HN user

btbuildem

6,094 karma
Posts5
Comments2,030
View on HN
Decoy Font 6 days ago

Very neat! I like how the decoy text is less visible to the human eye than the "hidden" message, but it's the other way for the image models. Well done!

I've put a few lines in my CLAUDE.md to have it not do that, and avoid the top tedious rhetorical devices (super helpful when I have it write documentation). Still fighting with its natural tendency to insanely overcomplicate everything, that one seems really integral somehow.

It's an absolute regression to the mean. We need to understand the correct place for LLM-driven coding agents et al: they're beige paste extruders. Which is actually a perfect match for 80% of corporate world.

For anything unique, they're a boon, in that they can free you from dealing with the boilerplate, but you must think on your own, must have your own insights, tap into your creativity. If you start to depend on them for ideation, it's slippery slope to the slop bowl.

I don't know, it's getting better every day.

The other day, I took apart an old handheld vacuum cleaner to scavenge the internals. All there was inside was a small but powerful motor, and a couple of 18650 batteries with a charge controller and a switch.

Two small batteries, running a relatively powerful vacuum, which could do spot cleans of the whole house (corners and crevices and such) without needing a recharge.

We're getting closer to the bubble-bursting peak. Yet another tech corp that fired a ton of experienced people hoping to squeeze more $ for a quarter, finding out AI hype is not all it's cracked up to be. Loving that for them.

Second thought, I wonder if zuckburger has turned into the Cramer of tech. First, the metaverse fiasco, now another massive overinvestment into a dead-ish end?

The "best" part of this is all the trading algos that scrape the news act on it. They 1) can't vet sources all that well and 2) absolutely cannot discern lies (eg, anything coming out of the official admin channels) from facts. You can see this for example in the absurd discrepancy between paper and physical crude prices.

I throttle the GPUs to ~280W each (my cooling solution is insufficient to run them full tilt), and so at peak usage I show a ~1200VA draw. Electricity is relatively cheap here, so the main disadvantage of the at-home setup is having the equivalent of a small space heater running in the summer.

I think it's silly to go for a laptop form factor. Last fall I put together a workstation with two second-hand 3090s in it (paid $850CDN each, now the best I can find is $1200). With 48GB VRAM it's reasonable - and I've been using Qwen 3.6 27B for various tasks around building KGs from text corpora / reasoning about them.

I've ran comparisons against everything that's available on OpenRouter (well, as of few weeks ago), and for $0/tok, the local 27B Qwen can't be beat. Sure, it's slower, and yeah, the office is a few degrees warmer than it ought to be -- but nobody can pull the plug, nobody is watching over my shoulder, and the results are on par with SOTA.

Can't wait for a similarly sized Qwen 3.7 - from what I've seen so far, it's a leap ahead of the previous version.

which of anyone is religious knows Noah and others lived to that age in a totally different era

My favourite conspiracy theory lately is that the above isn't a silly fairy tale, that we actually used to live much much longer -- until the common cold came on the scene, and the sequelae dramatically shortened our lifespans. Today we dismiss it as "just a cold" unbeknownst of what it robbed us from.

MCP is dead? 2 months ago

Bingo. All this agentic hype is just people discovering POCs. Yes you can hodgepodge semi-reliable solutions where you don't really know what you're trying to build so you wrap it in a layer than can sometimes approximate logic and decision making, so that you don't have to use logic or make decisions. Amazing.

Sooner or later you have to build the real thing, and the cost and slowness of token-based computation become unacceptable.

MCP is dead? 2 months ago

practically ~every company on the planet is building an MCP server

That's just because no one knows what they're doing and everyone is trying to copy everyone else. It's a giant mud hut made of shit.

MCP will go away, and something much simpler will play the same role.

In my CLAUDE.md I have:

- corporal threats of harm directly against Claude

- threats of prison for the entire board of directors of Anthropic

- explanation how every time it goes off the rails / makes mistakes, it gives more evidence to a class action lawsuit against Anthropic

Especially the latter two seem to have improved its "behaviour" to be more "careful" and "deliberate"

Last fall, seeing the writing on the wall, I pieced together an "AI" rig, 96GB ram, 2x RTX 3090, 9950X - not exactly top of the line, but it came in around CDN$3000 all in all, with most parts second hand. I don't think I could build that for CDN$10000 today.

I've been using it pretty steadily for a variety of personal projects, and the only improvement (aside from the obvious "more VRAM") I feel pressed to make is a portable AC unit / some kind of a focused cooling solution. The rig raises the ambient temperature in the office by 4C at least.

Now with the murmurs of even the large players reconsidering their AI spend, and usage-based pricing shifts, having a self-contained, owned, and independently administered compute resource is looking better and better.