Hacker News: tempoponet

New comment by tempoponet in "Ask HN: What was your "oh shit" moment with GenAI?"

tempoponet — Sat, 06 Jun 2026 11:24:30 +0000

I can actually use and enjoy Linux. The "year of the desktop" never came for me, but instead I got the "year of the cli".

For 20 years I've used Linux in one form or another, but I've felt like I was kneecapped for the most basic things. Just trying to plug in an external drive or a second display meant hours of stack overflow and pasting commands I didn't understand.

Now I'm using several Linux machines for Steam, NAS, local LLM, development, and what used to derail a weekend project now amounts to a coffee break while Claude figures it out.

New comment by tempoponet in "Use your Nvidia GPU's VRAM as swap space on Linux"

tempoponet — Wed, 03 Jun 2026 03:24:34 +0000

It's fine for dense models where you need them in VRAM, less so for MoE where you're offloading layers to ram. But 32/32 is pretty good for both in the popular ~30b range right now.

New comment by tempoponet in "Tulip mania: when a single flower was worth more than a house (2025)"

tempoponet — Fri, 29 May 2026 14:25:47 +0000

- You can send any amount of money to anyone in the world very quickly and cheaply, and nobody can stop you.

- No government can dilute it or limit its supply.

Stuff like that. Maybe that matters to you, maybe not, but BTC was created because that didn't exist. And even if you don't use it, you're living in a world where financial institutions have to live alongside an alternative that does these things, for whatever that's worth.

New comment by tempoponet in "Google employee charged with $1M Polymarket insider trading bet on search term"

tempoponet — Thu, 28 May 2026 13:51:24 +0000

This is where a lot of the crypto scammers on x have moved, selling ai/bots to do this. It seems like the odds slip significantly after these large bets are filled.

New comment by tempoponet in "Google's Antigravity bait and switch"

tempoponet — Thu, 21 May 2026 17:39:44 +0000

For the huge percentage of devs using vscode, switching to Cursor was essentially adding a new color theme and a chat window. The CLI switch was far more radical.

New comment by tempoponet in "Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks"

tempoponet — Wed, 20 May 2026 22:15:45 +0000

Thank you for the thoughtful reply. I have some smaller 3080's I'm looking to place and this sounds like a good opportunity.

New comment by tempoponet in "Qwen3.7-Max: The Agent Frontier"

tempoponet — Wed, 20 May 2026 12:59:33 +0000

The memory upgrade is $1k on a Macbook Pro. The laptop is ~$5500.

New comment by tempoponet in "Qwen3.7-Max: The Agent Frontier"

tempoponet — Wed, 20 May 2026 12:53:26 +0000

Expect to pay $4k-10k

- Your RTX 6000 is closer to $10k now

- Sparks are creeping into the $4-5k range

- AMD Strix are ~3.5k

- Apple depends on chipset and memory. Sweet spot would be 128gb M3 Ultra, probably $6-8k but admittedly haven't been tracking closely. New M5 might come in the fall. You can get a new 128gb M5 Max laptop for ~5-6k today.

- a 4x3090 rig would take $5-6k

Every platform has tradeoffs, but it's mostly ecosystem, memory bandwidth, and power consumption. They're all slow. The best option is likely to rent hardware on Runpod. The RIO on self-hosting is very low unless you have a specific need or you're ok treating it as a hobby.

New comment by tempoponet in "Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks"

tempoponet — Tue, 19 May 2026 23:02:19 +0000

Why this entire tool chain instead of building within something like pi code?

I've been exploring this area and a project like https://github.com/itayinbarr/little-coder (not my work) lets me mix and match with my current setup or any plugins built for pi.

New comment by tempoponet in "Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model"

tempoponet — Wed, 13 May 2026 15:22:41 +0000

It's older, but Hermes Pro 2 (same lab as Hermes agent) is a fine-tune of Mistral 7b for tool calling and structured outputs.

This isn't for agentic loops, though. This is for turning simple requests into API calls.

New comment by tempoponet in "Agent Skills"

tempoponet — Tue, 05 May 2026 04:49:02 +0000

Similarly, the agentic coding success stories are from orgs that had all of these things out of the gate.

New comment by tempoponet in "HERMES.md in commit messages causes requests to route to extra usage billing"

tempoponet — Wed, 29 Apr 2026 19:55:11 +0000

It reads like the inventors of Claude can't get Claude to apply a "human in the loop" workflow.

New comment by tempoponet in "The beginning of scarcity in AI"

tempoponet — Fri, 17 Apr 2026 16:19:07 +0000

You can fine-tune a model, but there are also smaller models fine-tuned for specific work like structured output and tool calling. You can build automated workflows that are largely deterministic and only slot in these models where you specifically need an LLM to do a bit of inference. If frontier models are a sledgehammer, this approach is the scalpel.

A common example would be that people are moving tasks from their OpenClaw setup off of expensive Anthropic APIs onto cheaper models for simple tasks like tagging emails, summarizing articles, etc.

Combined with memory systems, internal APIs, or just good documentation, a lot of tasks don't actually require much compute.

New comment by tempoponet in "GLM-5.1: Towards Long-Horizon Tasks"

tempoponet — Wed, 08 Apr 2026 12:49:09 +0000

Rather, Imagine you have 2-3 of these working 24/7 on top of what you're doing today. What does your backlog look like a month from now?

New comment by tempoponet in "Rank the 50 best Apple products"

tempoponet — Fri, 27 Mar 2026 15:53:27 +0000

You're right for the same reason that the original iPhone outranks the iPhone 3Gs.

New comment by tempoponet in "Nvidia NemoClaw"

tempoponet — Wed, 18 Mar 2026 19:46:22 +0000

OpenClaw had a huge viral marketing campaign. It wasn't a coincidence everyone on twitter was talking about it at the same time suddenly. To its credit, it also executed well enough in a few areas that captured people's imagination. Most of the concepts are ideas people have been toying with for years, though.

New comment by tempoponet in "Can I run AI locally?"

tempoponet — Fri, 13 Mar 2026 23:18:16 +0000

What kind of small tasks do you find it's good at? My non-coding use of agents has been related to server admin, and my local-llm use-case is for 24/7 tasks that would be cost-prohibitive. So my best guess for this would be monitoring logs, security cameras, and general home automation tasks.

New comment by tempoponet in "Kimi Released Kimi K2.5, Open-Source Visual SOTA-Agentic Model"

tempoponet — Tue, 27 Jan 2026 15:56:46 +0000

Maybe for a coding agent, but a daily/weekly report on sensitive info?

If it were 2016 and this technology existed but only in 1 t/s, every company would find a way to extract the most leverage out of it.

New comment by tempoponet in "What an unprocessed photo looks like"

tempoponet — Mon, 29 Dec 2025 16:23:14 +0000

And here's the blog article describing the widget: https://maurycyz.com/misc/ads/

New comment by tempoponet in "Netflix to Acquire Warner Bros"

tempoponet — Fri, 05 Dec 2025 14:31:10 +0000

Remember when Netflix almost split its brand with "Quickster"? It was the dying DVD by mail service, but the whole debacle did nothing but confuse people.