Qwen 3.8 Flash Next is amazing. I only have a 64G Mac so I have to run Sushi project’s 3 bit quant. Amazing results with pi-dev. More for fun than anything else, but I am trying to do as much as possible with local models, now rarely falling back to a paid deepseek-4.1-flash API.
Progress on running local models has been amazing.
Yes, I am running the same on a 64G mc. It's good, but slow at 25 tps on average! I want > 100 tps - but I don't have $5k to spare for an m5 ultra or an nvidia setup.
So I still wonder if one could get good enough quality with a faster higher quant or superoptimized Qwen3.8-27b with dflash2
Same boat, Mac mini M4 Pro 64GB. 25 tps is a bit slow for interactive coding. Any tricks that helped (quant, MLX vs llama.cpp, context size, thinking level)?
It was inevitable that the providers would stop giving away free cookies and milkshakes.
I pay Google $5/month for Chat and my wife gets to share that: a fantastic deal. I even get a short weekly (one each) opus and gemini vibe coding sessions with agy.
I pay for inference: I paid $3300 for a Mac mini 64G M5-Pro which runs Qwen-3.8-Flash-Next (3 bit quant) with pi-dev and the results are so very much excellent enough for about 60% of my work and paying Deepseek for deepseek-4.1-flash with Deepseek Harness handles almost everything else.
I worked at Google in 2013 and I mostly like them as a company. I like their approach to AI in general, but I hate the business models of Anthropic and OpenAI and I fear the US taxpayer is going to pick up the tab on this one.
I would be curious to see how Steve Jobs would have delivered AI tools via Apple. The current mess of agents, harnesses is a utter shambles for the average non-techie.
That would be interesting. I hate to say it, but he might have given us something like Muse by Meta. I made a comment on HN a year or so ago about wanting a strong personal AI agent from a company I more or less trust (e.g., Apple or American Express).
The article resonates with me. I am easing back off of vibe coding. Now I will use dsh with a deepseek-4.1-flash commercial API occasionally, but now run Laguna-xs-2.1 running on oMLX locally for code reviews, and routine code changes. I am “devolving” back to doing most work myself.
I have lived in a tech-rich life since I bought my first single board home system in around 1975.
I think it is as easy as setting boundaries: practice meditation. Learn to enjoy sitting and doing nothing, both in the living room and sitting outside.
Then when the time is right, work hard for several hours to get important stuff done.
Food tastes best when we are very hungry, so we must go long periods of time doing mini-fasting a few times a day in order to enjoy food. Similarly, earning a living or experimenting with tech should be something that you sit down and do for a while, then do something else.
if fasting (and spiking your blood glucose with ostensibly bigger meals) is required to enjoy food, then something has gone quite wrong. I assume you're referring to more whole and less processed/sugar-infested food. in that case, maintain a consistent diet of whole foods, eat small meals throughout the day, and your palate will adjust.
nah, periodic calorie-restriction without feeling you 'have to' feels alright when you next eat, and, you can consciously choose a healthier snack in the moment to continue the nicer feeling.
Knowing you skipped a pizza and it's still available in the freezer (plus you still don't need to buy another one to replace it, yet) after growing up feeling overweight, eventually being overweight, and feeling the same during both periods - the price is an electricity bill for the freezer, not priceless.
I have a different take on this: I bought a Quest 2 several years ago, spent some money and bought about 10 experiences/games/etc. for it, and it is good enough that I continue using it with no real desire to buy a newer model. My wife was watching me use it last week and she commented “isn’t there an upgrade for that?”
Wonderful toy, even though I only use it about 90 minutes a month it is worthwhile for me to own.
The three year old Quest 3 is still the absolute best thing you can buy in this space in terms of value per dollar. Especially the color passthrough is a feature I found to enjoy quite a lot and it prevents me from even considering the new Steam Frame. After the price hike I think Meta might now sell roughly at break even or perhaps even with some tiny margins, but before it was definitely at a loss. If mine fell down and broke today, I'd probably buy it again in a heartbeat, even though I only use it semi-regularly like you.
Given the memory and general hardware shortages, I expected the price to be above $1200. Valve’s subsidy isn’t as high as Meta’s insane and aggressive hardware subsidies which is not the norm.
Still, you basically pay twice the price for finger and eye tracking and a slightly newer snapdragon with more RAM. Resolution, lenses, refresh rate are all basically equal and passthrough is way worse without the hardware upgrade.
I bought my Quest 2 when it first came out, and I played it for a while, about 2-3 hours a week, peaking at about an hour a day when I found that Blade and Sorcery is a really good game for "exercise".
I bought the Quest 3 as an upgrade because I had noticed my Quest 2 started having intermittent input lag issues. I never pinpointed what was causing it, but my Golf clubs would fly out of my hand and I'd have to wait a few seconds for them to eventually find their way back to me. My controllers would drift out of view when navigating menus. I uninstalled everything, reinstalled it again. When that didn't work, I upgraded.
The issues persisted in the new version as well. So for about the last 20-ish months, I've averaged under an hour a month, most months I don't even pick it up. I might do some homemade PC VR "experiments" (still have access to mouse and keyboard for the game, and not the controllers) on some random claude code experiments. I have a "cyberpunk" mobius strip space station walking sim I've been working on, that will eventually hook into a treadmill.
I average about 2-3 hours per week. I’ve gotten into simracing and an average Le Mans Ultimate race is around an hour which I play a couple of times per week.
The native experiences are too barebones and I don’t even use it untethered
re: “”Start with the harness, because it is what makes everything else usable.””
I have written three harnesses this year (in Common Lisp, Python, and Racket Scheme) and it has been a fantastic learning experience. I have been using neural network tech since I was on a DARPA neural network advisory panel in the 198os, and I am even more excited (by an order of magnitude) than I was back then.
I think Tim has it right, and the hyperscalers serve a function of bootstrapping smaller systems, but they are far from the whole story.
What i find insane is how harness engineering feels like this newly discovered thing, but it’s been like 50 years. Why are harnesses still trash, it’s frustrating. AI regularly bricks systems, both physical and in code
I was the second featured Creative Commoner decades ago and I have published all my books using Creative Commons share and share alike, no commercial reuse for the last few decades.
I haven’t been considering AI training use to violate my use of this license, but I suppose it does. When I have some free time I think I will switch the license on my books to the CC license that permits commercial reuse.
I think there are (at least) 2 important things here:
AI training web scrapers should respect robots.txt, ai.txt, etc. files associated with content.
Privacy issues are a severe problem, and privacy and security issues should be ‘top of mind.’
Progress on running local models has been amazing.
reply