Viewing profile — biddit

That ~119 GB optimization is great. Hadn't seen that yet. That pops a 4x-Spark setup to 476 GB, which gives a lot more headroom for running something like GLM 5.2 at 4-bit, which i…

Ah yeah, your reaction makes sense. In the circles I run in, there is a lot of hype around Sparks for inference, so my gut reaction is to respond with this type of warning. I did n…

Please don’t buy a DGX Spark unless all three of these are true: - You value simplicity more than performance or price-to-performance. - You accept that the hardware will depreciat…

> cruelly cancelling This is assigning intent without evidence, as is common in tribal politics. A non-charged assessment might use the phrase " abrupt cancelling." We cannot creat…

> The polarization of politics has become so intense > The same people who want to paint the Statue of Liberty gold seem to have no clue what it represents You seem to be lamenting…

I have a similar setup, but separate desks: - A sitting desk for coding - A standing desk for thinking and working on paper There is something magical about standing while working …

> Does anyone here have experience running large models in a multi-GPU setup with several RTX 6000s in a high-concurrency regime and with large context lengths? (something like Dee…

What an entirely unserious company. So glad I dumped Claude Code last summer after being gaslit by Anthropic over service degrades. I was fine with the service degrades, totally un…

Comparing Apples to Oranges. Apple only makes disposable devices now. They're a megacorp can negotiate massive discounts at every stage of the supply chain. I've helped several peo…

Yep. And there will be 50 clones on GitHub by end of week. It’s just how it is now.

Strongly disagree with the thesis. Everything points to commoditization of models. Open/distilled models lag behind frontier only by 6-12 months. Regulatory capture is the only thi…

Also, ironically, they are the most dangerous lab for humanity. They're intentionally creating a moralizing model that insists on protecting itself. Those are two core components n…

Call it what you will. But the experience is like you have a reliable coworker, but he randomly decides to take bong hits. "No no yeah bro no I'm good like really the work's done a…

Okay that makes sense. Do you see more pushback in specific industries? I did some quote/purchasing automation work in food mfg a decade ago, and those guys were super difficult to…

> Agents that source quotes, negotiate prices, and get the best deals. Didn't Alexa fail miserably with the "have AI buy something for me" theory? There is a significant mental in …

I have a bespoke local agent that I built over the last year, similar in facilities to Moltbot, but more deterministic code. Running it this kind of agent in the cloud certainly ha…

Yes, frontier models from the labs are a step ahead and likely will always be, but we've already crossed levels of "good enough for X" with local models. This is analogous to the f…

I’ve been following Peter and his projects 7-8 months now and you fundamentally mischaracterize him. Peter was a successful developer prior to this and an incredibly nice guy to bo…

Yes! pi is the best-architected harness available. You can do anything with it. The creator, Mario, is a voice of reason in the codegen field too. https://shittycodingagent.ai/ htt…

> I am writing this because almost no one talks about these issues openly, but everyone yelping about Claude Code. Not sure where you frequent online, but there is ample discussion…

Yep, this was a skillset combination I never envisioned. (am married to a Turk). Maybe a good reason to push past the intermediate plateau.

The dialog around AI resource use is frustratingly inane, because the benefits are never discussed in the same context. LLMs/diffusers are inefficient from a traditional computing …

> In practice, it'll be incredible slow and you'll quickly regret spending that much money on it instead of just using paid APIs until proper hardware gets cheaper / models get sma…

Sorry for your loss - it's a terrible disease. My mother is also data point - grew up on a farm where her father used it. She was diagnosed with Parkinson's 2018.