paradite's comments

On: Void: Open-source Cursor alternative

[paradite]

Missing OpenAI Codex cli

Also missing a class of non-IDE desktop apps like 16x Prompt and Repo Prompt.

[underlines → paradite]

Thanks. I added codex.

Though, since I specifically mentioned agentic, I wanted to exclude non-agentic tools like prompt builders and context managers that you linked. :)

Reason being: my idea of agents is to generalize well enough, so the need for workflow based apps isn't needed anymore.

During discovery and planning phase, the agents should traverse the code base with a retrieval strategy packaged as a tool (embedded search, code-graphs, ...) and then add that new knowledge to the plan before executing the code changes.

[paradite → underlines]

I don't think it's a black and white distinction between agentic and non-agentic tools. Not to mention tools are constantly evolving and changing.

For example, Cursor a year ago was not agentic at all. GitHub Copilot only recently added agentic features.

I also think the end game for an agentic tool would not an IDE, because IDE was designed for human workflows, not agents.

I wrote about this topic a while ago and made a classification that's probably a bit outdated, but still relevant: https://prompt.16x.engineer/blog/ai-coding-l1-l5

On: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?

[paradite]

There are actually a lot of tools that do this:

https://prompt.16x.engineer/cli-tools

On: Ask HN: How much better are AI IDEs vs. copy pasting into chat apps?

[paradite]

I built a tool that helps with copy pasting code into chat UI called 16x Prompt.

https://prompt.16x.engineer/

It is used by quite a lot of people. So the problem is definitely there.

The app supports API integration as well. From usage stats, still there are more people using the copy pasting flow instead of API flow.

I suspect it is because people are already have a subscription so they can basically use that for free, versus via API where they have to pay.

With that said, Cursor's $20/month unlimited usage is really too good to miss. I will wait for it to end soon.

[ssd532 → paradite]

I use 16x for the copy-paste workflow. Really useful tool. Thanks.

On: OpenAI for Countries

[paradite]

I'm getting so much sci-fi vibes from this post.

I've read so many sci-fi stories where big tech corporations have similar control over people as countries. Now we are actually heading there.

I'm both excited and a bit worried about the future.

[nicbou → paradite]

Heading there? Facebook has been a kingmaker for a decade. Musk runs DOGE. Most big companies can bully smaller administrations when they feel the need.

On: Claude's system prompt is over 24k tokens with tools

[paradite]

It's kind of interesting if you view this as part of RLHF:

By processing the system prompt in the model and collecting model responses as well as user signals, Anthropic can then use the collected data to perform RLHF to actually "internalize" the system prompt (behaviour) within the model without the need of explicitly specifying it in the future.

Overtime as the model gets better at following its "internal system prompt" embedded in the weights/activation space, we can reduce the amount of explicit system prompts.

On: We identified a North Korean hacker who tried to get a job

[paradite]

I wonder what if this is just a decoy to get the more sophisticated candidate in.

On: Qwen3: Think deeper, act faster

[paradite]

I can't belive Ollama haven't fix the context window limits yet.

I wrote a step-by-step guide on how to setup Ollama with larger context length a while ago: https://prompt.16x.engineer/guide/ollama

TLDR

  ollama run deepseek-r1:14b
  /set parameter num_ctx 8192
  /save deepseek-r1:14b-8k
  ollama serve

On: Qwen3: Think deeper, act faster

[paradite]

Thinking takes way too long for it to be useful in practice.

It takes 5 minutes to generate first non-thinking token in my testing for a slightly complex task via Parasail and Deepinfra on OpenRouter.

https://x.com/paradite_/status/1917067106564379070

Update:

Finally got it work after waiting for 10 minutes.

Published my eval result, surprisingly non-thinking version did slightly better on visualization task: https://x.com/paradite_/status/1917087894071873698

On: Ask HN: What are you working on? (April 2025)

[paradite]

https://eval.16x.engineer/ - 16x Eval: A desktop GUI app to evaluate prompts and models

With 16x Eval, you can manage your prompts, contexts, and models in one place, locally on your machine, and test out different combinations and use cases with a few clicks.

On: Wikipedia’s nonprofit status questioned by D.C. U.S. attorney

[paradite]

Seems like the story of Stackoverflow.