aniceperson

That's great, really. i do many small tools for the enterprise, and i know first hand that you cannot assume they will read the docs or know where to click.

my rpi5 + wireguard + pi.dev is my 'duet'

yep, sw had their own visualization, those platforms were the chewed out version. now with llm, the entry bar is lower; the dinosaur managers at enterprise will have to adapt tho

if I have a Sass platform where the user pays per seat $8 and assess to the llm is a listed feature, the clause do apply.

the comparison does not make sense, steam is doing much more than launching games, including handling a whole windows compatibility layer through proton/wine.

I'm pretty sure it was already available, but now they are expanding the god forsaken things it does?

the era of dual booting linux signed and linux unsigned has started...

having a daemon PID helps for web gui, but may bite in unexpected ways under extensive parallization.

Just ... use systemd nspwan ... stop reinventing the wheel ...

it has all the options you would ever want, and is actually deeply aware of the kernel capabilities.

every day someone comes with a new sandbox solution because they are too lazy to read one page documentation.

for my agents without rw/bash, I gave a memory mcp that is just json entries with some expire dates and priority. works fine and the llm itself defines the meaningful structure. using it to monitor market prices and ci/cd failures.

getting those fixes is simply bumping the kernel build to the latest patch level, the distros must do it in a timely manner. also, roughly only 10% of the affected files are compiled into a kernel image; from this number i would say only 4 needs attention per week. But again, the reasonable approach is simply building the latest patch version

? are you seriously preferring a vibe coded project over the war tested sqlite?

this whole thing is a misunderstanding from legacy docker semantics. you can easily use namespaces in systemd as user in lighter ways, for example, keeping the rootfs but protecting home and binding a private tmpfs, or to bind a completely different rootfs, providing a vm-like experience. Please read the documentation before vibe coding; the name wsl for Linux just shows how lost you are.

you may still need + to forward the job server to other builder https://github.com/rust-lang/cargo/issues/14407

> I see you are using Cadence IP in your project, unfortunately this is not allowed per the terms and conditions and you will be reported to the authorities

Also : create proprietary locked down eda->no data to train models->models suck at it->reach out to ai lab to rl on it -> expect users to pay for eda and the model.

those are openclaw but skip the setup vps step for your regular joe, with the enormous downside of vendor lock-in and low/none customizability.

Of course, my opinion is based on my personal experience + openrouter data that shows stickiness and low terra adoption; with openai confirming by making sol terra, astra sol.

I honestly never saw anyone doing /model gpt mini. I think those models were mostly used for copilot-like products, like those pull request reviews with untasteful dumbness to it (idiotic CodeQL finding -> LLM vomits a "fix" instead of assessing). While Luna seems to be the first model that you can trust to reason in the background, and this is predatory to their own more expensive model.

I saw that with corporate software too. What works is creating a skill with the task steps, it fades its initial reasoning. (I am not talking about observer safe guards, but the safety RTL).

This will be interesting. While no one cared about small models in the last few months except for the OSS community, there is a silent small model revolution with gpt luna and jev. Headless/background llm routines are cost-feasible, which will of course lead to exponential usage and cost.

My take on anthropic is that haiku 5.5 has been shelfed for a while since it is predatory against sonnet (see terra 5.6 usage), but openai went kamikaze and they are now forced to release.

Nevertheless, the elephant in the room has grown: will any of the Labs be able to profit if mass adoption lies in the highly crowded small model territory?

https://openrouter.ai/blog/insights/gpt-5-6-discounts-jevons...

Microsoft inviting IT to nice events and giving them perks is the reason they keep a grip so tight on enterprise. For unknown reasons, every garbage new microsoft add-on will be enabled silently without any clear way to manage. At least for copilot pro plus premium they sent an email that "i was invited" so i could promptly reject before they activated, but here is the trick, 99% of the employees won't bother to opt-out.

yes and no; you cant dump DNA in the context window and call it a day, in the blog post it was a common tool calling session. you do can have actual ml models for that, that the llm could use as a tool.

they ported their coding harness, something known for being simply an extensible http and subprocess wrapper, into a monolithic blob. They took their bloated and slow coding harness, and turned into an un-maintanable blob.

github pull requests are not performant. Alternatives that are not JavaScript based are welcome. Many projects still use mail lists for a reason.

this is chatgpt, web gui from mistral built-in Firefox, not for tech savvy users. I think anyone that will complain about this knows very well that you can just give your harness control over firefox through puppeteer, which is much more powerful. could firefox itself become a harness and speak openai api responses? maybe yeah, but why?

I dont care about codex,cc harness. but I do miss a proper terminal in pi web; I will likely endup forking it... the lamma cpp built-in web app is super nice, but also needs to be hacked to support api providers, and also no terminal :/ .

I think the definitive solution way would be using vscode stripped for web (what gh codespaces use) and add pi to it.

pi + pi web on a raspberry pi. an agent is just a path with its own .pi/ folder. you can have clown/.pi with only jokes mcp enabled (no bash, no read/write) and for sessions spawn from this path, the agent will think it is in the circus reality and will never go rogue (no tool to do so)

considering the current state of the internet and meta having no control over a solid marketplace (like amazon), it is very hard to see the shopping feature to take off. even if some legit business register/allow the bot to buy stuff, it will be ridiculously overwhelm by scam sites.

add to your system prompt?

git lfs just dumps your bin on s3, and is abandonoware since ms bought github, since github historically hosts on aws s3 and improving it would immediately benefit amazon. gh, the maintainers of it, is the only forge that does not allow clean-up unreachable artifact from the server.

from the screenshot, i believe it took the linux driver and transcribed to the mac kernel.