captainregex

When they started the laptop program in my junior high school back in the early 2000s we’d communicate via broadcasted network name. not just the nerds! Just like the OpenAI agents! Message dead drops and all

I am skeptical. Lived experience is what matters and I don’t have anyone in my life (Devin shop) saying good things about SWE other than it’s free. Hope I’m wrong and it’s not so bad this time

my personal experience with swe has been…suboptimal. I am not sure how much I buy these benchmarks and it has a very “just blurt it out even if it’s probably not right” style but hey it’s free.

It’s a partial driver, perhaps even meaningful in some way, but this is hardly an A/B test. Suffice to say lack of CarPlay is costing them in some way but model refreshes, steep price discounts, and other economical considerations are going to win out. Sure, 79% of some sample of car buyers said they wouldn’t buy a car without carplay but putting carplay in an otherwise crappy car isn’t going to magically make people buy that instead. There’s a lot of reasons Chevy is struggling. Blowing their own foot off with this decision can’t have been good for business but it’s certainly been hilarious for the quotes their execs have had to say in public with straight faces so they don’t get whacked for not following the party line. At some point I’m sure there will be a reorg where the opposite will become true.

I enjoy all the fun of these new models as much as the next guy but I truly don’t see a circumstance in the near future where my $200 a month with the frontier labs doesn’t get me more than enough consumption of what I need. Local models, chinese models, etc are all very fun weekend projects to tinker with but until something changes (entirely possible!) with how much you get with one of the subscriptions I just don’t see why I would move. What am I missing? Is it simply that a subscription is no good for production use cases? I kinda feel the same way with choice of coding harness, openrouter, etc. why would I use anything other than frontier if I don’t have to pay any more pretty much no matter how much I use? pls tell me if I am holding this wrong haha

what trade off would one need to clear to justify the hardware and the work to get this running locally as part of a broader system? It’s a lot of work setting up and maintaining a production harness/system on a local device. I don’t personally repeatedly generate images at a scale where using a lab’s app somehow burns all my tokens. I like the ideas of local ai but I don’t see widespread adoption of it happening in commercial or customer situations anytime soon no matter how little/good enough they get. Even Uber- token burn whiplash but I doubt their answer will be “run some of it local”. IT nightmare, I’d imagine.

wow, this blows on so many levels.

anyone remember the whole “delete uber” thing from 2017ish? good times

I’m super envious. I can’t seem to do anything without a half a million tokens. I had to create a slash command that I run at the start of every session so the darn thing actually reads its own memory- whatever default is just doesn’t seem to do it. It’ll do things like start to spin up scripts it’s already written and stored in the code base unless I start every conversation with instructions to go read persistence and memory files. I also seem to have to actively remind it to go update those things at various parts of the conversation even though it has instructions to self update. All these things add up to a ton of work every session.

I think i’m doing it wrong

Sorry, the point? isn’t the point of art pretty much what a person wants it to be?

I have really struggled to get nano banana to follow size/proportion ratios for sprite art. any tips? I fed in a bunch of examples first and tried to write a really strict prompt. I wonder if any of the sw being discussed here can be programmatically controlled by claude code or similar to do sprite work

entirely possible I’m just really bad at this stuff but I can’t get browser agents to do simple report pulls without running into a captcha or a dropdown menu that breaks its brain. hopefully this is the one!

this is a disgusting amount of money for this

the third party ones seem to be suffering in similar ways in my short use

I intended to tie experience where it says short use

I intended to tour type where it says tie

I intended to type type where it says your

I intended to type tour where it says your

jesus…it might be time to consider android

oh dear god, tears of joy…they told me I was crazy. this is so validating

I had to threaten to sue them by opting out of their time triggered arbitration clause to get them to give me the deposit back on a car they couldn’t/wouldn't deliver. Carvana sucks.

This is such a self own.

I can't with them anymore. Pick a lane

How much of a hit would you take on quality if you moved the processing local? have you experimented with it? don’t think llamaindex has local sadly

this is nuts! beans? whatever, it’s super cool!

ahhh yes the noted privacy respect of…checks notes…Intuit

I should add that sometimes LM Studio just feels better for the use case, same model same purpose seemingly different output usually when involving RAG, but Anything is definitely a very intuitive visual experience

AnythingLLM also good for that GUI experience!

It’s crazy you have to go like four comments deep and into the sub convo before you find mention of windows on arm- apple silicon is just so dominant in the zeitgeist for people who think about this stuff

if anyone else is curious, beyond all the political football stuff happening with the bureau of labor stats, Odd Lots did a good episode recently on the challenges with monthly jobs reports

Not that he’s necessarily wrong but got a chuckle out of the wide ranges of token estimates for various tasks being attributed to “a variety of sources”.

anyone else get excited about nano and then sad when you realized it’s not actually a small model

I desperately wanted Qwen vl to work but it just unleashes rambling hallucinations off basic screencaps. going to try nanonet!

What are you aiming to do with these models that isn’t chat/text manipulation?

one of my day to day responsibilities involves using a portal tied to MSFT dynamics on the back end and it is the laggiest and most terrible experience ever. we used to have java apps that ran locally and then moved to this in the name of cloud migration and it feels like it was designed by someone whose product knowledge was limited to the first 2/5 lessons in a free Coursera (RIP) module