For a 30B model, you want at least 20GB of VRAM and a 24GB MBP can’t quite allocate that much of it to VRAM. So you’d want at least a 32GB MBP.
It's a MoE model so I'd assume a cheaper MBP would simply result in some experts staying on CPU? And those would still have a sizeable fraction of the unified memory bandwidth available.
I haven’t tried this myself yet but you would still need enough non-vram ram available to the cpu to offload to cpu, right? This is a fully novice question, I have not ever tried it.
You can argu that you will have skill atrophy by not using LLMs. We have gone multi cloud disaster recovery on our infrastructure. Something I would not have done yet, had we not had LLMs. I am learning at an incredible rate with LLMs.
Yes, you certainly can argue that, but you'd be wrong. The primary selling point of LLMs is that they solve the problem of needing skill to get things done.
They purportedly solve the problem of needing skill to get things done. IME, this is usually repeated by VC backed LLM companies or people who haven’t knowingly had to deal with other people’s bad results.
This all bumps up against the fact that most people default to “you use the tool wrong” and/or “you should only use it to do things where you already have firm grasp or at least foundational knowledge.”
It also bumps against the fact that the average person is using LLM’s as a replacement for standard google search.
We dropped Claude. It's pretty clear this is a race to the bottom, and we don't want a hard dependency on another multi-billion dollar company just to write software We'll be keeping an eye on open models (of which we already make good use of). I think that's the way forward. Actually it would be great if everybody would put more focus on open models, perhaps we can come up with something like the "linux/postgres/git…
> open models
Google just released Gemma 4, perhaps that'd be worth a try?
The bump from 4.6 to 4.7 is not very noticeable to me in improved capabilities so far, but the faster consumption of limits is very noticeable. I hit my 5 hour limit within 2 hours yesterday, initially I was trying the batched mode for a refactor but cancelled after seeing it take 30% of the limit within 5 minutes. Had to cancel and try a serial approach, consumed less (took ~50 minutes, xhigh effort, ~60% of the rem…
From what I understand you shouldn't wait more than 5min between prompts without compacting or clearing or you'll pay for reinitializing the cache. With compaction you still pay but it's less input tokens.
(Is compaction itself free?)
We dropped Claude. It's pretty clear this is a race to the bottom, and we don't want a hard dependency on another multi-billion dollar company just to write software We'll be keeping an eye on open models (of which we already make good use of). I think that's the way forward. Actually it would be great if everybody would put more focus on open models, perhaps we can come up with something like the "linux/postgres/git…
Any recommendations on good open ones? What are you using primarily?
LMArena actually has a nice Pareto distribution of ELO vs price for this
I’m trying to understand how this is useful information on its own?
Maybe I missed it, but it doesn’t tell you if it’s more successful for less overall cost?
I can easily make Sonnet 4.6 cost way more than any Opus model because while it’s cheaper per prompt it might take 10x more rounds (or never) solve a problem.
We dropped Claude. It's pretty clear this is a race to the bottom, and we don't want a hard dependency on another multi-billion dollar company just to write software We'll be keeping an eye on open models (of which we already make good use of). I think that's the way forward. Actually it would be great if everybody would put more focus on open models, perhaps we can come up with something like the "linux/postgres/git…
Is that why they are racing to release so many products? It feels to me like they want to suck up the profits from every software vertical.
>we don't want a hard dependency on another multi-billion dollar company just to write software One of two main reasons why I'm wary of LLMs. The other is fear of skill atrophy. These two problems compound. Skill atrophy is less bad if the replacement for the previous skill does not depend on a potentially less-than-friendly party.
I was worried about skill atrophy. I recently started a new job, and from day 1 I've been using Claude. 90+% of the code I've written has been with Claude. One of the earlier tickets I was given was to update the documentation for one of our pipelines. I used Claude entirely, starting with having it generate a very long and thorough document, then opening up new contexts and getting it to fact check until it stopped…
Yeah, +1. I will never be working on unsolved problems anyhow. Skill atrophy is not happening if you stay curious and responsible.
We dropped Claude. It's pretty clear this is a race to the bottom, and we don't want a hard dependency on another multi-billion dollar company just to write software We'll be keeping an eye on open models (of which we already make good use of). I think that's the way forward. Actually it would be great if everybody would put more focus on open models, perhaps we can come up with something like the "linux/postgres/git…
Another aspect I haven’t seen discussed too much is that if your competitor is 10x more productive with AI, and to stay relevant you also use AI and become 10x more productive. Does the business actually grow enough to justify the extra expense? Or are you pretty much in the same state as you were without AI, but you are both paying an AI tax to stay relevant?
Either the business grows, or the market participants shed human headcount to find the optimal profit margin. Isn’t that the great unknown: what professions are going to see headcount reduction because demand can’t grow that fast (like we’ve seen in agriculture), and which will actually see headcount stay the same or even expand, because the market has enough demand to keep up with the productivity gains of AI? Increasingly I think software writ large is the latter, but individual segments in software probably are the former.