joshstrange

I say please and thank you, though never as a last/final message (“Thank you, that’s great! Now let’s move on to…”), and I do apologize when I’ve said something wrong or told it to do something and then changed my mind.

However I also let my frustration through, “Why the ** would you do XYZ?”, which normally comes due to the semi-stream-of-consciousness STT flow (both for pleasantries and frustration). I don’t have infinite patience for the machine.

Gemini in Google Docs products is embarrassingly bad. Like Microsoft Copilot-levels of "shove AI into everything even if it's dumber or more limited than than GPT-3".

Every time I'm in google docs and want to do something with AI I try Gemini only to get frustrated that basic things are completely beyond its ability. I'm better off opening Claude's extension to do the work.

I avoid gemini because it's always been trash IMHO but I am forced to use a version of it via Siri now and I don't know if it's Apple's AI incompetence (of which there is plenty) or Google's trash model that causes Siri to still be shit. The fact I don't hear Android users raving (or taking at all) about gemini on their phones makes me think the model is just bad.

Years ago when I went to Planet Fitness I didn't like their app and it was slow to load the barcode I needed to scan to get in. Thankfully that barcode didn't rotate so I was able to just make my own Apple Pass and set it up to be geo-fenced on the gym so as I walked up it would pop up as a notification I could tap to open my code.

I love being able to do things like this and rip out the crap being forced down our throats.

It's the same reason I won't buy something through my Alexa. I want to see the price, I want to make sure it's not 50% smaller than the last time I bought it, and I want to compare. The same is true for food.

I work for a POS company and was asked about the ACP (Agentic Commerce Protocol) and I told my boss we should skip it for now because of this exact reason. Not anti-AI at all, in fact I've built tools for our clients to manage their menus via LLM ("Add Pumpkin Spice as a seasonal flavor to all my coffee drinks", "Mark lettuce as out of stock", etc) but ordering food does not feel like a good fit for agents as things currently stand.

1. Claude Ultra for personal, Claude Max for work, Codex $100/mo

2. OpenRouter, DeepSeek, Luna, and testing out models here and there

3. Claude Code and Codex for the respective subscriptions. Played with OpenCode and Pi some as well

4. I've tried a number of these tools and settled on my own tool (not released) to oversee my agents

5. Played with OpenClaw and Hermes in the past, cool ideas but execution fell flat. I currently use Dots and Duet for little things (mostly monitoring communications). Dots is much better than Duet today but I hope Duet gets better.

This is off-topic and I'm no fan of xAI or any company circumventing rules to allow them to use dirty energy sources.

That said.

> Normally, that would be enough to keep around 15,000 homes up and running.

Am I the only one who finds this kind of comparison meaningless? Like it's supposed invoke a feeling of "15K homes worth of power! How absurd that a data center use that much!" but that kind of how all centralized things work. That datacenter does work for, one would assume, way more than just 15K homes and if those homes wanted the same "work" output they'd use the same, or most likely, more energy to accomplish the same thing.

In many/most cases they aren't using electricity just to use it, they are using it because people are paying them for the output. With economies of scale I would guess a datacenter is many times more efficient than if we were all running local models at home.

Again, not an argument for data centers as much as I find this comparison always pointless.

New review submission is broken, give generic error. I never miss an opportunity to complain about the dumpster fire that is ClickUp but I was unable to submit my 1-star review.

> Each chat lasted an average of 11’ 4

What does this mean?

You never like to see layoffs but this makes sense to me. Even as someone who could code up his own websites (and has many times), I've considered Squarespace in the past for something like a marketing website. But today, I wouldn't even consider spending the money on that unless I was doing ecommerce through my Squarespace site.

Straight informational websites with rare/few edits can much better be handled with LLM-coded websites deployed to something like Cloudflare or just static hosting.

Super excited to see more products in this area. I talk to my computer the majority of the time now, and I can do that because I work from home. If I were on public transportation or in an office, it would be much more difficult. It's been interesting to watch the Overton window, if you will, shift for people talking _to_ their phones. Now, the majority of my family will use voice to text on their phone whereas I remember just a few years ago, if not even just a year ago, it was made fun of.

