Please link me to the python3 gtk2 library so that I can migrate all my python2 gtk2 software to python3 without rewriting the entire UI. Thanks in advance!
You can cultivate passion, in my experience. It's easy-ish to think back to childhood and say: "oh, my love of drawing started when I was a child." But that was 20 years ago. The love of drawing has had 20 years to develop. Now, if I play the parent role to myself and start a new music hobby, imagine what I'll say in 20 years. I'll probably say: "I'm pretty passionate about music, my love for it has been growing over the last 20 years."
You are taking the statement of "toxic individualism" to mean "all individualism is toxic" rather than "certain parts of individualism can become toxic if not followed."
It is possible to say "some things could be done better" without meaning "throw it all away."
Yeah I can understand that, and sure this is part of it, just not all of it. There is also broader societal issues (ie. inequality), personal questions around meaning and purpose, and a sprinkling of existential (but not much). I suspect anyone surveyed would have a different formula for what causes this unease - I struggle to define it (yet think about it constantly), hence my comment above.
Ultimately when I think deeper, none of this would worry me if these changes occurred over 20 years - societies and cultures change and are constantly in flux, and that includes jobs and what people value. It's the rate of change and inability to adapt quick enough which overwhelms me.
I see no reason this product should exist even under the Thunderbird umbrella, especially if ANY resources under ANY Mozilla org were employed in this. This product is a distraction from their core mission in either case.
This model is a MoE model with only 3B active parameters per expert which works well with partial CPU offload. So in practice you can run the -A(N)B models on systems that have a little less VRAM than you need. The more you offload to the CPU the slower it becomes though.
Agree. I keep effort max on Claude and xhigh on GPT for all tasks and keep tasks as scoped units of work instead of boil the ocean type prompts. It is hard to measure but ultimately the tasks are getting completed and I'm validating so I consider it "working as expected".
I've been telling analysts/investors for a long time that dense architectures aren't "worse" than sparse MoEs and to continue to anticipate the see-saw of releases on those two sub-architectures. Glad to continuously be vindicated on this one.
For those who don't believe me. Go take a look at the logprobs of a MoE model and a dense model and let me know if you can notice anything. Researchers sure did.
There is something incredibly valuable about forcing yourself to trace execution logic on physical paper. It builds a mental model of state changes and memory that you just don't fully develop when a modern IDE's debugger is doing all the heavy lifting for you.
I personally find that LLMs help me store my mental energy to later put into more (personally) fruitful endeavors. Instead of being too tired to contribute to OSS, write, do other things at the end of the day, I find I can leave more juice for the end of the day after work hours, or just at work, I can move faster thus I utilize that extra time and energy into stuff like Anki, ups killing, etc.
Just as anything, I believe the dose is the poison. I still find myself thinking about the high-level and decisions, but I spend less cognitive load into library, implementation specifics I can put somewhere else.
This is a fantastic, highly readable overview. Does anyone have a recommendation for a similarly well-written guide that covers modern GPU architecture for someone coming from a traditional CPU background?
on Tuesday, with 4.6, I waited for my 5 hour window to reset, asked it to resume, and it burned up all my tokens for the next 5 hour window and ran for less than 10 seconds. I’ve never cancelled a subscription so fast.
Doesn't seem that new. I go to a meditation group each week where we do body scan + attention on breath, it seems you are putting together different elements that mediators are likely to put together. Communicating that it is mix and match is good but not new -- there are a lot of big words here for a subject which is actually simple and experiential.
I am interesting in meditations you don't find in the literature like the method I use to cut off the mind-body connection over the breath to deal with acute stress. (e.g. attention to the breath is good for a daily habit when things are basically calm, when you are tilted the mind causes chaos in the body and vice versa and that attention makes the problem worse not better.
Ha, grew up in Harahan. When I left the LA for college, people were shocked to find out where I was from based on how I talked. I would hear areas of New England, 'no discernible accent,' and also Canadian. Apparently the Canadian comes out when I say words like out, about, and house. I can't hear it but my friends all swore up and down they could.
There are so many unique dialects hyperlocal to New Orleans, it's amazing.
