SoMomentary

I actually feel the opposite of what most people are saying here. I thought your writing style was great. It felt like you respected my time as a reader and got to the fucking point.

I thought the lack of fluff was refreshing!

Not at all! My company has 100s of clients and we track time in 6 minute increments. I feed in my browser history, terminal logs, session scripts, calendar, git commits, etc etc into it and voila it produces a highly accurate timesheet in no time flat.

Automating it has been way better for me than the alternative of breaking my flow whenever I'm switching tasks to chart my time, or logging all my hours for the week in one sitting. Different strokes for different folks I suppose.

Local privacy respecting inference can be worth it. I use a local model to log everything I do all week to automate my timesheet. I also have it do a bunch of other data tasks. I won't say that larger SOTA models wouldn't do these tasks better than a local model but PII is a concern and my employer wouldn't approve of me just setting tokens on fire everyday to do what I could do myself.

Having seen all the AI interactions that you can get through clickstream data I have no doubt that $GOVERNMENT_AGENCY can see much much more.

Awesome, thank you so much for that! I'll have to dig in and get this working for my work machine where I still have to use Chrome. I literally quit using Chrome for personal use over this but I guess it was premature.

Webpages run a lot better when I block all that extra shit from running!

I thought these stopped working altogether with the release of Chrome 142? I know you could override it for awhile there, but I've been lead to believe that option is gone.

This is part of what forced my hand and made Firefox my daily driver, at least for personal use.

Yes, it's been a way better deal to go for a subscription than pay as you go for me in the past. I had a month where I burnt through ~3.8b tokens which was somewhere in the ballpark of $8k worth of savings.

Now though I don't dare use spend tokens for basic note taking with Sonnet because I'm hitting the limit over a couple million tokens on the 20x plan, so they've really tightened the purse strings since November.

They must mean by creating a composite image with multiple in focus areas? Otherwise I agree, I can't see anyway that multiple exposures would help, at least from some light reading on Wikipedia - https://en.wikipedia.org/wiki/Multiple_exposure

> Quality of answers from quantized models is noticeable worse than using the full model.

This is the very reason I've heard I shouldn't use Alibaba!

I think some of this comes down to undeclared A/B testing. I've had the worst week of interactions I have ever had using Claude Code. The whole week whenever I have a session that isn't failing miserably I seem to get tapped for a session survey but on any that are out and out shitting the bed it never asks. It has felt a little surreal. I'd love to see a product wide stats graph for swearing, I would 100% believe that it is hitting an all time high but maybe I'm just a victim of a bad A/B round.

Not at all! My shop is having one of its best years ever. We've been switching to value based billing with our clients which has made them happier and us more profitable.

Using AI powered prototypes to sell clients on new features has gone really well for us. Many of our clients have presold themselves on adding AI features of some kind, which is nice because it generally means they will need support for these features going forwards.

Interesting, I'm apparently a bot for saying I don't know.

$7 a pop when other price watch tools are free? I'm not sure I'm understanding the value proposition here.

Has OpenAI banned it's use already? I hadn't seen that one come through yet.

Absolutely, but it occupies them later and only when needed. This is what I think they're driving at here.

Their latest update just introduced indexing for handwriting + text, so now you're able to search through all of your notes! This has been a huge QoL upgrade for me.

I think their point is that all of the content out there is turning in to AI Slop so it won't matter if search changes because the results themselves have already been changed.

They should also reject duplicates and probably rate limit uploads...

Did he have to leave for the same 130 day rule that made Musk leave?

I thought it had been bandied about that Deepseek had exfiltrated a bunch of data from OpenAI's models, which was then used to train theirs? Did this ultimately prove untrue? My apologies, I don't always keep up on the latest drama in the AI circles - so maybe that has been well proven wrong.

You don't consider copilots agent mode to be agentic? I've had some pretty great results with agent mode + mcp to have it check it's own work.

I'm always surprised by people sleeping on GitHub Copilot. Is this because people truly don't find any value in it?

Huh, today I learned my wife is not a woman. Who knew?

But for real, my wife is probably the most minimalist person I know. She lived out of a suitcase for years while traveling, and now between us, I'm the one with electronic knick-knacks while her tastes can only be described as spare.

Maybe instead of making sweeping generalizations about what "women" want, we could acknowledge that people of all genders have different preferences about possessions? Some people feel sentimental about objects, others prioritize mobility, and many fall somewhere in between.

Your moving cost estimate is helpful, but the gender stereotyping doesn't add anything to your point about the economics of moving versus replacing possessions.

I had this happen to a client and even though they had both the web and print licenses they were hit with a 50k suite because the font file was malformed somehow. I'm not sure how it shook out but I hope they didn't pay a god damn cent.

Pro tip:Those em dashes are always a red flag for LLM usage. Normal humans use - because it's actually on the keyboard (at least in English)