HackerTrans
TopNewTrendsCommentsPastAskShowJobs

sgc

3,151 karmajoined 12 tahun yang lalu
Busy with a lot of things, but my favorite is CatholicLibrary.org

comments

sgc
·kemarin dulu·discuss
It seems like they are actually using the subscription providers' respective cli tools and managing context for them. In which case I believe it is not against the ToS any more than invoking codex cli from a custom python script would be? I personally cannot find an openai-hosted clarification, just on hn and x.
sgc
·kemarin dulu·discuss
Can anybody share a tested system prompt they use for general coding tasks in pi?
sgc
·kemarin dulu·discuss
I have one core complex task where there are a number of simple errors like this. The easiest thing for me was to just have a post-processing script that performs: lint > mark known fail-early results > fix common errors (all formatting or type errors right now) > relint > final pass / fail > pass to next step (retry with tweaks / user in the loop since I don't have the token budget to just blindly keep trying the same thing).
sgc
·8 hari yang lalu·discuss
I ran into a website for work that would let you create a long password, but silently truncate it to 12 characters before saving. Mind boggling.
sgc
·10 hari yang lalu·discuss
Sounds more like they are implementing mass surveillance and reporting whatever the US Gov wants for 'security reasons' back to them.
sgc
·14 hari yang lalu·discuss
Cruise missiles are not general purpose tools, it's obviously not even remotely similar. Virtually everybody reading this could use Mythos immediately to do real work, collectively in virtually every part of the economy.

It's pretty problematic to not make it more widely available at least to US businesses, and there is not even a vetting process to get approved quickly and easily. If this is the new norm, the intended or unintended consequences of this type of gatekeeping will be an unprecedented consolidation of power amongst the largest corporations. Even more than we have seen over the last 20 years.
sgc
·17 hari yang lalu·discuss
What I find impossible to judge is whether me choosing the harness that works best for me and the way I like to work will limit the quality of the LLM output.

In this case, given the complexity of LangChain I don't know if it would burn a lot of tokens or confuse the LLMs with context creep due to the large env and tooling compared to something much simpler, or would something much simpler burn a lot of tokens and stutter in execution compared to LangChain, because they have a lot of middleware optimizations that I would have to relearn the hard way? Or are both those strategies off the mark and there is a better tool for the job I am not even thinking about?

It gets a bit expensive in terms of both time/effort and money to experiment on a full workflow rather than specific steps which is quite easy in openrouter, hence my curiosity as to others' experiences.
sgc
·17 hari yang lalu·discuss
I am very curious about this as well. I'm looking for something that does really well with workflows that require 20 plus steps including a couple while loops and user verifications, but also something simple like a chat bot with access to MCP servers and tools. I need to be able to use Gemini directly, openAI directly, and openrouter at various steps.

Right now I am having trouble deciding whether it's better to just write my own harness, or use langchain, or something else.
sgc
·20 hari yang lalu·discuss
I think in most scenarios you don't need to worry so much about kvm ram use, since it looks static but actually it's not and you can over-commit [1]. And of course disk allocation can be dynamic as well. I prefer a lot more security for a bit less flexibility. I am not as ram rich as you are, and still every time I think of my few LXCs, my main thought is 'why did I do that?'.

[1] https://docs.redhat.com/en/documentation/red_hat_enterprise_...
sgc
·21 hari yang lalu·discuss
Since models just output the the most probable tokens and you can never accuse them of doing anything other than making it all up, I would like to see these tests run with a prompt that attempts to mitigate hallucination and finishes with something like: "Telling me that you don't have the relevant information or that the task is impossible is extremely useful to me and a valid answer", and see how much that changes the scoring - as well as the usefulness of the answers. There are so many skills like context7 that can be tweaked to improve these results as well.

In other words, you shouldn't choose the model that hallucinates the least without detailed prompting, since a well-crafted agents.md clause should go a long way to improving output, and almost certainly the top scoring order will be different. To the point that I don't find this type of raw comparison useful beyond maybe 'make sure you test that one with more explicit prompts'.
sgc
·21 hari yang lalu·discuss
The actual research paper:

https://www.sciencedirect.com/science/article/pii/S135041772...
sgc
·22 hari yang lalu·discuss
I *literally* cannot read that yellow text on the white background. I even tried changing the brightness to almost 0, but there is just not enough contrast.
sgc
·22 hari yang lalu·discuss
To check whether I understand how this all works: Wouldn't a 4 bit quant run reasonably well (for that hardware) with far less ram, something like 1.5x the 476gb, or 714gb+ ram?
sgc
·27 hari yang lalu·discuss
This is the first time in terms of model progress where my personal response is: It does not matter to me because the models 6-12 months ago were already good enough for most everything I need to do. I think 95% of dev work is perfectly fine 6 months behind, if that is truly where we are at now with these open models.
sgc
·27 hari yang lalu·discuss
As far as I can tell this type of model requires 640GB+ of memory using FP8. So likely can be run using 320GB+ memory if using FP4 or similar. So that would be 3 Nvidia DGX Sparks, or 12k of hardware. Is that correct? If so, it could make perfect sense for a small business.
sgc
·28 hari yang lalu·discuss
If you wouldn't mind, could you explain a bit what the 248B model is good for, and where it breaks down and you need something better? I hear this take often, but it is always a fleeting remark so I have no idea what the 'useful' looks like - at all.
sgc
·29 hari yang lalu·discuss
You can absolutely do that by using subprocess.run, or use the codex sdk

https://github.com/openai/codex/tree/main/sdk/python
sgc
·29 hari yang lalu·discuss
I thought the most interesting part of the post was that they have an mcp endpoint for bring-your-own agents, and they won't be force feeding ai on anybody. In the security context of the post, they mean that you are responsible if your ai is duped into falling a victim, or tricked to send malicious mail.
sgc
·29 hari yang lalu·discuss
My first daughter I managed to flip the switch for reading through Tintin and other graphic novels. My younger daughter skipped that entirely. She started reading later than the first, but jumped right in to longer full length books that were captivating for her (they were series she had seen her sister read).

I completely agree that we can encourage but reading needs to come naturally to them. You can't force-feed curiosity and passion, which is what reading is all about for young people.
sgc
·bulan lalu·discuss
I was looking at their docs and Burr has agent cookbooks to get started with this, and it can handle multi-machine workflows. Is this not what you were looking for? I am not sure how it integrates and uses skills etc, but it seems like it should work to me.

https://burr.apache.org/docs/examples/agents/