Comments URL: https://news.ycombinator.com/item?id=50447870

Points: 10

# Comments: 0

..I laughed.

Comments URL: https://news.ycombinator.com/item?id=50365928

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=50365895

Points: 2

# Comments: 0

https://wikispooks.com/wiki/The_Intercept

Glenn Greenwald still defends them, to the point of going after Whitney Webb, which is insane.

It is absolutely true when you look at the facts. Whistleblowers were HEAVILY prosecuted under Obama. He went after Manning and then Manning was crying to Obama for the pardon; to the man who's justice department literally led the charge for prosecution.

Trump is no different and is equally as corrurpt as those before them. It's a narrative game. Like Orwell predicted, people hate Big Orange even though he's equally corrurpt (not more, not less) than all the others in the Epstein class before him. People have been conditioned to scream at a screen, not for 2 minutes, but 24/7 with hate.

Comments URL: https://news.ycombinator.com/item?id=50351750

Points: 3

# Comments: 3

Comments URL: https://news.ycombinator.com/item?id=50344912

Points: 51

# Comments: 19

With OpenCode you can run /model and just select whatever your provider offers. I always recommend not using prompts. Create an AGENT.md with your project rules, then create a plan/01-initial-requirements.md. Write an entire requirements spec. Commit those. Then tell the LLM "Read AGENT.md for project rules and run plan/01-initial-requirements.md".

That way you can commit that output on a branch, jump back to the original commit, and run the plan again with a different model. You can do that multiple times and compare the output on all the branches. Some models might give you better UI, some better structure. You can just keep the one you like most, or ask a model to combine certain aspects of each branch into your final.

The harness provides a means for the LLM to write file output and run tools (commands) to test output. Alternative harnesses including things like OpenCode.

You can point OpenCode to your Anthropic account, but only if you have API usage (there are ways around this, but if Anthropic detects it you could get banned). Anthropic locks their subscription plans to THEIR harness and no others.

Most harnesses like OpenCode, Cursor, Pi, Hermes, etc. have settings to tie into a bunch of different providers (although they'll always try to promote their own by default, because they have to fund their own harness development of course).

I recommend OpenCode + OpenRouter. OpenRouter has a bunch of models and their web interface shows where those models are run (AWS Bedrock, xAI, Anthropic, etc.) and what data they collect from your prompts (although this is kinda a 'trust me bro' status as a provider could be lying about collecting data).

Comments URL: https://news.ycombinator.com/item?id=50325637

Points: 2

# Comments: 1

> Would you prefer if Linux allowed local users to replace the kernel and/or its modules without root? What kind of faux-outrage is this?

On any Linux distribution, which managed packages update themselves? zero. Crowdstrike should provide package repositories so admins can pull in updates at their regular cadence.

At a minimum, the package should NEVER update its own binaries located in /usr/bin or /opt. If it need to pull updates, those should go in /var. Crowdstrike could have made the core binaries a shim where they load a second stage from /var.

Back when I was in DevOps, the Linux Falcon Sensor was an absolutely disaster. They recompiled it for EVERY kernel release of every supported distribution (they had never heard of DPMS apparently), the service ran as root, it UPDATED ITS OWN BINARIES as root! It broke nearly ever Linux design philosophy.

I know newer version use eBPF and don't have the stupid kernel lock-in issue, but I still don't trust it.

It doesn't appear that the Claude Code harness itself was compromised, was it? or Cursor if you use Anthropic models via Cursor's API itself?

Lately I've been using a script that mounts my current working directory in a container and I put all my build tools in a Dockerfile. I also map the harness config (~/.config/opencode or whatever) to a named volume to minimize the chance a harness could grab other things off my host. I can't use it if I ask the LLMs for docker work since they need the docker socket and then all bets are off (it could just mount your root volume somewhere). I sure I could use a full QEMU VM or some other type of isolation for such devops tasks, but I haven't really looked into it yet. Guess I should.

Comments URL: https://news.ycombinator.com/item?id=50292886

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=50281071

Points: 5

# Comments: 0

LLMs should actually be the level to oppose such things allowing for rapid reverse engineering of closed systems and custom bespoke software, but it's all dependent on "cloud" architecture, and OpenAI/Anthropic could ban you at any time for any reason. Independent models like Kimi 3 and GLM-5 should hedge that situation, but compute hardware required to run such models (e.g. 4x DGX units) use to sell for <$20k, but have now been pushed to nearly $40k. Enthusiasts can no long affordably buy the hardware that was so prevalent that made the modern compute era possible.

I feel your frustration with your "strike" which is an unplanned vacation. It's won't amount to much and hopefully you won't lose your job. Organizing anything at scale will be impossible, because every large at-scale protest you see is organized by the state or massive private interests. They're all psychological operations, yes even the famous 9 minute clip. When you really dig into all of it, the vast majority of people in this world are in the global control net of the new technocratic religion, and they believe everything they see from a major news site on social media, Google or the TV screen.

Comments URL: https://news.ycombinator.com/item?id=50271820

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=50246465

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=50245339

Points: 1

# Comments: 1