dools

When was the last time you heard a change of government as a result of democratic election referred to as “regime change”?

The trump admin is a hive of scum and villainy worthy of a comic book universe, and Musk is inextricably linked. Thus anyone using twitter or grok or buying a Tesla or using starlink is complicit.

EDIT: or working for these companies!! Couldn’t pay me enough to do it.

This just means you have to describe what you want in Swift or whatever. If it doesn’t have the language then it doesn’t have the capability to transform intent into code.

No way is it less capable. When deepseek can't get its shit together, I give Luna a go, then Terra, then Sol.

Most of the time Luna figures it out where Deepseek was failing. I rarely have to go to Sol levels.

And all it takes is buying from a Nazi white supremacist child pornographer!!

I can go for days on end without topping up my deepseek account. When it can’t solve a problem I switch to GPT and have to top up in real time.

Mind genuinely blown

The only effective way to police this is to make the telco accountable and have a reporting system. Someone is terminating the calls and getting paid for doing it.

All this talk starts from the assumption that anonymity is something to which anyone in a society should have a right.

I have been using deepseek v4 pro almost exclusively. I was using Kimi a lot but it just nose dived. The decline started with the release of 2.7 and accelerated with the release of 3.

When I need vision capabilities I use GPT 5.3 codex and if deepseek can’t figure something out after a few goes I switch to GTP 5.5 or 5.6 (I’ve been giving Terra first bite recently and it does pretty well, and have used Sol a couple of times).

Using this regimen means I spend under $100 per month on inference and I work all day everyday with multiple agents running simultaneously all on API token spend not subscriptions.

Well I have spent a LOT of time working with these devices, and I took a look through the website, and I didn’t see anything that looked wrong.

But not exhaustively no, because why would I? it’s just the first google result for ”openstick”.

It’s a pretty cool project with a cult following. If you’re interested you could spend years working with the same devices and then verify the information yourself.

What is, that website? It’s pretty thorough. It’s not my website but the information is all accurate.

Here you go https://hackaday.com/2022/08/03/hackable-20-modem-combines-l...

Speaking of Linux on mobile, I have about 300 of these things for sale with some associated hardware and software if anyone is interested (in Australia but can ship obviously) https://www.openstick.de/

It’s an extension of technical debt. They’re both bullshit in my opinion.

I don't understand the concern about "cognitive debt". I frequently have to maintain code I wrote, or someone else wrote, weeks/months/years ago and I have NFI what's going on. Now I say to the LLM "tell me what's going on" and it tells me. I can ask it some follow up questions, and build up my understanding. It's SO much faster than grepping through the source myself and I can do it for as multiple issues in parallel. The notion of reading every line of code is absurd to me, the notion of RETYPING it beggars belief. Surely this is satire.

Have you been consistently replying with the same answer to that comment? Or have you genuinely tried using coding agents?

I've built 4 pretty novel features where the LLM didn't know how to solve the problem, but with design/decision input from me was able to implement it. Between the two of us it was done, I would estimate, 10 - 20 times faster in terms of man hours than the same implementation would have taken without the use of LLMs. Like it's team level productivity from a single developer. In my case it was done infinity times faster because I just wouldn't have done these things, it would have been cost-prohibitive.

> and AI has yet to show any real utility

Ummm ... have you not tried using LLMs for coding work?

I don't understand how you could compare crypto, which has no utility and no fair value, with AI which is used by hundreds of millions of people every day to achieve real outcomes.

Yeah it was a deceptively complicated issue. I’m not sure if my implementation is as comprehensive, but it sounds similar: optimistic local writes, outbound queue, server as source of truth, each client has local SQLite.

The issue I found most difficult architecturally was how to deal with staying responsive on first sign in with a large DB. I ended up with a system I called “materialisation on demand” where it will search the server and download only those rows ahead of time.

EDIT: I also ended up using multiple local databases to ensure responsive writes during heavy synching activity.

The app is https://www.benko.app/ it’s available on iOS, android, Mac and windows.

Interesting! I wrote something similar for my app recently, it was the first thing I coded using LLMs.

It’s a hunch. You think it’s outside the realm of possibility? How else do you explain wild swings in capability?

Code review has always been pointless

Hopefully this helps reduce some of the pressure on their infrastructure. Their models have all become super dumb recently and their support are not addressing it. I have a hunch they’ve been serving a significant percentage of requests with quantised models.

I’ve had no issues with deepseek at all. Maybe it’s just luck of the draw

They may have all this amazing architecture but Kimi has been super dumb recently. I reckon they’re under compute pressure and quantising to stay afloat. I was a heavy k2.5/2.6 user earlier in the year and built serious features with it, but even k3 now does stupid shit like fail tool calls and get stuck in endless thought trains. K2.6 was spinning its wheels on a problem for over 10 minutes today and then deepseek v4 fixed it in under a minute.

Something is wrong at moonshot.

“I don’t know about you, but I don’t want to live in a world where someone makes the world a better place better than we do” - Gavin Belson

The difference with open weight is that everyone has access to the same weaponry

Americans don’t get to lecture the world on authoritarianism anymore