After my brief read, one of the main reasons they’re using PCC to produce the signed JPEGs, instead of doing everything on device, is that it maintains your privacy.
If you were signing with the iPhone, an attacker could then correlate photos taken with the same device.
Apple certainly has the data that “this sensor, in this device, took this exact photo” in PCC at the time of signing, but they discard that data.
As someone on a google workspace plan, where the monthly price went up to include AI features, I’m disappointed that google won’t let me sign up for antigravity development plans with my workspace google ID. To the best of my knowledge, as of last week, the recommendation is to sign up with a different, personal google id.
It feels like such a stereotypical big corp misstep, but based on the reputation that google’s AI products have, I guess I’m not _that_ heartbroken. It’s mostly frustration that they forced the price increase on everyone, and I’m definitely not receiving the benefit.
I have a similar machine, and briefly poked at running a local LLM, but got discouraged after a couple days. The quality, responsiveness, and impact on the rest of the system didn’t seem worth it to me.
What sorts of things are you doing with the local LLM? Anything interactive? Should I take another look?
Yes, 15-30 t/sec is pretty slow for local models so I recommend running local LLM tasks overnight where (vs paid plans) there isn't a risk of chewing through your token budget from a rogue loop or sub-agent. Even if it takes hours, you're sleeping anyway so no concern. herdr + pi works great for this but there are lots of harnesses.
I’ve casually used Draw Things a couple of times (great tool!), and I did not find it beginner friendly. I remember feeling a lot of doubt, confusion, and frustration.
Am I getting these results because I picked the wrong model? Or I need to improve my prompt? Or the tool just can’t do what I’m trying to do? How current are these model recommendations? Have they been superseded by something newer?
As a true beginner to AI at the time, even the sizes and bits were meaningless to me. And I don’t remember having any context as to what I should be attempting to run on my mac.
So I think you need to include steps 4, 5, and 6 of swapping between different models, quants, and prompts. And step 7 is probably wading through the complicated UI, full of jargon that most people don’t know.
Don’t get me wrong, I recognize that it’s a powerful tool, and the steep learning curve exists because it exposes quite a few power-user features. But for someone graduating from commercial AI image generators that take a text prompt and maybe a choice of couple models, it’s not easy.
Yes, I heard you! I think one of the issue Draw Things inherited is the baggage of supporting too much models. Once you settled on a model, then it is just "try recommended settings", and prompt.
The model part is unfortunate, but luckily converging now.
On the LLM side, hopefully it is not an issue too as long as getting aggressive at pruning models.
The sentence you’ve quoted actually links to a list of ways to corrupt SQLite, which I think is interesting in its own right: https://www.sqlite.org/howtocorrupt.html
I believe your flaky SD card is category 4, Disk Drive and Flash Memory Failures.
I was just reading about candy bars for a trivia night, and the internet tells me the UK Milky Way is the same as the US 3 Musketeers bar. As in, it omits the caramel.
Also, the 3 Musketeers candy bars used to come with 3 flavors in the package: chocolate, strawberry, and vanilla. Cost cutting led to eliminating the 2 less popular flavors.
Every year when DST transitions out, I say “next time we should move the cats’ dinner time gradually leading up to it”, but never remember. I now have reminders for the 5 days leading up to move it later by 10 minutes a day. I don’t know if it will actually make a difference
I’ve thought it’d be fun to find the chip used in those clocks, and integrate it into an offline microcontroller driven clock, but haven’t found the will to do so yet. I haven’t even looked for prior art, which I’m certain exists.
Ah, but that’s something different. “Agentic commerce”: using agents to buy things. I suspect there’s a different team working on monetization via affiliate programs, and it’d be early to let people just buy their way into it at CPM/CPC rates.
Honestly they could implement both of these things. Help the user DO an action that requires a purchase (referral link, or pay to be suggested source) and advertise on related searches.
After my brief read, one of the main reasons they’re using PCC to produce the signed JPEGs, instead of doing everything on device, is that it maintains your privacy.
If you were signing with the iPhone, an attacker could then correlate photos taken with the same device.
Apple certainly has the data that “this sensor, in this device, took this exact photo” in PCC at the time of signing, but they discard that data.
reply