HNHacker News
TopNewBestAskShowJobs

hkchad

304 karma · joined August 15, 2017

submissionscomments
hkchad··on I don't like passkeys
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.
hkchad··on PS5 Linux lead quits: "a bunch of noobs using LLMs" that "they don't understand"
Tell us you know nothing of how AI development work without telling us.
hkchad··on Setting up OpenCode with Ollama and sbx on Mac
Friends don't let friends use Ollama
hkchad··on Silicon Valley is transforming the military-industrial complex? (2024)
Transforming? You guys do know where google got it's start right? SV has been DOD funded from the start.
hkchad··on Gateside by TSA Precheck
Lots of people get TKN's with their work, for free.
hkchad··on Ask HN: Who is using MCP in production?
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.
hkchad··on My local model setup on an M4 Pro Mac Mini
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.
hkchad··on My local model setup on an M4 Pro Mac Mini
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).
hkchad··on Six months of writing code exclusively with agents
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.
hkchad··on "That's not SOC 2 compliant"
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.
hkchad··on TreasuryDirect: Prepare for ID.me – Your New Way to Log In
Why on earth are they not using login.gov
hkchad··on Auto mode is now the default in Claude Code
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.
hkchad··on Anyone else get a vague GitHub shakedown notice?
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.
hkchad··on Postgres rewritten in Rust, now passing 100% of the Postgres regression tests
X written in Rust seems like the new Hello World for LLM coding agents now.
hkchad··on Ask HN: MacBook vs. Dedicated GPU for LLM
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.

hkchad··on LastPass notifies users of yet another data breach
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.
hkchad··on Chrome is looking to permanently drop MV2 extension
I dropped Chrome about 2 years ago. FireFox does everything I need it to do and more.
hkchad··on How to setup a local coding agent on macOS
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.
hkchad··on Ferrari shares fall after launch of first EV as Jony Ive design proves divisive
Probably have to turn it upside down to charge it
hkchad··on New Lifetime Plex Pass Pricing
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.
hkchad··on Amazonbot is finally respecting robots.txt
They can't get out of SES sandbox /s
hkchad··on Plex's price hikes prove I was right to switch to Jellyfin
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.
hkchad··on We built an air-gapped Jira alternative for regulated industries
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.
hkchad··on Airbnb and Vrbo are going downhill like a hippo on a water slide
Rarely is it worth it for me to deal w/ AirBnb type places anymore. After all the fees and extra work trying to understand each of their 'rules' I find getting a hotel is just easier. Unless I'm trying to stay at a particular destination for several days in a row and need a 'home base' hotels are just more convenient as long as all I need is a place to crash at night. They make the beds and cook me breakfast and I don't even have to start the washing machine when I leave...
hkchad··on Calculating Oil Storage Tank Occupancy with Help of Satellite Imagery
Saw this headline and thought, HA been doing this for YEARS, yea, need to add a (2017) to the headline...
hkchad··on Google aims to reinvent email with Wave (2009)
Me and a few buddies used it to plan trips and coordinate plans, it was awesome. The shutdown of Wave and Google Reader is what turned me off to investing any more of my time into Google products.
hkchad··on Ask HN: What do you spend your money on?
Life takes about 1/2, Mortgage, Insurance, Tuition, Utilities. SCUBA takes the rest, gear/travel. When SCUBA doesn't take the rest it goes into retirement/investments.
hkchad··on SMS 2FA is not just insecure, it's also hostile to mountain people
I have garbage cell signal in my house, was only an issue for sending/receiving large pictures/video's over iMessage, apparently those don't send over WiFi for some unknown reason as well... I called Verizon and they sent me a Fem2Cell, problem solved.
hkchad··on Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?
I'm using JetBrains w/ GitHub CoPilot, the amount of context it has around what I'm working on is next level, it's not just 'code complete' but it's 'context aware' as well, say for example I need to open a csv and parse out a few columns by the time I have named the file it's giving me the entire block of code WITH the proper column names of the files, all you do is hit tab and refactor. You won't get that just w/ copy/paste.
hkchad··on Dropbox will require App Indicator support on Linux
I finally go so fed up with drop box, every time I login more and more popups trying to get me to upgrade, etc. It was the final push to just use my NAS Software to self host my files. In the past it wasn't as reliable as DropBox but with hardware now and Tailscale its much easier and much better experience.
Page 1 of 5Next →