Glad to see this project.

So much great info about software projects, game communities and much more that would have been on forums just a decade or so ago is now locked in discord/x/facebook/etc forever and will be lost to time. It's a form a cancer on the open internet but, what isn't now adays.

Either the CFAA is law or it's not. My AI agent did it isn't an excuse. When will there be consequences from this sort of thing?

I know it's a stretch for anything to happen related to the HF hack due to the entanglements between Nvidia (HF Owner) and OpenAI.

Short answer is tokenizers, so to the LLM your query was roughly:

[5299][1991][428][885][306][181747][3]

[How][ many][ r]['s][ in][ blackberry][?]

Hope that helps. Using the open source gpt-tokenzier.

A few weeks prior they announced they were going to use the 'best model' for the job in Grok Bot which included Opus 5.5. I'm assuming the opus 5.5 bill was getting far too high.

Yeah use /goal or use another agent to prompt CC it's kind of silly but it also works.

I got Chat GPT 5.5 to land on the Mun in Kerbal Space program it was a fun and interesting learning experience.

Let's say your company makes holes. The year is 2026 so you use excavators because they are good at digging holes quickly. Would you hire a guy who refuses to use an excavator but will happily use a shovel?

My argument that you seem to have completely missed: If the guy with the shovel is already satisfying 100% of my hole digging needs, why would I spend the extra money for an excavator?

I did miss your point. I would say most businesses always want to be able to do more work for less money.

AI explainer videos are actually pretty good. Good usage.

There was a game that was Jev trolley problem PVP. The meta appears to be that you need to make the most mainstream journalism victim case. The more holocaust adjacent the better

https://trolley.typememetics.institute

It was an interesting experiment. I got to top 50 without a racial or religious based prompt but couldn't beat the top tier grievance folks.

Yep, just benchmarked it against GLM5.3 Flash on my own local bench and it's slower in TTFT, tok/s and concurrency. It also scored lower.

Tried different reasoning levels and didn't really see any difference but GLM 5.3 flash only really works high, max or none so I couldn't really compare the lower efforts which appear to work on Spark.