hkchad

Yes, there are. The Semiconducter stuff is 6 9's 99.9999, then there's UHP .9995 which is what I use, then .999 mostly welding I think? Then goes down from there. Most 'balloon' grade has some oxygen in it since people like to inhale it and talk funny, adding a little o2 keeps people from dying.

Lets hope this get my T bottle's lower than $675 each, it's almost 2x what I was paying last year.

I will NEVER buy google hardware again. They kill stuff that we depend on and then just expect you to buy their latest version. Up yours, not going to happen. Got rid of my last nest products this year and did NOT replace with the google version. Goodbye!

The problem with all the AI IDE's is you can't use them with most enterprise/teams accounts, you have to use API which can cost upto to 10x more over an enterprise plan. I really like JetBrains, used them for a LONG time, but just find myself doing 99% of my day to day with iterm and sublime now.

Such an awesome way to kill a somewhat useful program. Just keeping putting nails in the coffin. The future is here and it's NOT reverting no matter how much people want to stick their head in the sand.

Yes, but then they can't use that entire interaction. They used humans to verify the detection in the past, now its good enough to auto ban users and force them to be 'nice' so they can gather more training data.

Long time JB user here, and I mean long time. The past year I have been using claude in the JB terminal but nothing, and I mean nothing new has come of it in that year. Stuck in a tiny terminal window, opening files every so often. A couple months ago I switched back to iTerm2, full screen and use sublime to open the odd file every so often. So this makes 100% sense. They need to do a better job integrating with agents and not pushing their own.

I have passkeys on literally everything that will support them and store them in 1Password. I can access them on my laptop, phone, desktop without issue.

Tell us you know nothing of how AI development work without telling us.

Friends don't let friends use Ollama

Transforming? You guys do know where google got it's start right? SV has been DOD funded from the start.

Lots of people get TKN's with their work, for free.

MCP's are great for adoption of your service outside of developer circles. Non Technical users can click a link, trigger an OAuth flow and authenticate. You can't do that with API. API still is better for developers using a AI via a CLI but MCP is easier adoption for web or desktop based clients.

What do you want to know? Just start llama-swap with the models i have downloaded, add llama-swap as a provider in bifrost, expose the models you want and they become available in one single endpoint you can use in anything like opencode, openwebui or anything that speaks openai.

I run a similar setup to the one he described on similar hardware. I run bifrost and llama swap though (tailscale rocks). My local model usage is for some out of band batch processing one of my personal apps uses. Basically a personalized recommender for media, it curates stuff for me based on a database i've compiled over years, so non-interactive. For that use case, I don't really care that it might take a few minutes to run. It's free. The machine is just sitting there anyway. I have tried using qwen-coder and opencode on my M5 Max 128gb and compared to claude code it's painful. I did setup a workflow where claude plans, qwen executes (unattended overnight, again b/c it's slow) and then claude reviews. I benchmarked this several times and I ended up using MORE tokens with claude because it had to 'fix' all the qwen issues. While the code it produced was 'good enough' the fixes were worth it so I just stick to coding task using API models (codex and claude).

I've been a software dev for 25 years. In the past year I've hand written maybe 10 lines of code. For the first 2-3 months i would read it, then I figured out how to really use AI/code gen and the amount created was more than I could read. I can work on 2-3 projects at once, or 2-3 parts of a larger project at once. More than that I can't keep task switching. The speed and complexity of what I'm able to create is 10x doing it by hand. In the hands of someone that understands system design it's a great tool, but still need fundamentals. I've seen junior's build stuff that would never deploy and would crash with a handful of users.

SOC2 doesn't really prescribe anything, they require that you document what you say you do then prove it over time. It's not complicated and kind of a joke in the end. So many companies just want to see a 1 page PDF, updated yearly saying you passed your audits, some request your documentation, most don't. Those that do probably just stick it in a folder somewhere and never open it anyway.

Why on earth are they not using login.gov

I setup an alias in my shell for --dangerously-skip-permissions after about a week of the constant y, y, y a year ago. I felt like Homer Simpson running the nuke plant and couldn't take it anymore. So far it's only deleted some files I likely would have said NO to, but in reality would have just hit y anyway. They were recoverable so no harm.

Uh? What? Shakedown? You enabled a free preview of a paid service, they are now letting you know what it will cost to continue to use a paid for service, how on earth is this a 'shake down'? GitHub deserves a lot of crap, but not for this.

X written in Rust seems like the new Hello World for LLM coding agents now.

It depends. I have a M5 128 so i can play around with large models and even keep several of them loaded at once and use something like llama swap to access them all via bifrost or litellm. You won't do this without some serious local GPU's with big memory. The downside is the speed, it's not fast, but fast enough to tinker and develop with worrying about ongoing cloud cost. When done developing and you need to really scale up this is when you can swap to cloud computing and get the job done faster. My $5k macbook can do more than a $50k nvidia/intel/amd setup, just not as fast.

So you need to decide whats important to you if you want to work locally, large/many models or speed. It's the pick 2 problem speed, size, cost, pick 2 or go with cloud and accept your development time is also spent $$ on each iteration.

I was hoping for the M5 ultra by now, but looks like that's not coming until much later this year for a much higher price now.

Anyone still using lastpass in 2026 deserves this, I'm sorry but this company has proven time and time again they should not be trusted. I migrated off them years ago after one of these breaches and haven't looked back since.

I dropped Chrome about 2 years ago. FireFox does everything I need it to do and more.

I have a M5 MAX with 128, local models are toys compared to hosted ones. I've spent a lot of time and money trying to make it work even 1/2 as well.

Probably have to turn it upside down to charge it

Goodness, that's a 10x increase since I got mine in 2014, no way in HELL I'd pay their new price. What on earth are they thinking.

They can't get out of SES sandbox /s

Everytime I read these post I'm glad I bought a lifetime pass 12 years ago, very well got my $$'s worth over the years.

Why? I use to manage one on a classified air-gapped network, back before Atlassian was all Cloud Based or 'Data Center' license junk. We had Stash, Jira, Confluence, FishEye, HipChat, everything hosted on a non-internet connected network.