robotswantdata

I believe it

Love meshtastic. There’s something about the setup friction that has the vibe of early internet, select community, high signal, nobody trying to monetize your attention.

Slop as a letter is a thing already https://www.axidraw.com/

Don’t mention the cs case gambling

Local hardware catching up doesn’t matter if the thing worth having never leaves the building. Enterprise services are hard, moat is in distribution and know how.

History suggests otherwise. railroads, telecoms, search all consolidated. The natural equilibrium for transformative infrastructure is winner take all. AGI/ASI won’t be different but will be nearly every vertical and governments will legislate too little too late.

If you’ve gone to the trouble of setting up Ableton MCP, you’ve already worked harder than Suno requires to make a banger

I want the frontier on prem to be true but IMO not good enough yet unless async.

What started as all-you-can-eat $50 buffet has quietly become a $6k bill, frontier models that don’t ship your codebase to Beijing don’t come cheap anymore.

IMO assisted coding (auto complete style) has more flow state than the old days of getting stuck on obscure bugs (as satisfying as those were to crack).

Full agent coding however is the complete opposite, you’re in constant damage control of a junior who moves fast and breaks everything. They’ve got better but still do dumb mistakes.

lot of engineers are discovering firsthand what it’s like to manage a team of eager but useless employees. Not fun at all

Try this https://soundcloud.com/jochempaap/07-01-2010-speedy-j-bunker...

This was a colleague favourite for flow state time

See http://arxiv.org/abs/2602.16800

And http://news.ycombinator.com/item?id=33755016

Also http://github.com/antirez/hnstyle

Glhf

When disconnected all services immediately stop. So no big bills.

Do yourself a favour and automate unlinking the billing account. Set it to fire when your budget is hit or whatever your risk tolerance is.

Yes nuclear option, but I’ll take an hour down time over a $100k unexpected bill

Max Schrems has entered the chat.

I’d go back. The BBS and dial up days look cosy

Now it’s owned by corporates and everyone is using bloated JS frameworks.

They found a nail in a small bucket of sand, vs mythos with the entire beach reviewed.

It’s as if it gives up, I respond keep going with original plan, you can do it champ!

Anthropic when they scrape the entire internet without permission: I sleep

Anthropic when their own source code ends up on GitHub: Real s**

Seems crazy that anyone (startups and buyers) would trust these guys for audit.

Shows the “compliance theatre” of what SOC2 has become

The code smells very vibe coded in a bad way, sorry OP.

Interesting to use MCP for GRC but probably the most risk adverse to MCP segment to build in!

The security ratings in the readme are hilariously wrong

Keep seeing similar mistakes with vibe coded AI & MCP projects. Even experienced engineers seem oblivious to this attack vector

Why are you using Ollama? Just use llama.cpp

brew install llama.cpp

use the inbuilt CLI, Server or Chat interface. + Hook it up to any other app

Forget all the vibe coded slop or Ollama. Lemonade is the real deal and very good, been using about a year now.

AMD are doing gods work here

Scrape normally collect emails, if no email seen take screenshot and OCR OCR is cheap and REGEX is cheap

How does that work if the scraper takes a screenshot to feed to a LLM or OCR?

Feels 100% vibe coded in a bad way.

Llama.cpp already has KV compression and one of the turbo quant PRs will get merged at some point.

If you don’t care about the fancy 3 bit, the q8 KV compression is good enough! Don’t bother with q4

./build/bin/llama-server -m model.gguf \ --cache-type-k q8_0 \ --cache-type-v q8_0 \ -c 65536

Etc

“Just use Postgres” greybeards right again. Looking forward to giving this a go soon

Why are people still using Ollama? Serious.

Lemonade or even llama.cpp are much better optimised and arguably just as easy to use.

Costs a lot? It’s a bargain for globally resilient infrastructure.

db-f1-micro is about $10pm inc storage for something that just works and can scale, be shifted on prem etc. you can run all your vibe coded slop on one instance.

Google have you covered: https://www.youtube.com/watch?v=Kl8ig2BtLAY