Телеграм канал «Anticodeguy»

AI Gets Dumber On Weekends
<written by a human being>

I swear, models degrade on weekends!

I see a clear correlation between the weekend kicking in and a noticeable drop in intelligence, even in flagship models.

Right now I use Opus 5.5 by default for everything, including orchestration, and I've got nothing to complain about. All it takes is stating the task and the model handles it properly: gathers context first, asks if something's missing, designs the solution and implements it.

But the same tasks I gave it this weekend, for some reason the model does way worse. Missing important context only comes out at final acceptance, decisions are questionable and suboptimal, and the implementation is buggy. And across different tasks, even simpler ones.

Saturday was still tolerable, but yesterday, in Sunday sessions, I literally stopped Opus 5.5 in every single one, asked what it's doing, changed direction, hinted at obvious solutions and so on.

On weekdays I don't see this at all. Usually it's enough to blindly trust the model and it does everything top class. Of course there are misses, but not on this scale and not as often as yesterday.

I bet it's about the heavy load on the models because of token-maxxing, when everyone tries to burn through the remaining limits and make it before the reset on Monday.

Do you feel it too, or is it just me?

Vibe-coding Smart Lights
<written by a human being>

Some people do whatever on weekends, and I'm vibe-coding for smart lamps!

By the way, I didn't know the wireless modules are built right into the bulbs themselves, and to make them work you just screw them into the socket! No extra wiring or add-ons. You just turn on the light and it works.

Through the mobile app you connect the bulb to WiFi, in my case (there are models that connect over Bluetooth), and just like that it's on the local network. In the official app you can change the bulb's color or even set up music sync. But that's not interesting to me.

A couple months ago I vibe-coded a desktop app for a USB desk lamp. And now I thought it'd be cool to sync it with the ceiling one!

Said and done: one session with Sol and we upgraded our app, which now controls both lamps. You can change colors and modes separately, or both at once. Now you can make a real ambient lighting for the room.

This bulb was experimental. But now I'm thinking about buying the same ones for my office too and screwing them in. You could sync them with, say, the keyboard backlight for full atmosphere!

IoT for all!

When Less Is More
<written by a human being>

Yesterday I rewatched RoboCop, which I last saw as a kid, and was pleasantly surprised by things the movie showed very carefully and literally predicted how modern AI systems behave.

For example, there's an episode where they loaded hundreds of different directives into the cyborg that he had to follow. And, predictably, something went wrong and RoboCop started doing all kinds of crazy stuff and reacting totally inadequately to what was happening around him.

Reminds you of anything? Same thing today: pile any AI agent with instructions, surround it with rules it has to follow, and the result of its work looks pretty depressing, and getting anything coherent out of such a system gets very hard.

That's why lately, when it comes to editing project disciplines, I prefer removing rules and guardrails rather than adding new ones or tweaking the old ones. And it leads to a noticeable jump in the quality of the agents' work.

This is exactly the case where less is more. And the latest models are already smart enough to handle most tasks even without strict rules and instructions, like it was some time ago.

Same way RoboCop worked way better and more adequately with just 4 basic directives in his software. Everything else can easily be left to the human brain inside the robotic body.

AI Shopping Assistant
<written by a human being>

Looks like I've finally found one more practical use for AI assistants: a shopping consultant in stores.

I used to spend long hours looking for products that fit on every parameter. Had to dig up reviews, check if they're real, match specs, compare brands and a bunch of other stuff that really ate a lot of time.

Now you can just voice-dump your picky requests into a chat with an assistant and it, right while you're standing in the store, picks what you need and even checks availability where you are right now. Especially helps me here in Thailand, where store staff often don't speak English, and talking through translators is still pretty janky.

Some things, of course, I'll still research going all in, because I find it interesting. Computer hardware, components, photo and video gear, audio and other stuff where I get a kick out of the studying itself.

But routine things, like a new set of bedding or a frying pan, I'm happy to hand off to an AI assistant.

By the way, just yesterday I noticed a banner in ChatGPT offering to buy ads from them. So it's started. AI is now a full-on ad platform. Which means the choice won't be objective anymore.

Curious to see how this will work and whether it'll be possible to talk an AI agent out of it, to convince it that this particular product is not what I need and that it's pushing it on me for its own profit.

