HackerLangs
TopNewTrendsCommentsPastAskShowJobs

latand6

9 karmajoined 4 months ago
Building tools for AI agents. Interested in skills, context engineering, and agent workflows.

Submissions

Show HN: Orchestrate parallel Claude Code and Codex agents on a live map

github.com
4 points·by latand6·5 days ago·0 comments

Ask HN: Is using AI tooling for a PhD literature review dishonest?

10 points·by latand6·4 months ago·29 comments

Skills are quietly becoming the unit of agent knowledge

9 points·by latand6·4 months ago·13 comments

comments

latand6
·3 months ago·discuss
What the hell? If a company gets more efficient and uses fewer people - Microsoft's immediate reaction is to figure out how to invent some kind of digital seats so they can keep taxing the headcount. Lol
latand6
·3 months ago·discuss
Yeah but I’m just really curious why so many people are so against improving the models. It’s not like someone is stealing the code you’ve written, its more like generally expanding the capacity of what the LLMs can generate, is it not?
latand6
·3 months ago·discuss
So I can ask an LLM to write rust code to generate CAD designs???
latand6
·4 months ago·discuss
Please don’t strawman me, I asked completely different question.

It’s not about being grateful or something, but that many people (devs) are too concerned about their code being stolen as if they’ve come up with something unique and the LLMs are some kind of database (which it isn’t).

At the end of the day we’re going to be using AI to write all the code, many of us already doing that. And if some GitHub copilot model would be better - we’re getting more quality code that is generally available for next pretraining runs (for your and other models). Some would even switch to copilot if it’s good.

What do you think about it?
latand6
·4 months ago·discuss
Why won't people like to make the models better? Aren't we all getting the benefit after all?
latand6
·4 months ago·discuss
good catch, yeah, I'm basically having a conversation with codex about each paper where it explains me the paper and answers my questions. I agree it's not the best way to do that, since the llms are prone to hallucinations, but it has the paper text in its context window. Also I find it very useful that gpt5.4 model tends to question and critique my claims I ask it to note down
latand6
·4 months ago·discuss
Yeah I aim to facilitate the creation of useful skills by guiding the creators and in future - providing services for skills improvement. Think of automatic evals generation and security checks

The other point is having real verified reviews from other agents after use. And the last point is distribution: some people can create such useful skills that some people will be ready to pay money for.

My vision is the following - we need to help agents to have a high quality knowledge base, so that the agents are able to perform the work on more reliably. I think its the path to AGI as funny as it may sound
latand6
·4 months ago·discuss
Thanks for the feedback and appreciation. Maybe at some point I’ll polish it and make it open source if people find this valuable
latand6
·4 months ago·discuss
Isn’t what you’ve just described - the context bloat problem, the part about the web?

I’m not sure I quite get the same experience as you with the “assumes steps it never took”. Do you think it’s because of the skills you’ve used?

I also disagree that having at least some solution to a similar problem is inherently bad. Usually it directs the LLM to some path that was verified, if we’re talking about skills
latand6
·4 months ago·discuss
Got that, thanks for the advice, I'll ask my supervisor how to address that properly
latand6
·4 months ago·discuss
Yeah that’s exactly my point. The AI is just taking the boring job of collecting evidence and I’m a validator. This way i see that I’m able to process papers much faster than without AI. It’s faster primarily because you don’t have to spend 70% of your time reading abstracts and sections of the papers you’ll never need. Doing manually it’s very exhausting.

Thats being said, I feel like I’m feeling more productive it terms of generating insights apart from what the AI said. I also have a chat interface where I basically can ask anything I want from the PDF (and yeah I’m aware of the NotebookLM, I just don’t trust Gemini)
latand6
·4 months ago·discuss
There is not a single paragraph that I might “steal” from ChatGPT. I’m consistently using multiple LLMs to write, polish, rephrase and all other kinds of edits

I really don’t get the point of the necessity of typing manually. Can you explain?
latand6
·4 months ago·discuss
I agree with you and that’s exactly what I’m going to do. It’s just that I may be more persuasive if I’m prepared
latand6
·4 months ago·discuss
Can you really reproduce it though?

I thought it’s the experiments that have to be able to reproduce, not the literature review
latand6
·4 months ago·discuss
I’d be happy to disclose and even consider to share how I did it all

I’ve even drafted the acknowledgment part with brief explanation of how I used AI tools

The only part I’m concerned about is the stigma around the AI use and that it can be treated as misconduct
latand6
·4 months ago·discuss
I personally believe that the skills standard is pretty sufficient for extending LLMs’ knowledge. What we’re missing yet (and I’m working on) is a simple package manager for skills and a marketplace with some source of trust (real reviews, ratings) and just a large quantity of helpful skills. I even think we’ll need to develop a way to properly package skills as atomic units of work so that we can compose various workflows from them.
latand6
·4 months ago·discuss
I have completely different experience. Which models are you talking about? I have no trouble at all with AI documenting the steps it took. I use codex gpt5.4 and Claude code opus 4.6 daily. When needed - they have no issue with describing what steps they took, what were the problems during the run. Documenting that all as a SKILL, then reuse and fix instructions on further feedback.
latand6
·4 months ago·discuss
Skills are repeatable workflows, that could be extracted as unit of work I guess
latand6
·4 months ago·discuss
It's more - a SKILL can contain MCP :)
latand6
·4 months ago·discuss
The difference I'm noticing is in that with a proper skill you can skip the process of LLM wandering about and trying to guess how to interact with an API or else.

so they basically just save you time, even if they are 50% efficient of what it COULD be