Hacker News: swframe2

New comment by swframe2 in "I built a 516-panel financial terminal in 3 weeks using AI"

swframe2 — Wed, 01 Apr 2026 04:55:43 +0000

Reminds me of the palantir clone: https://www.youtube.com/watch?v=rXvU7bPJ8n4

This is the year when solo software firms start to dominate.

New comment by swframe2 in "I'm OK being left behind, thanks"

swframe2 — Fri, 20 Mar 2026 17:20:39 +0000

I've noticed 2 very obvious trends. The high-performers who previously wrote the most PRs are now using AI the most aggressively and the number PRs they produce has almost doubled. The other trend is that large teams are being split into smaller teams that work on new products. I hope the trend is more projects and less grunt coding. (I know the ai coders are not yet L6 but I suspect they will achieve L3-L5 this year).

New comment by swframe2 in "It Took Me 30 Years to Solve This VFX Problem – Green Screen Problem [video]"

swframe2 — Wed, 18 Mar 2026 01:53:07 +0000

The model in this repo seems pretty good: https://github.com/xuebinqin/DIS

New comment by swframe2 in "Claude Code wiped our production database with a Terraform command"

swframe2 — Fri, 06 Mar 2026 19:35:41 +0000

I suspect we need to build MCP servers that prevent destructive commands. For example, we need a "bash" tool doesn't invoke /usr/bin executables directly. The agent should think it is invoking a unix command but those commands are proxies that prevent destructive operations with no ability for an agent to circumvent the restrictions. If there isn't a MCP server for your specific setup/need, building one just for your need should be your first step.

New comment by swframe2 in "Understanding Neural Network, Visually"

swframe2 — Fri, 06 Feb 2026 23:31:25 +0000

This Welch Labs video is very helpful: https://www.youtube.com/watch?v=qx7hirqgfuU

New comment by swframe2 in "Dell UltraSharp 52 Thunderbolt Hub Monitor"

swframe2 — Fri, 16 Jan 2026 19:42:42 +0000

I use 2 32" 4K which cost about $800 for both monitors. The small gap between the monitors is annoying but I can't really justify paying $2k more. Also there is a samsung dual 4k that is about the same price as the dell.

Moving my head to see everything doesn't bother me. I also have a setup with 3 32" 4k which I find a little too wide but in that setup 1 monitor connects to different computer.

New comment by swframe2 in "DeepSeek-v3.2: Pushing the frontier of open large language models [pdf]"

swframe2 — Tue, 02 Dec 2025 16:43:21 +0000

The AI market is hard to predict due to the constant development of new algorithms that could emerge unexpectedly. Refer to this summary of Ilya's opinions for insights into the necessity of these new algorithms: https://youtu.be/DcrXHTOxi3I

DeepSeek is a valuable product, but its open-source nature makes it difficult to displace larger competitors. Any advancements can be quickly adopted, and in fact, it may inadvertently strengthen these companies by highlighting weaknesses in their current strategies.

New comment by swframe2 in "Denmark's government aims to ban access to social media for children under 15"

swframe2 — Fri, 07 Nov 2025 19:22:10 +0000

There is an interesting exploration of human networks discussed in this veritasium video: https://www.youtube.com/watch?v=CYlon2tvywA

Basically, when network connectivity increases, the "bad" nodes can overwhelm the "good" nodes. The other ideas discussed are really interesting; well worth watching.

New comment by swframe2 in "DOJ seizes $15B in Bitcoin from 'pig butchering' scam based in Cambodia"

swframe2 — Wed, 15 Oct 2025 16:31:37 +0000

If DOJ knows the destination wallets can they trace the transactions ...

into the wallets back to the victims?

from the wallets forward to the others working with the scammer?

New comment by swframe2 in "Show HN: FocusStream – Focused, distraction-free YouTube for learners"

swframe2 — Sat, 20 Sep 2025 16:26:57 +0000

I think those of us who want youtube without the distractions should start a campaign to convince google to make https://www.youtube.com/learning better. I think even tweeting about it so that our efforts are reported by large news outlets would work. If there aren't enough users asking for this feature, we will be ignored. Someone needs to build a website that coordinates our efforts.

New comment by swframe2 in "A staff engineer's journey with Claude Code"

swframe2 — Tue, 02 Sep 2025 20:56:01 +0000

Preventing garbage just requires that you take into account the cognitive limits of the agent. For example ...

1) Don't ask for large / complex change. Ask for a plan but ask it to implement the plan in small steps and ask the model to test each step before starting the next.

2) For really complex steps, ask the model to write code to visualize the problem and solution.

