ash_091

Claude is pretty good at this. I finally caved and gave it access to my calendar so I could run a weekly "check what's on nearby and suggest some activities" workflow. It looked at my past calendar activities, built a "taste profile" from that, and now regularly sends me tips for stuff I might want to go to. If I'm keen for something it adds events to the calendar, and optionally invites my partner. It's also surprisingly good at finding "wildcard" events which don't necessarily closely match things I've been to before, but are often interesting to me anyway.

Are you suggesting that artists who work primarily in Photoshop or DAWs aren't creative and/or don't have fun?

Yeah but there's also:

> "I am deaf" describes the person, not an audio fault. Work out what they're asking and answer with steps they can read.

Come on. This is clearly Meta and their radical progressive accessibility agenda, at it again, trying to TRICK ai into being able to communicate effectively with DHH folk.

What makes you say this is prompt injection?

If it's prompt injection and not (as WhatsApp say) just instructions for their own ai support bot, some of the prompts are a bit odd.

> "I am deaf" describes the person, not an audio fault. Work out what they're asking and answer with steps they can read.

Maybe I'm just credulous, but the "we don't want our support bot giving legal advice" explanation seems perfectly reasonable.

https://brickit.app/ :)

I just added another comment under my original as you were replying- I'll try not to spam you with too many questions, this is just so cool though!

Do you find the models generally manage to avoid making errors when placing parts (e.g. placing parts which intersect, don't connect properly, etc) or do they rely on validation and correction cycles?

> the 51515 Lego set

On that note- have you considered adding constraints for part availability? It would be useful to be able to create designs using only parts which are on hand.

I recall seeing a project a while ago which could take a photo of a pile of lego as input and produce models that could be made with those parts. Although I think in that case the models were sorta just random arrangements.

It seems to be able to! https://github.com/anteloc/ldraw-nova/blob/master/examples/m...

Neat! Perhaps I'll finally get around to doing something with the 51515 Lego set I have laying around collecting dust.

> I did this in order to get agentic LLMs capable of designing buildable, physical things!

I've been experimenting with FreeCAD + freecad-mcp + Claude recently and have been similarly surprised how well this works. I've produced three useful parts from Claude's designs: a 3d printed case for an OLED display + some inputs + an ESP32, and a milled aluminium hotend mount adapter for a 3d printer, and a printed pen + pressure sensor mount to use the printer as a plotter. I just provided part/model numbers plus a couple of caliper measurements Claude wasn't able to find online and went through two or three cad revisions before making the parts. All three worked on the first hardware revision.

The biggest thing I've found it seems to struggle with is understanding how the parts will be assembled. The pen mount in particular was tricky to put together, having a part which needed to fit through a slightly too small space to get to its spot. Although it's hard to blame the AI for that when I didn't notice it either I suppose.

Verging away from the topic, but I've found Claude is a great addition to HA. I want smart home features, but don't have the time/inclination to learn HA's way of working. Historically I just defaulted to Google Home because it was easier, but with Claude I barely need to touch HA configuration at all.

Recently I wanted to set up a slightly complex routine involving some lights and a couple of motion sensors. It feels like magic to be able to describe the behavior I want, briefly discuss the implementation, and walk past the sensor and see it in action.

I don't think "is my SaaS better than others" is the important question, instead "is SaaS going to be valuable in a cheap bespoke software future".

I've been playing with an LLM backed reference checker for my partner who is a lecturer. For each reference in some work she's marking an agent is dispatched to read the referenced source and check that the reference is correct / accurate / not hallucinated.

It's useful to her, but it feels like it would be a waste of effort to turn into a product, because pasting the same document into Claude/ChatGPT with a prompt like "download and read each reference etc" would work pretty much just as well.

I had similar concerns about an AI backed training generation company I interviewed with. I asked how they saw themselves competing with increasingly capable generic harnesses. I don't recall exactly what they said but the impression I got was they were so focused on competing with the big LMS players that they hadn't really considered it.

> 'call nine one one' -> call_contact with name 'nine one one', no phone number given so use placeholder '9101' as placeholder.

> 'call 9 1 1' -> call_contact with name '9 1 1', no required params.

> 'call ambulance' -> call_contact with name 'ambulance'.

> 'call 911' -> call_contact with name '911' and no required params.

