 Notice. New forum software under development. It's going to miss a few functions and look a bit ugly for a while, but I'm working on it full time now as the old forum was too unstable. Couple days, all good. If you notice any issues, please contact me. |
Forum Index : Microcontroller and PC projects : AI Is Evolving Fast
  Page 5 of 5 |
|||||
| Author | Message | ||||
| lizby Guru  Joined: 17/05/2016 Location: United StatesPosts: 3771 |
In the past week, Gemini, which had successfully built PicoDB and PicoRR V1 over the course of about 8 weeks, has become unworkable for me. First it spent several days botching a compound IF statement which resolved into 4 conditions. I noticed at one point that it had dropped me from a PRO to a FAST model--which meant it would guess rather than look at the actual code. Then, for the last 3 days I have gotten hours-worth of "Error: can you re-prompt?" or "I'm having a problem, can I help you with something else?". As a result, issues I had hoped to resolve a week ago remain unresolved. I had seen some of this coming (though I hadn't expected it to be so bad). I bought a MINISFORUM UM870 PC: 32GB DDR5, 256GB SSD, Ubuntu 24.04.4 LTS. Yesterday I set up Claude Code Pro on the device, loaded my files, and asked it to do its initialization. Quite impressive--128 lines of assessment, spot on. Then I asked it to analyze the PicoDB library.bas file. Again impressive, with 8 issue areas located. 6 of them were easily fixed; the others are deeper, and I'll have to ask it to resolve them. We'll see. It was a good 7-week run with Gemini. It showed me what the capabilities were. Claude Code goes to the Anthropic servers for intelligence, so it's also going to be susceptible to this tsunami of token usage that is coming. I'm hoping, if need be, I'll be able to go entirely local with my setup. But first I want to see what Claude Code can do at the present time. ~ Edited 2026-03-23 00:34 by lizby PicoMite, Armmite F4, SensorKits, MMBasic Hardware, Games, etc. on FOTS |
||||
| lizby Guru Joined: 17/05/2016 Location: United StatesPosts: 3771 |
More on AI coding on the MINISFORUM UM870 PC. I did a brief test of ollama & qwen2.5-coder running entirely locally--a few hours. It seemed somewhat primitive, but probably workable in the case of an internet outage or a funding shortfall. So I went back to Claude Code API (separate from the monthly subscription). With this, your files are stored locally, but Claude understands the structure. All the AI is done on Anthropic's servers, not locally. This was around 5,000 lines of code in PicoDB and PicoRR. I was very impressed by the way it worked through the PicoDB problem Gemini had cycled around for several days. Fixing that bit of code revealed some other dependent problems which I systematically worked through with Claude. Then I set it on some difficulties in PicoRR, and quickly got those sorted. I liked the way it presented its suggested changes as a diff which you accepted or rejected. Several times I accepted code I knew to have an error, then, before testing, suggested a change which it incorporated. This was very smooth, but expensive (by a retired person's standards)--I paid $25 over the course of 5 days. I thought it was well worth it, both as a learning experience and for fixing problems I had been stuck on with Gemini. I can't in the long run spend $5 a day for hobby coding--but if it was for a job, it would be a trivial expense. So now I'm back to Claude Code in the browser with the $20 monthly subscription. Plus, for some reason, it has given me $50 in extra credits to be used if subscription limits are hit. That will probably expire before I use much (or any) of it. The "Page not responding" issue I had some weeks ago seems to be resolved. Gemini, Claude, Chat are all trying to respond to the same basic dilemma: they want to throw all the compute they can at the effort to reach AGI before anyone else does (the holy grail), but they also need to address exploding demand from customers who just want current AI to solve their immediate problems. Here is a take on one aspect of the dilemma from a major doubter of the finances of all AI-related companies ( "A massive bubble" ): ~ Edited 2026-04-02 00:36 by lizby PicoMite, Armmite F4, SensorKits, MMBasic Hardware, Games, etc. on FOTS |
||||
twofingers Guru Joined: 02/06/2014 Location: GermanyPosts: 1750 |
Me: I asked Gemini about the announced NVIDIA RTX Spark* and the expected prices. * 1.000 TOPS (1 Petaflop @ FP4)! Gemini: Since the NVIDIA RTX Spark is an absolute premium product that blurs the line between a consumer PC and an AI workstation, prices are in the upper segment of the market. Nvidia is not aiming at the budget segment here, but is entering into direct competition with Apple's high-end models (MacBook Pro with M-Max chips). The first official price indications as well as leaks from European retailer listings (e.g., for upcoming Lenovo and Microsoft devices) over the last few days paint a very concrete picture of the different price tiers: Overview of Imaginable Price Tiers (Autumn 2026) Class & Configuration | Price Range | Target & Application ------------------------+------------------+------------------------------------ Entry (Nvidia N1 Base) | approx. | Business users seeking local • 10–12 CPU cores | €1,400–€1,800 | AI assistants & long battery life. • 16 GB to 32 GB RAM | | ------------------------+------------------+------------------------------------ Premium (Nvidia N1X) | from approx. | Content creators, demanding gamers • 18–20 CPU cores | €3,000 | and software developers. • 32 GB Unified Memory | | ------------------------+------------------+------------------------------------ Enthusiast/Developer | €4,000 to | AI researchers & 3D designers • 20 CPU / Blackwell | nearly €5,000 | running giant LLMs (up to 120B) • 64GB–128GB Unified Mem| | completely locally. ------------------------+------------------+------------------------------------ Desktop Mini-PCs | €3,500 to | Stationary AI developer boxes as a • Compact, no display | €4,700 | local alternative to cloud rentals. • Up to 128 GB RAM | | Why are the devices so expensive? The fact that we are moving almost entirely in the four-digit range here has two primary technological and economic reasons: • The TSMC 3nm manufacturing process: Manufacturing the chip at TSMC on state-of-the-art 3-nanometer lines is extremely expensive. The yield of defect-free high-end chips is physically limited, which drives up the base price of the hardware. • The Unified Memory price shock: The heart of local AI performance is the shared, ultra-fast LPDDR5X memory. Due to an acute, worldwide shortage of memory components in the first half of 2026, procurement costs for RAM have increased drastically. Especially the 64 GB and 128 GB top models are pushing the end-customer price up massively as a result. ________________________________________ And finally, there is quantum computing (combined with AI) on the horizon. Let's see what Peter makes of it.  Regards Michael Edited 2026-06-07 22:50 by twofingers causality ≠ correlation ≠ coincidence |
||||
| Page 5 of 5 |
|||||
 Print this page |
 |
The Back Shed's forum code is written, and hosted, in Australia. | © JAQ Software 2026 |
