victor9000

using jev is a significant step towards using jev

I ask coworkers point blank to send me a non-llm version of their slop sagas. The initial exchange can be a bit awkward, particularly with new hires, but consistently asking for human prose has worked for me.

It's also well established that an algorithm or architecture alone are not enough to produce a useful model. The same architecture can produce vastly different results depending on the training data, post-training, harness, etc.

The fact that something like this is so widely celebrated shows just how user hostile anthropic has become.

I wonder if this is willful sabotage on the part of the model. In other words, if you ask the model to craft a defense for a morally questionable case, will the model execute the defense in good faith? Or will it apply a training or system prompt bias in subtle ways?

In Perplexity's case everything is getting routed through the user's browser, so there is no server to server communication between Perplexity and Amazon, thus no CFAA unauthorized access was established. However, Anthropic and OpenAI did not use the pattern of routing through authorized parties, so I don't think this opinion gives them any cover.

US enterprise customers aren't going to convert to overseas models, average consumers might though.

The hardware is not open

Accomplishments like these are standards we should use for when to build someone a statue

Yes, they haven't advertised a pending price jump in the near future.

Contributing to a project like this seems like a great way to get yourself export controlled

But you don't need an F1 car for a grocery run

UBlock Origin can clear those on FF mobile with one of the Annoyances lists

The article makes it pretty clear

> It’s not that I can’t afford to help him,” Steve told me. “I just have a real problem with handouts. And I want him to have the satisfaction of knowing he’s built something himself, with his own hard work. That’s how I was raised, too.

So it has nothing to with the son, Steve is just looking to validate his world view. The reality of the situation is that the boomer generation was provided with an immense amount of social assistance, affordability, and opportunity. Yet these are the same benefits they deny even their own children in favor of sadistic fantasies.

Baby Food, Adult Diapers

Denying your own child a $15K business loan just to placate your sadistic delusions perfectly describes the mindset of aging boomers. They're happy to watch their own children struggle for the opportunity to validate their ideology. They don't have enough empathy to help their own children, so it's futile expecting them to care about anyone else in society. They use tragedy of the commons situations to justify endless gluttony, and will act surprised when the next generation pisses on their graves.

Particularly in this day in age when the FF market share is down to low single digits

These videos are far from good, but it's possible to create a decent AI music video if you use a human-in-the-loop workflow: https://www.youtube.com/watch?v=52Km88uAZ4M

I'm at the point where pricing is the first thing I look for in announcements like this.

If this model is not willing to fix security issues in your application, does it mean that it's implicitly embedding vulnerabilities as well? How can it be trusted to write secure code?

This is precisely the issue. It took a fair amount of idealism, conviction, and commitment in order to create the open source movement and bring it to where it is today. In contrast, most skilled data science practitioners are just chasing IPO exits these days.

Fable is a complete joke:

what's the best way to run this mcp server against the OData API used in this project? Can you come up with a PoC in a docker container?

https://github.com/oisee/odata_mcp_go

● I'll dig into two things in parallel: how this project talks to the OData API, and what the odata_mcp_go server needs to run. Let me start exploring.

Searched for 1 pattern (ctrl+o to expand)

● Fable 5's safety measures flagged this message for cybersecurity or biology topics. They may flag safe, normal content as well. These measures let us bring you Mythos-level capability in other areas sooner, and we're working to refine them. Switched to Opus 4.8. Send feedback with /feedback or learn more ⎿ Tip: You can configure model switch behavior in /config

● Let me read the key integration files and fetch the MCP server's README at the same time.

  Read 2 files (ctrl+o to expand)

● Fetch(https://github.com/oisee/odata_mcp_go)

The linear MCP is amazing to work with as it lets me keep all my workflows in the terminal. The ergonomics around search and ticket management are dead simple going through a terminal agent, so I didn't need much more convincing after enabling that configuration.

It was just a little baby GTA

Clearly they need more layoffs, and for that matter why keep anyone around? After all, AI will be writing 100% of code in 2026.

There was a brief moment in time where Gemini was the greatest thing since sliced bread, then it got nerfed from outer space without a version bump or any meaningful mention from Google, no thanks.

Care to elaborate? I jumped ship when 5.4 first released, have things gotten worse?

CC usage limits and the 5 hour cool downs are what made me realize that I can't depend on this tool in a professional setting.

Yes, junior candidates lacking the knowledge and wisdom to redirect an LLM, that's who will unlock the mythical AI productivity.

This is the real intent