Hacker Newsnew | past | comments | ask | show | jobs | submit | YetAnotherNick's commentslogin

You can remove featured, games and preview from browse feed. I have never got product link ads.

I think you are overestimating power usage by order of magnitude or two. For a much bigger Deepseek model, you can get <0.1J/token[1], or 36M output token for 1 kWH.

Or more than 500 book worth of token for 1 hot shower.

[1]: https://inferencex.semianalysis.com/infx/inference/deepseek-...


Interesting. Is that just for inference or does that also amortise the energy used to train the model across the expected number of tokens served over its useful lifetime?

For inference. For models like deepseek, training energy would be tiny compared to inference. But that's not including all experiments etc.

I am willing to bet 1:1 that a model from any other lab will beat Fable 5.2 within 3 months in any metric of your choice.

I am also willing to bet for their next frontier model that a model will beat it within 3 months of its release.


Index is proportional to free float, so Anthropic will be treated as $100B company by index, not $1.5T company.

for first few months.

SpacesX float already increased from 70B -> 600B


I gave both ChatGPT and Claude exact same prompt and none did anything close to what author was claiming. The blogpost could just be poor AI writing.

This seems like terrible PSA. Why would I think that it is compromised.

> investment-grade

Does it mean something or is it a new buzzword. I am seeing this everywhere and the traditional meaning applied to bonds doesn't apply here.


https://finance.yahoo.com/technology/ai/articles/wall-street...

Blackstone think that post-IPO Anthropic will start out with a junk credit rating.

FT seemingly covered it too if you can see it (I can’t):

https://www.ft.com/content/59383c7f-8d82-493f-bf01-d2e862a10...


Which non US government are you talking about. China is investing heavily and making at least some progress. EU couldn't get "legacy rocketry programs" working, so the reason is incompetence not stubbornness. India is trying a bit, but they don't have capacity to spend. Russia is also trying.

DeepSWE was released on May and Deepseek v4 flash was released on April. By definition it couldn't be benchmaxxed on this particular benchmark. My guess is the mutation is not like real world and it is tripping small models, not benchmaxed model.

It's not clear which v4 flash they used. There are 3 different releases for that one.

Edit: I think that's the answer. This page lists the score as 53.3% which is close to the 54.4% reported here https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731 for the 0731 update. The original from April was called preview, doesn't list the score, but in the comparison with the update it scores 7.3%.


That makes sense. I wish they run it on some model released before deepswe release like gemini-3.5-flash.

DS flash also has V4.1 update and supposedly achieves 77.0 on deepswe v1.1

https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017


That's a totally new model.

> already discussed at length on HN

Couldn't find it. Care to provide link.


The actual vulnerability got very little discussion. It's clever. Because Linux networking people are obsessed with checksum performance, virtio-net plumbs checksum offload metadata through the host/guest driver interface. Guests can thus deliver the host packets along with instructions on what to checksum. The vulnerability is a missing sanity check that allows checksum instructions to instruct the host to overwrite the header length field in the IPv4 header, rather than the checksum field.

Crucially, this happens in the middle of packet processing, so the kernel code is forced to work with two different ideas of how long the IPv4 header is. All hell predictably breaks loose.


That’s fascinating. I’ve seen this sort of thing on protocol implementations in layer 4+ but it’s rare to find it in layer 3.

The removal of a copy across the guest host boundary in the name of performance here is irresponsible.


Additional color: per the commit, the bug was found by Paulos Yibelo, who runs PwnAI (the author of this piece), and worked on security at AWS for 4 years prior.

OP asked for a link

And honestly, how the &*DK is this ANYTHING related to firecracker?

Ah maybe not on HN, I forget where I learned of it. Either way, multiple weeks ago: https://news.ycombinator.com/item?id=50108845

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: