Maybe the haphazard/devil may care look feels more authentically American

How true is this? How does a regulated industry confirm the model itself wasn't trained with malicious intent?

Why would it matter if the model is trained with malicious intent? It's a pure function. The harness controls security policies.

Much like a developer can insert a backdoor as a "bug" so can an LLM that was trained to do it.

One way you could probably do it is by identifying a commonly used library that can be misused in a way that would allow some kind of time-of-check to time-of-use (TOCTOU) exploit. Then you train the LLM to use the library incorrectly in this way.

Some truth to that. I hear it thrown around the office and everyone feels obligated to out agent each other (without actually proving a great use case)

For myself I don't need autonomous agents. I need a smaller version of Claude Code instead (the mcp client not the coding agent) that can run on local models that are under 24B params. I still need to try pi dev.

You'll be happy to know in the context of a "master branch" it never had any connotation to slavery, except in the minds of people who see everything as a question of race*

Anyway I'm off to listen to the 50th anniversary Dark Side of the Moon remaster. Wait, is "dark" an okay word? I didn't get a master's degree in English

* Parallel ATA on the other hand, yeah, yikes

> virtue signaling is fixing symptoms of the problem

It diminishes the seriousness of the entire anti-racism movement by making it look petty, out of touch and more interested in creating nuisances than solving real problems. The San Francisco school board got fired for doing similar nonsense during COVID, renaming schools and thus showing they weren’t serious people.

> by making it look

I have yet to see a good reason to believe that it isn't actually the case.

Can you, perhaps, cite your own pre-2020 writing attesting to the problem, and explaining why it should be considered a problem?

Do you consider that using the name "master" for a branch tends to endorse or normalize slavery, or (even stochastically) increase the amount of slavery that occurs in the world?

If so, how?

If not, why is it actually a problem to reference the concept (even disregarding the evidence that it was not intended to do so)?

Deep copilot integration feels so intrusive. It pops up with your recent files. What if they were my bank accounts or api keys? Whoever thought that would be a good use experience should be fired.

gguf or mlx? edit, just tried a community mlx and lm studio said it didn't support loading it yet.

Number 2 makes me chuckle honestly. Too many people going down the 10x rabbit holes on youtube. Next up, a framework that 100xs your workflow. You know its good because it comes with 300 agents and 20 mcp servers and 1200 skills

Short answer no. Less short answer, the science is catching up to big ones quickly.

forget the warning, just compact like someone suggested in the ticket. Who would opt for a massive cache miss?

I will say I have noticed none of these things in my enterprise account. Is this is a known targeting of non-enterprise clients only?