HNHacker News
TopNewBestAskShowJobs

lucrbvi

337 karma · joined January 10, 2026

https://lucrbvi.com
submissionscomments
lucrbvi··on Show HN: Adam – An embeddable cross-platform AI agent library
Cool but why would anyone write an agent in C? Since the language is verbose it seems to be a painful choice to use C for this task.
lucrbvi··on DeepSeek v4
They have added a lot of optimization focussing on the KV-cache, so they can have a much larger window without eating all the VRAM.

The 1M window might be usable, but it will probably underperform against a smaller window of course.

lucrbvi··on Stripe's Payment APIs: the first 10 years (2020)
Mollie seems to only provide services to business based in European Economic Area, Switzerland and the UK [0], so yes?

[0]: https://help.mollie.com/hc/en-us/articles/115002116105-Can-I...

lucrbvi··on Stripe's Payment APIs: the first 10 years (2020)
Mollie might be a direct competitor
lucrbvi··on Codex for almost everything
Is there anyone that feels that LLMs are wrong for computer use? It's like robotic, if find LLMs alone are really slow for this task
lucrbvi··on Claude Opus 4.7
Some people are speculating that Opus 4.7 is distilled from Mythos due to the new tokenizer (it means Opus 4.7 is a new base model, not just an improved Opus 4.6)
lucrbvi··on Why Claude Mythos is not AGI
Hi! I share my first blog post ever about the definition on AGI following the annoucement of Claude Myhtos Preview.

I hope some of you might found this interesting.

lucrbvi··on TurboQuant: Redefining AI efficiency with extreme compression
Sounds like Multi-Head Latent Attention (MLA) from DeepSeek
lucrbvi··on Astral to Join OpenAI
I wouldn't be surprised if Vercel were bought by Anthropic/OAI (but maybe it would be too expensive?)
lucrbvi··on Astral to Join OpenAI
This is a weird pattern accross OpenAI/Anthropic to buy startups building better toolings.

I don't really see the value for OAI/Anthropic, but it's nice to know that uv (+ ty and many others) and Bun will stay maintained!

lucrbvi··on Meta acquires Moltbook
I share the feeling; but people using it are mostly non-technicals (despite the 50+ config files lol) and are just runing it constantly to do random things.

But a message bot + Claude Code/Codex would be the better version

lucrbvi··on [dead]
The whole article feels like an ad
lucrbvi··on Ask HN: Maintainers, do LLM-only users often clutter your issues/PRs?
The "egg" system seems really good!

It will maybe solved soon if we train yet another neural network on scanning GitHub activities; but by also adding other forges like codeberg, gitlab, self-hosted forgejo, etc... to not lock non-github users out

Still really good idea!

lucrbvi··on Don't trust AI agents
Why does OpenClaw have 800,000+ lines of code?? Isn't it just a connector for LLM APIs and other tools?
lucrbvi··on Show HN: Microgpt is a GPT you can visualize in the browser
It's just hallucinating training data, the model is very small so it cannot be useful at all
lucrbvi··on Asking the best LLMs to design a post-AGI civilization
The name of the article is misleading, probably some clickbait since it's talking about ASI

Still, it's a good reminder that AGI is not a 'superintelligent' entity but just a _general_ intelligence

lucrbvi··on Compiling models to megakernels
Yes, in "runtime optimization" the model is just a computation graph so we can use a lot of well known tricks from compilation like dead code elimination and co..
lucrbvi··on I scanned 2,500 Hugging Face models for malware/issues. Here is the data
You should know that there is already a solution for this, SafeTensors [0].

But it may be a nice tool for those who download "unsafe" models

[0]: https://huggingface.co/docs/safetensors/index

lucrbvi··on Claude's new constitution
It's just Anthropic being Anthropic, nothing new
← PreviousPage 2 of 2