Hacker News: mv4

New comment by mv4 in "Are You Enjoying Our Linguine? (2025)"

mv4 — Wed, 03 Jun 2026 16:49:53 +0000

What the hell did I just read.

New comment by mv4 in "Microsoft builds MacBook Pro rival with NVIDIA-powered Surface Laptop Ultra"

mv4 — Tue, 02 Jun 2026 14:25:08 +0000

Intel has already tried this (CPU+GPU+NPU) in partnership with Asus [1]. Big announcement at CES back in January. Not seeing much traction. Let's see how this one is received.

[1] https://www.intel.com/content/www/us/en/ai-pc/overview.html

New comment by mv4 in "A 10 year old Xeon is all you need"

mv4 — Mon, 01 Jun 2026 15:20:13 +0000

I am sure it can. It will still generate a lot of heat when under load.

Are you telling me I should go for it? :)

I do have a dual DGX Spark cluster running MiniMax M2.7 already so I am all for on-prem. But will be interesting how this old machine will perform!

New comment by mv4 in "A 10 year old Xeon is all you need"

mv4 — Mon, 01 Jun 2026 14:05:09 +0000

I have an old 192GB DDR4 Dell Precision with dual Intel Xeon Gold 6130 that I've considered spinning up. What's giving me pause is 250W at idle.

New comment by mv4 in "A 10 year old Xeon is all you need"

mv4 — Mon, 01 Jun 2026 13:42:18 +0000

You just described the absolute nightmare scenario for the newly minted trillion-dollar companies whose only hope is for enterprises and SMB to move all their business processes to the cloud, with employees competing at token maxxing.

New comment by mv4 in "I think Anthropic and OpenAI have found product-market fit"

mv4 — Thu, 28 May 2026 19:13:48 +0000

Minimax M2.7.

New comment by mv4 in "I think Anthropic and OpenAI have found product-market fit"

mv4 — Wed, 27 May 2026 19:45:25 +0000

I configured a dual DGX Spark cluster, and it's certainly "good enough" for my agentic and coding needs.

New comment by mv4 in "I think Anthropic and OpenAI have found product-market fit"

mv4 — Wed, 27 May 2026 19:43:44 +0000

If people figure out how to run agents on-prem (already becoming feasible for both agentic tasks and coding on consumer hardware like Mac Studio 128GB+ or DGX Spark with some models) these companies will be in deep trouble.

Privacy is also a huge issue.

New comment by mv4 in "Dropbox CEO Drew Houston to step down"

mv4 — Tue, 26 May 2026 18:11:09 +0000

Only took 19 years!

New comment by mv4 in "Codex is now in the ChatGPT mobile app"

mv4 — Thu, 14 May 2026 21:54:15 +0000

Can someone recommend an IDE that can be used with a self-hosted model (via OpenAI or similar)?

New comment by mv4 in "Ask HN: Who is using OpenClaw?"

mv4 — Wed, 15 Apr 2026 22:57:59 +0000

I mentioned the same thing and it's getting downvoted lol

New comment by mv4 in "Ask HN: Who is using OpenClaw?"

mv4 — Wed, 15 Apr 2026 22:33:59 +0000

Looking at the comments here, it appears people are trying to do too much, too soon, which inevitably backfires. The key is to put OC in a sandbox (don't give access to your real accounts, it must have ints own separate non-admin accounts for everything only "invite" with limited access as you would a contractor) and generally treat it as a new employee during a trial period. You'll be surprised by how effective it can be if you pace yourself.

As for "you can easily do X,Y,Z with a cron job" we tech people often underestimate what hiding the complexity could do for UX.

"For a Linux user, you can already build such a system yourself quite trivially by getting an FTP account, mounting it locally with curlftpfs, and then using SVN or CVS on the mounted filesystem." -- top comment on "Show HN, Dropbox (2007)

New comment by mv4 in "Ask HN: Who is using OpenClaw?"

mv4 — Wed, 15 Apr 2026 22:24:35 +0000

#2 also provides an opinion on why a certain development is significant and how it relates so something else I am working on for that client.

The process is definitely more pleasant to me than setting up cron jobs and scripting things. I have a business to run.

New comment by mv4 in "Ask HN: Who is using OpenClaw?"

mv4 — Wed, 15 Apr 2026 22:21:23 +0000

No recurring expense, just the hardware upfront cost. My next step is run the models locally as well. I used to work at FAANG (incl. compliance) and I would never use a cloud-based assistant of any kind.

New comment by mv4 in "Ask HN: Who is using OpenClaw?"

mv4 — Wed, 15 Apr 2026 22:13:50 +0000

It is buggy. It's also good at self-diagnostics and I was able to either fix things or find working workarounds by collaborating with it.

New comment by mv4 in "Ask HN: Who is using OpenClaw?"

mv4 — Wed, 15 Apr 2026 22:09:21 +0000

Operations: mostly tasks and reminders, I often think of something while on the road and send a voice message (like I would to a real PA). I use Kokoro-based TTS for local text-to-speech. Anything from "remind me to discuss X with so-and-so tomorrow" to "I have a multiple PoC projects w/ large entities starting next week - think about how I can best handle that" to "brainstorm how can I maximize upfront revenue with them", etc

Sales: using Google/gemini web search API and it's best run off-peak due to rate limits 503 Service Unavailable (everyone is overbooked when it comes to AI) to see what's happening in the space, any new developments involving companies I care about - and send me a daily digest with an overview and conversation topics.

New comment by mv4 in "Ask HN: Who is using OpenClaw?"

mv4 — Wed, 15 Apr 2026 21:50:38 +0000

That's a fair assessment if you look at LinkedIn posts.

Personally though, I am finding it incredibly useful and I use it daily to assist with operations, strategy, sales.

New comment by mv4 in "Ask HN: Who is using OpenClaw?"

mv4 — Wed, 15 Apr 2026 21:39:53 +0000

I have it installed on a dedicated M4 16GB Mac Mini with Telegram, email, and Google Docs integration (the agent has its own accounts). I can chat with it, incl. sending voice messages via Telegram (it can send voice messages back using free TTS run locally).

Using google/gemma-4-31b-it as primary, google-gemini-3.1-pro-preview as secondary (I don't like how it's rate limited).

It's a great personal assistant. Helps me track industry news, key clients, reminds me of important tasks, and helps brainstorm (the rubber duck effect alone is worth it). Now building other skills.

Next step is to run all models locally (I think using Claude/OpenAI APIs is a huge mistake from a privacy standpoint). Since Mac Studios are sold out (and M5 Ultra is not out yet), will probably go with a GX10 or two.

New comment by mv4 in "US Court of Appeals: TOS may be updated by email, use can imply consent [pdf]"

mv4 — Mon, 09 Mar 2026 12:38:17 +0000

Wondering how Spotify is handling this issue

https://newsroom.spotify.com/2025-09-24/spotify-terms-creato...

New comment by mv4 in "Apple's 512GB Mac Studio vanishes, a quiet acknowledgment of the RAM shortage"

mv4 — Sun, 08 Mar 2026 15:45:42 +0000

I tried finding a 128 - 256GB Mac Studio online and most options would not be shipped for at least "8-10 weeks".