OpenDisplay's calculator is what I'm basing it off: https://opendisplay.org/firmware/battery/index.html

My first EN05 board had a problem with the battery and I just got the replacement a few days ago and haven't had time set it up or do long-term tests. I also was blown away by the WiFi vs BTLE power usage. I love ESP32 but for battery powered I'm looking closer at BTLE. I actually have 3 ESP32's around the house to act as BTLE proxies for Home Assistant which I can use with OpenDisplay as well.

And yes, it's a great form factor, it looks great, and just makes me smile when I walk by one. Once I can solve the "more updates, less recharging" I plan to frame a number of these to hang on the wall.

I'm not saying that OpenRouter isn't worth looking at but it, obviously, shows a much smaller slice of LLM market and it's going to, obviously, trend towards open models since those are the only model where there is any competition for inference pricing. No one is undercutting Luna because they can't really.

OpenRouter could so 90/10 split and it still wouldn't mean open models are beating (in usage) closed models.

I have a couple of these and they are great. I'm transitioning to BTLE e-ink screens (hand-assembled, I wish there were nice off-the-shelf versions) because of their much lower power draw.

Currently I have a handful of the all-in-on seeed studio reTerminal E1001's that rotate book quotes I've highlighted on my kindle (jailbroken, KOReader+BookOrbit) once a day so they can last months on a battery charge. But with BTLE you can go years on a single charge, update more often, and push to the device to force an update (all things not possible when deep-sleeping wifi for 23.99 hours out of the day).

e-ink displays are so nice and once I get the BTLE+OpenDisplay setup perfected I'll probably grab ~10 more boards/displays for other places around the house.

If you are on iOS, Heeler is a great Herdr client.

I'm finishing up my Voyager watch right now and was already considering TNG next, this seals the deal. TNG is such a cornerstone to my youth and growing up. Everyday after school I'd come home and watch TNG reruns (Tivo). Call it whatever you will but Star Trek and the ethos in it will always hold a very special place in my heart, I've always held it up as the model to aim for. He will be missed.

> Quite a few of them spoke no English, so yes, they'd just present their phone screen. I didn't take it as rude.

I want to be clear, the ability to speak English is not what I took issue with. That doesn't bother me and I'm fine with just showing the phone screen, no conversation. The issue I had was cutting the line and essentially demanding they be helped immediately. Wait in line like everyone else. This is a small food stall in a food hall with often just 1 person working the front. If they are actively helping another customer and have a line, I find it unacceptable to think you can cut to the front and immediately demand attention. What message does that send to the customers in line? "You're less important than delivery orders", and I can tell you that isn't the case due to the large chunk that DD takes.

My family member has even considered shutting down DD orders temporarily if/when the drivers act this way and publishing on social media about it. According to them, the loss in sales (and overall profit, which is minor on DD orders) wouldn't matter compared to the publicity/engagement (I don't know, that's not my world).

> DoorDash to Acquire Instacart to Help Local Stores Win

> to Help Local Stores Win

Any local store will tell you DD is a necessary evil they put up with but strongly dislike overall. From the % of sales they take to the incredibly rude delivery drivers, DD is not well liked.

On multiple occasions a family member's employees (or they, themselves) have had a DD delivery driver cut to the front of the line, interrupt the cashier, and shove their phone in their face. No words, no anything, just "here is the code/screen/whatever I need to show you to pick up the order". DD doesn't let stores rate delivery drivers so there isn't any recourse.

Does anyone use/like touch on their windows (linux?) laptops? I've never really been drawn to wanting to do that. My mouse is far more accurate and doesn't block my view. But maybe it's just because I don't have it and I would find tons of uses for it. Also, I don't love the idea of putting fingerprints all over my screen. I guess I can understand for testing iOS/iPad apps but past that I just don't see myself wanting to use that.

Then again, it really doesn't matter to me at all what the screen looks like or what features it has, I use my MBP docked 99% of the time with the screen closed, to the point that my next computer will almost certainly be a Mac Studio and I'll just use my MBP on the rare occasions I need it on the go.

> Oh come now, this rolled release is now the standard for frontier models.

Sort of? Yes, OpenAI has been bad about slow rolling but Anthropic's last few models have been available essentially at the same time as they announced it. In most cases I updated Claude Code and was using the new model right away.

Compare that to OpenAI who sometimes says "Available to all Plus/Pro/etc plans" without saying anything about "rolling out" and then it's a crap-shoot on when access will actually roll out. That said, they have gotten better, it used to be 1-3 weeks sometimes to get a new model/feature they announced was available for your plan.

