131–140 of 1001 posts
I like the pelican I got out of deepseek-v4-flash more than the one I got from deepseek-v4-pro. https://simonwillison.net/2026/Apr/24/deepseek-v4/ Both generated using OpenRouter. For comparison, here's what I got from DeepSeek 3.2 back in December: https://simonwillison.net/2025/Dec/1/deepseek-v32/ And DeepSeek 3.1 in August: https://simonwillison.net/2025/Aug/22/deepseek-31/ And DeepSeek v3-0324 in March last year:…
[flagged]
What's the current best framework to have a 'claude code' like experience with Deepseek (or in general, an open-source model), if I wanted to play?
I’m deeply interested and invested in the field but I could really use a support group for people burnt out from trying to keep up with everything. I feel like we’ve already long since passed the point where we need AI to help us keep up with advancements in AI.
I like the pelican I got out of deepseek-v4-flash more than the one I got from deepseek-v4-pro. https://simonwillison.net/2026/Apr/24/deepseek-v4/ Both generated using OpenRouter. For comparison, here's what I got from DeepSeek 3.2 back in December: https://simonwillison.net/2025/Dec/1/deepseek-v32/ And DeepSeek 3.1 in August: https://simonwillison.net/2025/Aug/22/deepseek-31/ And DeepSeek v3-0324 in March last year:…
Being a bicycle geometry nerd I always look at the bicycle first. Let me tell you how much the Pro one sucks... It looks like failed Pedersen[1]. The rear wheel intersects with the bottom bracket, so it wouldn't even roll. Or rather, this bike couldn't exist. The flash one looks surprisingly correct with some wild fork offset and the slackest of seat tubes. It's got some lowrider[2] aspirations with the small wheels,…
Earlier quoted context omitted.
Weren't there some frameworks recently released to allow Macs to stream weights from fast SSDs and thus fit way more parameters than what would normally fit in RAM? I have never tried one yet but I am considering trying that for a medium sized model.
I've been calling that the "streaming experts" trick, the key idea is to take advantage of Mixture of Expert models where only a subset of the weights are used for each round of calculations, then load those weights from SSD into RAM for each round. As I understand it if DeepSeek v4 Pro is a 1.6T, 49B active that means you'd need just 49B in memory, so ~100GB at 16 bit or ~50GB at 8bit quantized. v4 Flash is 284B, 13…
V4 is natively mixed FP4 and FP8, so significantly less than that. 50 GB max unquantized.
Already on Openrouter. Pro version is $1.74/m/input, $3.48/m/output, while flash $0.14/m/input, 0.28/m/output.
Getting 'Api Error' here :( Every other model is working fine.
Earlier quoted context omitted.
> (better than Opus 4.6) There we go again :) It seems we have a release each day claiming that. What's weird is that even deepseek doesn't claim it's better than opus w/ thinking. No idea why you'd say that but anyway. Dsv3 was a good model. Not benchmaxxed at all, it was pretty stable where it was. Did well on tasks that were ood for benchmarks, even if it was behind SotA. This seems to be similar. Behind SotA, but…
Anthropic fans would claim God itself is behind Opus by 3-6 months and then willingly be abused by Boris and one of his gaslighting tweets. LMAO
I have no idea why you'd think that, but this is straight from their announcement here (https://mp.weixin.qq.com/s/8bxXqS2R8Fx5-1TLDBiEDg):
> According to evaluation feedback, its user experience is better than Sonnet 4.5, and its delivery quality is close to Opus 4.6's non-thinking mode, but there is still a certain gap compared to Opus 4.6's thinking mode.
This is the model creators saying it, not me.
I like the pelican I got out of deepseek-v4-flash more than the one I got from deepseek-v4-pro. https://simonwillison.net/2026/Apr/24/deepseek-v4/ Both generated using OpenRouter. For comparison, here's what I got from DeepSeek 3.2 back in December: https://simonwillison.net/2025/Dec/1/deepseek-v32/ And DeepSeek 3.1 in August: https://simonwillison.net/2025/Aug/22/deepseek-31/ And DeepSeek v3-0324 in March last year:…