planning cycle after you can align all stakeholders.

To be fair I’ve worked on human programmed systems where similar “it should be a half point story” requests would be met with snark by the engineers and take 2 sprints.

I guess we are all PMs now.

I was going to mention OP might be rediscovering https://beads.gascity.com/

No, embargoed news is super common. Almost every single product announcement goes through that. Critics watch movies early, companies have access to LLM model improvements early, car manufacturers send production models early… it happens everywhere all the time.

It depends on what software you’re building. The npm ecosystem is huge, hosting is easy, etc. Sure C can do it but it will take longer.

It is until ARC-AGI-4. Maybe around 73 we will stop.

Gee, 100%. Articles basically saying genetics explain everything.

What's the methodology? Is Gemini actual gemini.google.com or mixed with google.com and Android searches?

No, it has happened to almost every other "sota" model before. There used to be a meme with a circular arrow going through Anthropic, OpenAI, Google as a hype circle. Now we can drop Google and add a couple of Chinese companies.

It's not an explanation of why it happens, I am just pointing Fable is not an exception, it has happened with almost every other model release by all these companies over the last 2-3 years.

I don't get what you mean?

To me the biggest news is Jeff and Sanjay leaving Google... but then not really, since Google will be "an investor". I guess that's sorta their retirement plan? And is Discovery Loop actually part of Alphabet? So complicated.

Yes. Be locked in. It's better to go 100% and only pay the switch costs if you have to.

Developing abstractions to let you switch technologies has 2 costs: The actual development, and not fully utilizing a specific technology. Lots of people prefer pain in small doses because it can be rationalized as eventual payoff.

There are degrees of this decision, of course, but I would say most folks worry too much about this particular champagne problem.

Maybe LLMs can't, but another form of AI will. I hope nobody is interpreting this as "nothing will never be as good as us".

I see similar thinking in stories of how humanity got here. Religion has thousands of years adapting to this problem, every time we explain something, the goal post moves. Catholics today accept evolution (or least the church does), but it is the "jump" from monkeys to humans where God is the only explanation.

Just 5 years ago we didn't have a technology that knows more about everything than even most experts. We keep coming up with benchmark after benchmark and LLM/AI keeps destroying them. Now we've moved the benchmark to "the jump". Again, maybe it's LLMs or the way we currently do them that can't do this, but eventually something will.

I’ve used Monica HQ a lot. I am building a similar tool but With AI (tm) https://meetemilia.com/

Currently struggling with actually giving it the personality you see on the website, or if it should be more of a tool. I hate the idea of humans having AI friends, partners, relationships, etc…

Anyway, the “personal CRM” space is filled with sales focused tools. They all connect to LinkedIn. What I like about Monica HQ is that it doesn’t follow this model. You can use it and get reminders and in general read about your family and friends so you don’t forget their names and life story next time you meet them. I suck at remembering these things, so to me it’s useful.

Back in the day "what happens when the user types a url in the address bar and press enter" used to be an interview question, and I remember nobody has ever mentioned the hardware and keyboard keys and interrupts. This post does! Pretty awesome detailed view of a request lifecycle.

Let's say you grab a can of Coke in the grocery store, shelf sticker says 49c. When you pass on the cash register, it clearly shows $5k in the cashier's monitor, and the point of sales screen, so you're charged $5k.

Ooops, says the grocery store: Coca-cola raised the prices, not me.

In the US the rich already has more public power than the poor... from lobbying to donations to "speech". I guess making it official would save them from all this work and simplify things?

Your language is not even sarcasm at this point, but was really used by Google a few years ago https://www.wxii12.com/article/google-home-confuses-users-wi... - "we were just surfacing timely content for our users"

More likely they don’t care what the company does. Sell cars or muffins, it’s all the same thing you just tweak numbers in a spreadsheet.

To me the tools are newer, but fit people in a controlled context to sell clothing is as old as photography itself.

Related, Patrick H Willems did a long video about it and I recommend https://www.youtube.com/watch?v=hAtbFwzZp6Y

I've done a version of "world" for Sigil, a programming language I was kinda doing but stopped, also for agents. LLM generated article here https://inerte.github.io/sigil/articles/worlds-not-mocks/

But basically world is a bit more narrow, that moment where your code touches the outside world (logging, http, etc), you can swap that. It's sorta like DI but deliberately narrower, only the moments where code touches the outside world are swappable.. With DI in theory you can replace anything, which has its benefits, but at least personally I am not a big fan of mocks, except when they touch the outside world. So that's what's replaceable.

I honestly interpreted and agreed with the version "this saves money".

I learned in Brazil. Here in the California I asked my son's kindergarten teacher if she would teach cursive, and she said they don't teach calligraphy and I've never seen it described this way, but she's right.

Reporting on percentage of AI generated lines of code is very different from total lines of code. Yes I know both of them are missing what's the value delivered, but the later assumes the value is the number of lines, while the former assumes value is at least the same but delivered faster.