Thank you. I have the same card, and I noticed the same ~100 TPS when I ran Q3.5-35B-A3B. G4 26B A4B running at 150TPS is a 50% performance gain. That's pretty huge.
I feel the global instability could easily be very disruptive to SpaceX. Just imagine if Russia gets vindictive and starts destroying these satellites or blowing up their satellites to create orbital debris that could knock satellites out of orbit. A really bad solar storm could be devastating.
Just saying there are some decent risks, and pricing it at 1.75T IPO seems risky enough. I would not take that gamble.
> imagine if Russia gets vindictive and starts destroying these satellites
Sounds like lots of demand for new launches from the military-industrial complex.
> imagine if Russia gets vindictive and starts destroying these satellites
Space is big. It’s almost always cheaper to individually target satellites than to try and blanket orbits. And with Starship vs ASAT, the cheap drones are the satellites. Russia would bankrupt itself trying to sink Starlink and Starshield.
(They would also set a precedent that would let the U.S. deny China a LEO constellation.)
> It’s almost always cheaper to individually target satellites than to try and blanket orbits.
The problem is that even one satellite could start the Kessler syndrome due to how many are currently in orbit, and the numbers are expected to keep increasing rapidly - everyone wants their "sovereign" Starlink now that it has been shown to be feasible and performant.
I think two recent advances make your statement more true. The new Qwen 3.5 series has shown a relatively high intelligence density, and Google's new turboquant could result in dramatically smaller/efficient models without the normal quantization accuracy tradeoff.
I would expect consumer inference ASIC chips will emerge when model developments start plateauing, and "baking" a highly capable and dense model to a chip makes economic sense.
Who will be funding state of the art local models going forward? AI models are never done or good enough. They will have to be trained on new data and eventually with new model architectures. It will remain an expensive exercise.
I could be wrong because I'm not following this too closely, but the open weights future of both Llama and Qwen looks tenuous to me. Yes, there are others, but I don't understand the business model.
If turboquant can reliably reduce LLM inference RAM requirements by 6x, suddenly reducing total RAM needs by 6x should have a dramatic shift on the hardware market, or at least we can all hope. I know 6x is the key-value cache saving, so I'm not sure if that really translates to 6x total RAM requirements decrease for inference.
There are many sources for data on before and after school cell phone bans. Oregon is far from the first to implement this. 35 US states have some form of school cell phone ban, and I believe the UK is doing a nation-wide ban. There is a good amount of supporting data measuring results on this topic.
For ~$60 you get a device that can play every type of audio file and has better sound quality than your cellphone + streamer combo.
I've been reading more about Chinese hardware and if you've been sleeping on it there are a lot of great Chinese consumer products that are both extremely high quality + very cheap.
Turns out when you have tens of millions of engineers they pump out banger after banger. Also always hilarious, in an enduring way, finding the factory engineers engaging with consumers on random forums that take their feedback seriously.
Note that in this case, you are getting what you pay for: I had a FIIO DAC that sounded amazing but was really bad about full-scale turn-on, sync and desync pops to the extent that it damaged my speakers. Yes, perfect power sequence hygiene would have prevented the problem, but one can't always be ready with the amplifier volume knob when their playback system crashes.
ah good to know. Outside of having a very basic dac for my cans on my desktop, I wouldn't think of any serious equipment failures could happen. Probably wrong to assume that these things are engineered to be safe/redundant.
This is going to be my first DAP in like 15 years, zune being the last one I had. Pretty excited to rock it out for a bit.
There's a current fad out there to move to more single-service type of devices rather than using a phone for everything. Want to try it out myself to be more intentional with my digital actions and ween myself away from corporate social media.
If they're allowed and help where phones wouldn't or don't there are still lots of options for stand alone MP3 players with minimal or no connectivity. They still exist as a market because they're dirt cheap to make.
This is what I've been working on. I've written a project wrapper CLI that has a consistent interface that wraps a bunch of tools. The reason I wrote the CLI wrapper is for consistency. I wrote a skill that states when and how to call the CLI. AI agents are frequently inconsistent with how they will call something. There are some things I want executed in a consistent and controlled way.
It is also easier to write and debug CLI tooling, and other human devs get to benefit from the CLI tools. MCP includes agent instructions of how to use it, but the same can be done with skills or AGENTS.md (CLAUDE.md) for CLI.
I thought this was going to talk about a nerfed Opus 4.6 experience. I believe I experienced one of those yesterday. I usually have multiple active claude code sessions, using Opus 4.6, running. The other sessions were great, but one session really felt off. It just felt much more dumbed down than what I was used to. I accidentally gave that session a "good" feedback, which my inner conspiracy theorist immediately jumps to a conclusion that I just helped validate a hamstrung model in some A/B test.
This article has some cowboy coding themes I don't agree with. If the takeaway from the article is that frameworks are bad for the age of AI, I would disagree with that. Standardization, and working with a team of developers all using the same framework has huge benefits. The same is true with agents. Agents have finite context, when an agent knows it is using rails, it automatically can assume a lot about how things work. LLM training data has a lot of framework use patterns deeply instilled. Agents using frameworks that LLMs have extensive training on produce high quality, consistent results without needing to provide a bunch of custom context for bespoke foundational code. Multiple devs and agents all using a well known framework automatically benefit from a shared mental model.
When there are multiple devs + agents all interacting with the same code base, consistency and standards are essential for maintainability. Each time a dev fires up their agent for a framework their context doesn't need to be saturated with bespoke foundational information. LLM and devs can leverage their extensive training when using a framework.
I didn't even touch on all the other benefits mature frameworks bring outside of shared mental model: security hardening, teams providing security patches, performance tuning, dependability, documentation, 3rd party ecosystems. etc.
reply