The Long Game Of Money
<written by a human being>

My epic with building a home bookkeeping system, which has been dragging on since April this year, is smoothly coming to an end. Years of data history are taking their final shape: fewer and fewer gaps and mismatches, and of course it's all thanks to persistent LLMs that tirelessly keep cleaning it up.

When designing the new version of the system, I set a goal to have answers in front of my eyes to the questions about finances I care about. For example, how much money I've earned over my whole life, how much I've spent on clothes, how purchasing power changed, how much my life cost in different periods, and others.

And so, looking at these beautiful charts, it finally hits me how real concepts like compound effect are, and that investing, or more precisely growing capital through investments, is a game of time.

When you can't see money visually over a long stretch of time, it exists just as an abstract construct that on one hand hugely affects our lives and everything around, but on the other hand stays in the shadows, hidden from view, just like dark matter.

Anyway, after I saw these charts, I suddenly realized I'm not gonna delay opening a brokerage account any longer, so I went straight to do it. I don't know yet where exactly I'll invest my tiny, for now, capital, but that doesn't change the point.

By the way, for a long time I thought that as a Russian citizen I only had access to the Russian market, which, to put it mildly, isn't particularly attractive for that. But turns out that's not true. Interactive Brokers is one of the few companies that officially and fully supports opening brokerage accounts for citizens of my homeland, which I'll gladly use.

The first rule of investing: don't lose money. Remember it.

Fake It Till You Make It?
<written by a human being>

Just listened to the latest My First Million podcast, where the guys were sharing their takes on the documentary You Can See Everything, about Elizabeth Holmes, who's currently serving time in prison.

For those out of the loop, this girl founded Theranos, a company that blew up worldwide thanks to pompous marketing and huge investments and promised to revolutionize medicine. They made a device that could run tests on literally a drop of blood and detect all kinds of diseases, helping to stop them before they develop.

Turns out the whole thing was fake and the girl got sentenced to 10 years for misleading investors, breaking the law by using the Pfizer logo without approval, and other unpleasant stuff.

So the documentary lets you look at this story from another angle, since the director spent the last days before her imprisonment living in Elizabeth's house, talking to her, her family, her close ones and the people involved in this whole drama.

But I wanted to talk not so much about the film, which I haven't watched yet, though after all the rave reviews I really want to, but about an interesting observation from the world of venture business. There's this stubborn template, "fake it till you make it", which literally describes what Theranos was doing.

Only in their case there was a clear tilt toward "fake", or maybe just not enough time to get to the "make" side. Either way, this line is thin as a knife blade, and holding the right balance here is where the real mastery is.

For me, as someone far from the US, where venture rules the tech world, this approach is still more of a pretty fairy tale and a marketing story. Yet how many great businesses were built this way, when people sold something that didn't exist in reality yet, only in a presentation. And somehow we only hear about the failures when someone gets put behind bars...

Meeting Notes On Autopilot
<written by a human being>

Haven't done a practical AI-for-business thing in a while. Here you go, sign for it.

Automatic transcription of work meetings became one of the first areas LLMs entered by kicking the door in, and nobody even tried to stop them. The convenience is so obvious to everyone, and the relief from boring routine work so big, that even stenographer-secretaries (do they still exist?) didn't mind handing their bread over to soulless machines.

Zoom and its siblings immediately got plugins and add-ons that transcribe, summarize and even log tasks for call participants automatically. Which, of course, saves a ton of time, but the quality of the free solutions leaves a lot to be desired.

My team and I noticed right away how bad Zoom's native transcriber is, so as soon as we had the resources for it, we decided to swap it for something better. After a short market research it became clear that the leader in transcription right now is ElevenLabs models, which we plugged in for this task.

On top of that, we set up saving all transcripts, plus the recordings themselves, into an internal knowledge base. You can search it and find something to pin on the boss's careless talk, the one nobody pulled by the tongue three months ago.

Simplified, the pipeline looks like this. When a call starts, recording starts automatically. A worker periodically checks the Zoom API for new recordings, and when it finds one, it triggers the following actions. The audio track is extracted from the video, saved to the archive and sent to ElevenLabs for transcription. The video itself is saved to YouTube. The resulting transcript together with the video forms a new page in the knowledge base, dated with the meeting time. After all that, the video and audio get deleted from the Zoom cloud, so they don't take up paid space there.