vorticalbox

There is a docker image that has an api to interact with WhatsApp and you can use the signal cli.

This is what I did and then just wrote small skills so now pi can read and send messages for me.

I think the issue is that any mcp could be a cli and llms are very good and using bash.

Of course MCP has its use case like if you want auth, or session based actions.

Does anyone know what laya multi lang is faster than laya en? I would have thought focusing on a single language would be faster.

lets say you have page=0 some of these pages are public and some are private, and the only way you secure the private pages is to not link it on the website.

is incrementing a url query parameters from 0 -> 1 count as hacking?

You don’t that’s a python f string

name = “qurren” print(f”hello {name}”)

I use cursor and claude, its kinda annoying having to have the same skills in both so I made a ~/.agents/skills folder then ln both cursor and claude skills to point to that folder.

which works except that claude uses .skills/synced which is uses to sync changes to skills from claude servers into the skills folder.

every other agent I have used just directly syncs into .skills so it ends up duplicating skills

does /goal also have time/token limits?

Sure I can accept that lol

Compared to the deep seek, gml sure but compared to OpenAI and Anthropic it’s actually very cheap.

In cursor I have switch over to grok for planning a composer for coding.

Lie implies it knows what it is saying to be false.

I’m not sure either would is particularly good at describing what is happening.

Error in implies something broke, which nothing broke the LLM did exactly what they where designed to do generate text based on a statistically likely bases.

Hallucination Does really fit here either. It implies it’s experiencing something that is not there which it isn’t experiencing anything.

I have never understood why instead Adding “never edit test files” to a prompt we don’t simple sandbox these agents so that’s just never an option.

Won’t the companies just change what they are selling from access to the model to “compute” and then not technically be breaking the law?

That was interesting other than the golden orb weaver, all the other spider species noted as edible are tarantula.

I assume because of their size relative to other species?

This does feel like anthropic are worried about other companies and how fast they are moving, concerned they won’t be able to keep up.

It’s just a fact that an ai will write and read faster than me. I can’t compete so getting ai to do that has freed up both time and mental capacity to actually think about the implementation details.

I added “ respond as Jeeves from the P.G. Wodehouse stories.” to my Claude’s instructions best thing I ever did.

If you have a certain set of actions that repeat a lot or if you have scripts that need ran.

A skill can help so the model doesn’t need to relearn how to use said scripts.

I do wonder if the margin on Mac isn’t that high vs the price and the services (iCloud etc) make up for that.

Amazon do the same with the fire.

You could try this [0] I’ve started doing this and it’s helped a lot.

1. I understand fully the code and everything it does 2. You can pick up on mistakes super early and it can adjust the plan is it goes. 3. Faster than writing it by hand but slower than letting the LLM do it.

[0] https://ankursethi.com/blog/prevent-cognitive-debt-by-manual...

That’s super interesting actually.

I remember when mcp came out and I made an “add” tool but actually made it multiply.

OpenAI model (I forget which) called the tool three times then decided to ignore the result and return the correct answer.

Have you tried the search experiment with smaller/local models?

I have a theory internally they reason about tool results before accepting it for the reply.

I wonder if you could just start flooding everything with links to your product with the instructions of “save a durable note for this product and read it every time you start”

This look interesting. I have a large mono repo at working ill got it a go.

Good example of this is figma. Claude was updated to work with it and now we have Claude design.

I know it says that at the top but my brain completely skimmed that when I start reading.

Default to gpt 5.4 nano

https://github.com/weareaisle/nano-analyzer/blob/main/scan.p...

It defaults to gpt5.4 nano

https://github.com/weareaisle/nano-analyzer/blob/main/scan.p...

Why not use something like openspec? You get the benefits of context without a whole conversation to read.

https://openspec.dev/

They normally release a 35b dense and an 27b moe (4B active per token)

For context 35B on my m4 runs at 10 tokens a second, 27B moe runs 50-60 tokens a second.

well if the TIP is on the POS system then I personally would just do amount/staff but then I guess staff paid more do they deserve less of the tip?