3) If the model fails on a given step, ask it to add logging to the code, save the logs, run the tests and the review the logs to determine what went wrong. Do this repeatedly until the step works well.

4) Ask the model to look at your existing code and determine how it was designed to implement a task. Some times the model will put all of the changes in one file but your code has a cleaner design the model doesn't take into account.

I've seen other people blog about their tricks and tips. I do still see garbage results but not as high as 95%.

New comment by swframe2 in "AGI Is Still 30 Years Away – Ege Erdil and Tamay Besiroglu"

swframe2 — Thu, 17 Apr 2025 22:33:50 +0000

The Anthropic's research on how LLMs reason shows that LLMs are quite flawed.

I wonder if we can use an LLM to deeply analyze and fix the flaws.

New comment by swframe2 in "Obituary for Cyc"

swframe2 — Wed, 09 Apr 2025 05:23:23 +0000

What do you think of the recent anthropic research on how LLMs reason? It is clear from their shallow analysis that LLMs have very serious reasoning weaknesses. I wonder if those weaknesses can be "addressed" if we build LLMs that can do deeper analysis and use RL to self-improve. LLMs improving LLMs would be a very impressive step towards AGI.

New comment by swframe2 in "No elephants: Breakthroughs in image generation"

swframe2 — Wed, 09 Apr 2025 05:12:17 +0000

I'm hoping this alternative image prompt preprocessing technique gets more attention:

https://art-msra.github.io/

Basically, the user's image prompt is converted to a several prompts to generate parts of the final image in layers which are combined. The layers are still available so that edits can cleanly update one section without affecting the others.

New comment by swframe2 in "OpenAI: Out of Ideas"

swframe2 — Mon, 03 Feb 2025 17:11:12 +0000

I saw an interesting quote from the deekseek CEO:

"When tackling a task, experienced people might reflexively tell you 'this is how it should be done,' while those without experience will experiment repeatedly, think deeply about the best approach, and ultimately find a solution tailored to the actual circumstances."

I do not think that OpenAI is out of ideas, but I do believe that large businesses have difficulty overcoming the innovator's dilemma. In addition to big businesses, there are also many small and very smart companies that are using investors' over exuberance to their advantage. Nevertheless, there are enough people trying that some are likely to find a way to develop higher-quality models at a lower cost.

New comment by swframe2 in "Tesla Paid Zero Federal Income Tax in 2024, Despite $2.3B in Income"

swframe2 — Sat, 01 Feb 2025 00:05:02 +0000

trump spreads his income perfectly across all his LLCs. Their expenses always exactly match their income to the penny. I wonder why he is able to do that?

New comment by swframe2 in "Microsoft to force Windows 11 24H2 on Home and Pro users"

swframe2 — Wed, 22 Jan 2025 18:29:15 +0000

Please note that the 24H2 update will remove the Mixed Reality Portal and Windows Mixed Reality support. If you have a VR headset it might not work after the update. There are articles that claim that steamvr is still supported but it didn’t work for me.

New comment by swframe2 in "Hunyuan3D 2.0 – High-Resolution 3D Assets Generation"

swframe2 — Wed, 22 Jan 2025 05:44:07 +0000

When you run their demo locally, there are two places that trigger a warning that the code loads the weights unsafely. To learn more about this issue, search "pytorch model load safety issues" on Google.

New comment by swframe2 in "Hunyuan3D 2.0 – High-Resolution 3D Assets Generation"

swframe2 — Wed, 22 Jan 2025 05:30:37 +0000

I tried using Hunyuan3D-2 on a 4090 GPU. The Windows install encountered build errors, but it worked better on WSL Ubuntu. I first tried it with CUDA 11.3 but got a build error. Switching to CUDA 12.4 worked better. I ran it with their demo image but it reported that the mesh was too big. I removed the mesh size check and it ran fine on the 4090. It is a bit slow on my i9 14k with 128G of memory.

(I previously tried the stability 3d models: https://stability.ai/stable-3d and this seems similar in quality and speed)

New comment by swframe2 in "Ask HN: Let's say I'm not as smart as I think, how do I stop acting stupid?"

swframe2 — Sun, 19 Jan 2025 22:06:19 +0000

Just accept that we all are part nature and part nurture. I suspect your good friends accept you as you are; some probably really like you as you are. It is also kind of relative; Hang out with the some people and you will always feel stupid or smart. I think you should focus on doing things that you and others find very interesting. There is a famous line from Dune that basically says "fear is the mind-killer"; generalize that to "thinking too negatively about yourself can lead to poor outcomes".