Hacker News: lordswork

New comment by lordswork in "Skip the Tips: A game to select "No Tip" but dark patterns try to stop you"

lordswork — Fri, 13 Feb 2026 04:05:37 +0000

fun idea but a bit repetitive and boring.

New comment by lordswork in "Thousands of U.S. farmers have Parkinson's. They blame a deadly pesticide"

lordswork — Mon, 15 Dec 2025 15:31:22 +0000

Technically, yes, but it's a similar relationship of humans being animals. If you say animals, the audience will assume you're not talking about humans.

New comment by lordswork in "Kimi K2 1T model runs on 2 512GB M3 Ultras"

lordswork — Sun, 14 Dec 2025 15:02:28 +0000

As long as you're willing to wait up to an hour for your GPU to get scheduled when you do want to use it.

New comment by lordswork in "M8.7 earthquake in Western Pacific, tsunami warning issued"

lordswork — Wed, 30 Jul 2025 01:11:39 +0000

https://www.conservation.ca.gov/cgs/tsunami/maps is getting a hug of death :(

If anyone gets on, please post a screenshot.

ml-engineering/training/performance

lordswork — Mon, 28 Jul 2025 00:36:26 +0000

Article URL: https://github.com/stas00/ml-engineering/tree/master/training/performance

Comments URL: https://news.ycombinator.com/item?id=44706041

Points: 2

# Comments: 0

New comment by lordswork in "Replit's CEO apologizes after its AI agent wiped a company's code base"

lordswork — Tue, 22 Jul 2025 13:24:09 +0000

Agreed, it sounds like nothing of value was actually lost, just a vibe coded app and synthetic database.

New comment by lordswork in "Replit's CEO apologizes after its AI agent wiped a company's code base"

lordswork — Tue, 22 Jul 2025 13:22:57 +0000

The database was synthetic and vibe coded itself:

>he said that the AI made up entire user profiles. "No one in this database of 4,000 people existed," he said.

New comment by lordswork in "Context Rot: How increasing input tokens impacts LLM performance"

lordswork — Tue, 15 Jul 2025 04:18:14 +0000

/compress is the command to do this in most cli agents

New comment by lordswork in "At Amazon's biggest data center, everything is supersized for AI"

lordswork — Fri, 11 Jul 2025 12:44:33 +0000

Far better than xAI's data center being powered by mobile Diesel generators

New comment by lordswork in "At Amazon's biggest data center, everything is supersized for AI"

lordswork — Fri, 11 Jul 2025 12:32:24 +0000

This comment got me wondering whether loss of farmland in the US is a serious issue.

It looks like there's about 800 million acres of farmland in the US and we're losing about 2 million acres per year to the land being repurposed. Despite that, crop production has more than tripled in the past 70 years due to technological advances.

That said, economic effects, loss of farmland, and climate change have contributed to slower growth and higher variability of crop yields recently.

In the past decade there's been a modest 0.8% annual increase in crop production despite losing about 2 million acres per year.

New comment by lordswork in "The Miyawaki Method of micro-forestry"

lordswork — Tue, 08 Jul 2025 14:34:40 +0000

For those wondering, the Miyawaki method differs from normal planting by doing the following:

- heavily pre-treat soil with organic matter (simulating forest floor)

- plant a mix of native plants that will make up canopy, tree, sub-tree, and shrub layers

- densely planting plants (3-5 saplings / m^2)

- heavy mulching after planting (weed suppression, moisture control, nutrients)

This encourages rapid growth into a biodiverse dense forest much faster than standard planting techniques.

New comment by lordswork in "The Llama 4 herd"

lordswork — Sun, 06 Apr 2025 01:21:23 +0000

MOE as an idea specific to neural networks has been around since 1991[1] . OP is probably aware, but adding for others following along, while MoE has roots in ensembling, there are some important differences: Traditional ensembles run all models in parallel and combine their outputs, whereas MoE uses a gating mechanism to activate only a subset of experts per input. This enables efficient scaling via conditional computation and expert specialization, rather than redundancy.

[1]:https://ieeexplore.ieee.org/document/6797059

New comment by lordswork in "AI 2027"

lordswork — Fri, 04 Apr 2025 17:57:13 +0000

Emissions are trending downward because of shift from coal to natural gas, growth in renewable energy, energy efficiencies, among other things. Major oil and gas companies in the US like Chevron and ExxonMobil have spent millions on lobbying efforts to resist stricter climate regulations and fight against the changes that led to this trend, so I'd say they are the closest to these evil corporations OP described. Additionally, the current administration refers to doing anything about climate change a "climate religion", so this downward trend will likely slow.

The climate regulations are still quite weak. Without a proper carbon tax, a US company can externalize the costs of carbon emissions and get rich by maximizing their own emissions.

New comment by lordswork in "Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison"

lordswork — Wed, 02 Apr 2025 07:20:59 +0000

I'm most interested in building cool projects, and I have found AI to be a major multiplier to that effort. One of those cool projects was a custom coding tool, which I now use with all my projects, and continue to polish as I use it.

As far as productivity, it's hard for me to quantify, but most of these projects would not be feasible for me to pursue with my limited free time without the force multiplier of AI.

New comment by lordswork in "Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison"

lordswork — Tue, 01 Apr 2025 21:21:16 +0000

>Would you mind sharing what the project is

rust + wasm simulation of organisms in an ecosystem, with evolving neural networks and genes. super fun to build and watch.

>which AI you are using?

using chatgpt/claude/gemini with a custom tool i built similar to aider / claude code, except it's very interactive, like chatting with the AI as it suggests changes that I approve/decline.

>No sign so far of AI's usefulness slowing down as the complexity increases?

The AI is not perfect, there are some cases where it is unable so solve a challenging issue and i must help it solve the issue. this usually happens for big sweeping changes that touch all over the codebase. It introduces bugs, but it can also debug them easily, especially with the increased compile-time checking in rust. runtime bugs are harder, because i have to tell the ai the behavior i observe. iterating on UI design is clumsy and it's often faster for me to just iterate by making changes myself instead.

New comment by lordswork in "Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison"

lordswork — Mon, 31 Mar 2025 15:18:47 +0000

I'm at 3k LOC on a current Rust project I'm mostly vibe coding with my very limited free time. Will share when I hit 10k :)

New comment by lordswork in "Firing programmers for AI is a mistake"

lordswork — Tue, 11 Feb 2025 17:23:51 +0000

This kind of error doesn't really matter in programming where the output can be verified with a feedback loop.

New comment by lordswork in "Show HN: Simple to build MCP servers that easily connect with custom LLM calls"

lordswork — Thu, 06 Feb 2025 21:56:08 +0000

Did Mirascope exist before MCP? MCP was announced in November, 2024.

New comment by lordswork in "Republican Congressman Introduces Bill Seeking Abolishment of OSHA"

lordswork — Thu, 06 Feb 2025 14:01:24 +0000

Some statistics on US health and safety before and after OSHA:

https://www.perplexity.ai/search/can-you-give-me-an-apples-t...

New comment by lordswork in "How to scale your model: A systems view of LLMs on TPUs"

lordswork — Tue, 04 Feb 2025 20:34:08 +0000

This has been my bible for performance work internally at Google. Kind of surprised they released it publicly, but I guess they removed all the Gemini-specific details.