And then there is Google... Who loves to talk about models like this and then give no timeline for release. Even when they do release the models it's miserable to find out how to even use it. Is it in the API? Which API? Google Cloud/Vertex/Gemini Cloud? Whatever it's called this week? Coding plan?

No, what Google does (or rather fails to do) in its rollouts does not compare to OpenAI/Anthropic.

As for the AA page, it's just embarrassing. Any smaller company doing that would get roasted, Google doesn't get a pass, learn how to coordinate or wait for something to actually be true/live before posting.

Ha, I didn't see your comment before I posted mine [0], there were still only 2-3 comments when I opened the thread but yeah. I completely agree. I don't think they are lying, but I still don't love the "it's the best, but you can't try it".

[0] https://news.ycombinator.com/item?id=50277040

> Carbon ranks #1 on the recently updated v5.0 of Artificial Analysis Intelligence Index at 59.

Clicks link

Carbon isn't anywhere on the page and you can't toggle it on either. I'm sure it's just timing and it will be there soon but still just look amateur, which is about how I feel about Google and AI overall. I know the models have improved but I still have a bad taste in my mouth from testing Gemini in the past and I still feel that Google has an overly complicated "how to use our models" that changes way too often. That coupled with "you could lose access to your google account if we don't like what you do with Gemini" means I have little desire to test it out.

On top of all of that I'm completely over announcing a new model that we can't actually play with or try out. I don't think Google is lying about how well their model scored exactly but it still has big "my girlfriend goes to another school, you don't know her"-energy.

> "And offloading that labor, regardless of whether it's taxing or not, is undercutting my ability to be a moral actor."

The objection in the article is specifically about offloading thinking to technology, which is something we've been doing for decades, or depending on your definition, since we first started using tools.

If offloading cognitive labor is the core problem, then what makes AI fundamentally different from the countless other technological advances that have allowed us to offload cognitive labor?

The car he drives to work, the house he heats, the electricity he consumes daily, all that labor is fine to offload, but AI is the line in the sand?

Where is the line? "AI" is completely arbitrary, might as well say a calculator is immoral because it offloads thinking. That my main issue with these people is that they think AI/LLMs are different than everything that came before them, yes they are more capable but all of computing has involved "offloading" effort/thought to computers. `

There’s a good chance I’m wrong about this, but I thought they lowered the price to account for not including Apple Care? So you’re correct, it’s no longer included, but the price per month and total cost of ownership is the same?

We’re still experimenting. Automatically fixing obvious issues raised by the agent (at another agent’s discretion) or presenting a list of the feedback items with fix/refute suggestions are things we’ve toyed with.

Personally I have an agent review the feedback and break down each item so it’s easier to review (helps remove some of the jargon/short-hand that agents use sometimes). Then I decide what to have an agent address and what to push back on. Like I said, I’m working on finding a way to automate part of that but haven’t settled on one I like yet.

>> Writing code by hand is dead.

> Is it still a controversy nowadays?

Reading HN would leave one with the conclusion that yes, it is still very controversial. We still have plenty of people who swear they will never use AI, who say it's trash, it only produces slop, that a reckoning is coming, etc.

See this post from today: https://news.ycombinator.com/item?id=50256738

My understanding is that while it's a loan->lease change, the TCO is the same under both plans. I might agree that the Klarna version feel scummier but it doesn't change the financials for me and it's still effectively a 0% interest loan. I set aside the full cost of the phone in my budgeting app on day 1 and then draw down from that category over the span of the loan/lease so it's effectively like I'm buying it but I get to park the money in a HYSA.

My go-to is adding unit tests or similar to existing projects that didn't have good coverage when originally written. It's effectively completely safe to do (only adding tests, not touching application code) and is nice to "pin" our existing functionality.

While I don't doubt many people are doing that, using the iPhone/Apple Upgrade Program does not immediately equate to that being the case. I always use the Upgrade program but I could buy the phone outright if I wanted but why would I? It's essentially a 0% interest loan if I buy the phone out at the end. Sure if you turn the phone in after a year (or two) you are leaving money on the table (vs selling it or repurposing it) but the Upgrade programs aren't only used by people spending outside their means.