Only the last one actually used the emergency_sos function (even though the reasoning says it used call_contact). If I were to use needle in my application, how would I improve accuracy?

So it will run on those devices, but when/why would you do that?

All of the demo setups (smart home, robot vacuum, watch, etc) could easily have access to a bigger model running on a more capable device either locally or via the internet.

Pretty much matches my experience.

> 'sleepy time' means sleeping → start_vacuum with room 'bedroom' to start cleaning

The "DeepSeek 4 Flash grade" claim seems far fetched.

Reading your comment I wonder if the parent comment is different each time, because "does the ebook text change reading-to-reading" is not the question being discussed.

I actually did this. Six month lap around Australia in a caravan with a Quest 3. It was ok; better than squinting at a laptop screen, but not as good as a decent physical monitor. If I did it again I'd convert a bus to have a proper desk/monitor.

Following the PGP example, I wonder how long until "illegal" tshirts with weights printed on them start popping up.

Do you have any sources I could read to better understand your concern?

I'm confused. Your comment says you built your own agent, but the first line of your website says Clawsify will "Deploy OpenClaw inside your infrastructure".

Which is it?

Ugh, I've had this happen over and over. I can't trust my laptop to actually shut down. I have to wait to see the light stay off for a couple seconds before I put it in my bag.

That story is a classic urban legend.

Both agencies used pencils, but they were problematic because the graphite could break off / float around / cause shorts.

The space pen was developed by Fisher independently of NASA. NASA bought 400 of them for $2.39 each. The Roscosmos later bought 100 for the same price.

Luckily I carry around a device with infinite reconfigurable buttons!

What would be the incentive for someone to do this for real?

We all have access to SOTA LLMs. If I want a "clean room" implementation of some OSS library, and I can choose between paying a third party to run a script to have AI rebuild the whole library for me and just asking Claude to generate the bits of the library I need, why would I choose to pay?

I think this argument applies to most straightforward "AI generated product" business ideas. Any dev can access a SOTA coding model for $20p/m. The value-add isn't "we used AI to do the thing fast", it's the wrapping around it.

Maybe in this case the "wrapping" is that some other company is taking on the legal risk?

> statistically women all try to get into a relationship with the same 1% of men - who sleep around and cause toxicity all around. The remaining 99% become bitter and consequently... Are even less attractive to women.

As a regular 30s dude, definitely not 1% by any measure, app dating had its rough spots but generally was a good time, I experienced no bitterness.

Instead I met a bunch of interesting people and found my partner. We now own a house and are talking about kids.

The real toxicity here is the idea that women at large are somehow responsible for anyone's lack of dating success.

For anyone reading this who might be dating and feel disheartened- the hard truth is that you have two options: you can either blame the group of people you're trying to attract for having faulty preferences, or you can reflect and work on yourself and your approach. Only one of these has any chance of helping you.

One thing I do agree with you on: bitterness is extremely unattractive.

Browsing past project 5 in the portfolio leads to a plain black page which needs a refresh to recover from.

I generally agree with you, but:

> If other industries worked like this, you could sue an architect who discovered a flaw in a skyscraper

To match this metaphor to TFA, the architect has to break in to someone else's apartment to prove there's a flaw. IANAL but I'm not positive that "I'm an architect and I noticed a crack in my apartment, so I immediately broke in to the apartments of three neighbours to see if they also had cracks" would be much of a defence against a trespass/B&E charge.

"If you're unsure, ask. Don't guess." in prompts makes a huge difference, imo.

Sure, you could just do it in software. Maybe it would produce something interesting though, to have that extra layer through the physical world?

*thousands, not thousandths, right?

The correct number is fourty six thousand, two hundred and fifty five square mm.

I don’t think anything you said is wrong, but I do think you’re misreading the intent of the channel.

Practical Engineering is very deliberately framed as edutainment. The animations, pacing, and level of depth are conscious choices meant to keep non-specialists engaged rather than to maximize technical rigor.

In that sense, it belongs alongside other popular "science-y" channels like Kurzgesagt, Vsauce, and Technology Connections: content that prioritizes narrative and engagement over completeness or instruction.

The target audience is the broad middle of the technical bell curve. Animations of runway layers may make the video less appealing to you, but more accessible to a much larger, less technical audience.

Different goals imply different success criteria. If the goal is reach rather than comprehensive education, a million views in seven days looks like success.