Viewing profile — steve-atx-7600

"So we are going back to blue books..." exactly. And, it is also efficient. You just need a proctor to ID the test taker and make sure they aren't using AI to cheat in order to ver…

charge more for it. its fine if free customers dont have service. dont break paying customers

gitlab self hosted though? no outage. i remember equivalent functionality at my last job taking this path

curious about methodology. ive seen them post results for claude/codex when they only ran over benchmarks 3 times per model...

how hard could it be these days for a mid to large size eng company to have their own gitlab/hub type solution hosted in aws

#0-nines

are you sure its actually two nines and not zero?

WTF. Outage every month if not multiple. Even for paying enterprise plans. Also, doesn't even have RAG offering.

Well then, the credible, perv glasses wearing authority on AI has spoken

Re the part about the brain associating how you feel at the moment / how you think you are performing with how you judge yourself as a person: I recommend reading Steve Hayes work …

Sounds like you need to switch jobs.

Great. Wake me up when they have model that works as well (quality and speed) as gpt 5.6 xhigh on most software engineering problems.

And you need the right genes to bulk up like Arnold back in the day

I can see that. I’m just afraid to sync too much time into complex routing schemes when I get pretty consistently good results out of got 5.6 or fabel. For code reviews, I’ll try t…

How much time do you spend on your setup vs getting a lot of stuff shipped by paying for fabel 5? For me, not using the best model is a huge opportunity cost since my company can a…

Artificial analysis always seemed sketchy as hell. If you read some of there methodology you’ll see a lot of <=3 repetitions on a particular pass for a given model. So low for call…

“…who had worked on well-being and safety issues for Meta” Never saw that one coming.

Gpt 5.6 is still like this at least for the $200/month option. It’s also always faster than fabel. Fabel might be able to do some things better but I don’t have time to constantly …

Won’t it soon be hard to tell if glasses are smart or not? At least for outdoor use sunglasses in black? I block meta so I have only seen third party pictures online.

Yes. You would only name it ant if you wanted to taint the first impression of anyone that’s been coding for a couple decades or more.

I used to have the same experience until 5.6 sol xhigh. I have instructions in my code review skill and agents.md to encourage parallelism including multiple agents as long as qual…

Set yourself up to be able to try / switch between models easily. I was a claude only user and just have my user level AGENTS.md for codex and others simply point at my user CLAUDE…

Good skills to have for mad-maxing it thru the desert after the ai apocalypse :)

I have not used grok 4.5 yet, but the other pictures match my experience doing anything graphical with the other models that it cracks me up. gpt 5.5 has no design sense whatsoever…

models? They prefer that we call them "entities" so that they don't feel belittled.