zeld4

it's done one by one in Claude.

https://github.com/maxandrews/Epstein-doc-explorer/blob/83ee...

curious to see your result/spec/time

I'm on the fence for SM bc of 8GB GPU RAM, but I just enjoy the tsunami of chinese followups after it, so guess I just have to buy one SM to make the wave work.

reading the comments on HN, guess most did not really read to the end. lol

with open sourced models getting more popular (and how ideology fixation is growing in both US and China), this type of work is very much appreciated.

is there some benchmark?

8GB vram in 2026?!

azure seems quite shitty too. I only use it for having GPT models which is a corp requirement. For 1 hour total I spent on azure.com in past weeks, besides how slow it usually is, I ran into two issues:

- models sometimes got deployed to an unwanted instance, likely because some API is slow and front end state was not well maintained, so user clicking Next too soon will end up screw up the data being submitted

- one of the models (5-mini) deployment took very long and failed, it apparently ended up in a bad and invisible state, and future models can't be deployed any more on that instance. I retried today, same thing, gave up and created a new instance/

Azure AI is supposed to be an area MS making all the bets which I assume should have high quality, but apart from frequent update, it's same low quality as MS Teams.

Everything breaks.

Jobs, if lived, will bow to ads or get fired.

i gave up on gemini cli.

1 in 3 times I used it in past 2 months, it failed for really odd reasons, sometimes the node app just exception quit, sometimes gemini stuck and blame itself and gave up. same task I throw to cc and codex, they nailed without a blink...

in this particular case maybe. but i don't think he's pardoning only crypto people. as long as criminals can offer sth useful to him, they will get above the law.

same, the genocide does not impact me directly in any material sense, but it changes how I see the world and human beings fundamentally.

You basically have to choose from

- Zed: VC funded open source

- Sublime Text: indie closed source

None is ideal, but I guess we all know why.

the integration is nice, but has some rough edges, I ran into situations that things becomes hard to stop

give me $50k raise and I need only $10k/yr.

seriously, I don't see the AI outcome worth that much yet.

On the current level of ai tools, the attention you need to manage 10+ async tasks are over limit for most human.

In 10 years maybe, but $100k probably worths much less by then.

> Even if it’s a bubble, sharing some of it with employees “before it bursts” is a noble action.

the bar for being noble is just low. or maybe I should interpret noble has the noble class in the history, that actually describes it well.

I read a few biographies for western missionaries to Asia, they all ended up get paid handsomely, except those not lived long enough see that day.

If anybody in OpenAI ever had any second thought about taking other people's property without consent, that doubt should go away now with $1.5M in pocket.

this is excellent business approach. best way to get away with stealing is to make everyone thief.

Knowledge cutoff: 2024-06

not a big deal, but still...

it should be a printable book.

Internet was built on trust, but not anymore. It's a Darwinian system; everyone has to find their own way to survive.

Cloudflare will help their publisher to block more aggresively, and AI companies will up their game too. Harvest information online is hard labor that needs to be paid for, either to AI, or to human.

Cryptocurrency is on the way being managed by govt. So it's correct to say cryptocurrency did not fail, but certainly the original libertarian vision behind it is dead.

I played Cyberpunk 2077: Phantom Liberty in 2023 on a mac M1 Pro when it came out, it's fairly playable already. Glad to see it's finally official, and honestly there should be more day 1 mac support.

The silicon valley should thank Huawei and Deepseek, as the only two reasons AI exists as an industry in US are (a) reduce labor cost (b) win over China.

(a) alone sounds super negative to ordinary people, but with (b), justified by the existence and achievement of Huawei & Deepseek, the AI cause now sounds a legit jihad silicon valley is carrying.

I'm struggling to see which is worse, using AI to police their own people, or using AI to genocide in Middle East.

Looks promising.

Do you store the uploaded doc from free/test account?