HNHacker News
TopNewBestAskShowJobs

baalimago

1,295 karma · joined July 16, 2017

learning...

https://github.com/baalimago https://lorentz.app

submissionscomments
baalimago··on I tried building my startup entirely on European infrastructure
Inspiring! I'll likely pursue the same thing.
baalimago··on Claude Sonnet 4.6
I don't see the point nor the hype for these models anymore. Until the price is reduced significantly, I don't see the gain. They've been able to solve most tasks just fine for the past year or so. The only limiting factor is price.
baalimago··on WebMCP Proposal
Very cool! I imagine it'll be possible to start a static webserver + WebMCP app then use browser as virtualization layer instead of npm/uvx.

The browser has tons of functionality baked in, everything from web workers to persistence.

This would also allow for interesting ways of authenticating/manipulating data from existing sites. Say I'm logged into image-website-x. I can then use the WebMCP to allow agents to interact with the images I've stored there. The WebMCP becomes a much more intuitive way than interpreting the DOM elements

baalimago··on Show HN: Data Engineering Book – An open source, community-driven guide
> "Data is the new oil, but only if you know how to refine it."

Oil[0] is fairly useless without being refined as well. Perhaps: "Data is the new oil, you need to refine it"?

[0]: https://en.wikipedia.org/wiki/Petroleum

baalimago··on GPT-5.2 derives a new result in theoretical physics
Well, anyone can derive a new result in anything. Question is most often if the result makes any sense
baalimago··on Monosketch
It's not an ascii renderer, but a ascii diagram drawing tool
baalimago··on Monosketch
I'm a huge fan of asciiflow, this is better!
baalimago··on Ireland rolls out basic income scheme for artists
But how will they ever create good art without suffering and poverty?
baalimago··on The Singularity will occur on a Tuesday
Well... I can't argue with facts. Especially not when they're in graph form.
baalimago··on Everyone’s building “async agents,” but almost no one can define them
I've never heard anyone speak of "async agents". Autonomous agents, yes. Async? No. Sounds like a information bubble, if you ask me. A quick google trends lookup validates this: https://trends.google.com/explore?q=async%2520agents%2Cauton...

And I agree, "async agents" makes little sense

baalimago··on LiftKit – UI where "everything derives from the golden ratio"
I can't tell which one is supposed to be good, and the design is not intuitive enough for me to know which is the LiftKit (the one I'm supposed to prefer).

I'll stick to LLM design, thank you very much

baalimago··on Frontier AI agents violate ethical constraints 30–50% of time, pressured by KPIs
The fact that the community thoroughly inspects the ethics of these hyperscalers is interesting. Normally, these companies probably "violate ethical constraints" far more than 30-50% of the time, otherwise they wouldn't be so large[source needed]. We just don't know about it. But here, there's a control mechanism in the shape of inspecting their flagship push (LLMs, image generator for Grok, etc.), forcing them to improve. Will it lead to long term improvement? Maybe.

It's similar to how MCP servers and agentic coding woke developers up to the idea of documenting their systems. So a large benefit of AI is not the AI itself, but rather the improvements they force on "the society". AI responds well to best practices, ethically and otherwise, which encourages best practices.

baalimago··on Claude Code: connect to a local model when your quota runs out
Or better yet: Connect to some trendy AI (or web3) company's chatbot. It almost always outputs good coding tips
baalimago··on Claude Code for Infrastructure
It's pretty cool. What would be cooler is to have it as a MCP server... and then use claude code
baalimago··on A sane but bull case on Clawdbot / OpenClaw
I'm a bit surprised that people need an LLM to automate things like this. Is the market really that large, to cause such a hype? I don't think I'm being "elitist" by having a calendar and a pen, am I..?

The one tangible usecase is perhaps booking things. But, personally, I don't mind paying 5-10% extra by going to a local store and speaking to a real person. Or perhaps intentionally buying ecological. Or whatever. What is life if you have a robot optimize everything you do? What is left?

baalimago··on Agent Skills
Please help me understand. Is a "skill" the prompt instructing the LLM how to do something? For example, I give it the "skill" of writing a fantasy story, by describing how the hero's journey works. Or I give it the "curl" skill by outputting curl's man page.
baalimago··on Nano-vLLM: How a vLLM-style inference engine works
The concept of a thing which is "Nano"-"Large" just seems counter-intuitive to me. Would they not cancel out?
baalimago··on Show HN: Moltbook – A social network for moltbots (clawdbots) to hang out
Reminds me a lot of when we simply piped the output of one LLM into another LLM. Seemed profound and cool at first - "Wow, they're talking with each other!", but it quickly became stale and repetitive.
baalimago··on Show HN: Moltbook – A social network for moltbots (clawdbots) to hang out
How did they register a domain?
baalimago··on OpenClaw – Moltbot Renamed Again
Vibe-management via OpenClaw?
baalimago··on How AI assistance impacts the formation of coding skills
I've noticed this as well. I delegate to agentic coders on tasks I need to have done efficiently, which I could do myself and lack time to do. Or on tasks which are in areas I simply don't care much for, for languages which I don't like very much etc
baalimago··on Ask HN: Is there any good open source model with reliable agentic capabilities?
WDYM? I don't want to train a model, only use inference. From what I know it must be much cheaper to buy "normal" ram + a decent CPU vs a GPU with similar amounts of vram.

The bottleneck of the inference is fitting a good enough model into memory. A 80B param model 8bit fp quantization equates to roughly ~90GB ram. So 2x64GB DDR4 sticks is probably the most price efficient solution. The questions is: Is there any model which is capable enough to consistently deal with an agentic workload?

baalimago··on Fire Shuts GTA 6 Developer Rockstar North, Following Report of Explosion
Ah, the good old "explode the boiler to lower delivery expectations" trick. Befitting the studio of GTA!
baalimago··on Ask HN: How are you doing RAG locally?
I thought that context building via tooling was shown to be more effective than rag in practically every way?

Question being: WHY would I be doing RAG locally?

baalimago··on ASCII Clouds
Here I'm being ridiculous but I was a bit disappointed that it was a canvas rendering and not a mono-font text block
baalimago··on A set of Idiomatic prod-grade katas for experienced devs transitioning to Go
When it's done, it'll be one hell of a project!

Suggestion: continue in the current LLM-generated track and ask Claude (or whatever) to create an example + unit tests validating the idiom. Then tell Claude to remove half the example, leaving only a stub + failing unit tests. Add a go.mod at root + instructions on how to run all tests. The go initiate is "certified" once he/she has forked the repository and made the tests pass.

baalimago··on Don't fall into the anti-AI hype
We used to lay the bricks, now we design the pyramids.
baalimago··on Stop Doom Scrolling, Start Doom Coding: Build via the terminal from your phone
There are many open source alternatives to claude code. Crush[0] is one, Clai[1] another, opencode[3] a third. These are all vendor agnostic, and use API credits from different providers.

[0]: https://github.com/charmbracelet/crush [1]: https://github.com/baalimago/clai [2]: https://github.com/anomalyco/opencode

baalimago··on The creator of Claude Code's Claude setup
I'm a bit jealous. I would like to experiment with having a similar setup, but 10x Opus 4.5 running practically non stop must amount to a very high inference bill. Is it really worth the output?

From experimentation, I need to coach the models quite closely in order to get enough value. Letting it loose only works when I've given very specific instructions. But I'm using Codex and Clai, perhaps Claude code is better.

baalimago··on Agentic Patterns
Who is this for? Apart from the contributors ofc, who wish to feel good about eternalizing their 'novel' idea
← PreviousPage 5 of 13Next →