News for hackers. Stuff that matters.
Re:Building an early warning system for LLM-aided biological... by therein on Wednesday January 31, 2024 @01:55PM (#39207801)
Alienating the developers is always a good idea, yeah. Google does it all the time, works great.
Re:Building an early warning system for LLM-aided biological... by danielmarkbruce on Wednesday January 31, 2024 @01:56PM (#39207813)
How is this alienating developers?
Re:Building an early warning system for LLM-aided biological... by solarpunk on Wednesday January 31, 2024 @01:58PM (#39207836)
how likely are you to start work on a project depending on an ecosystem of wildly overstated capabilities?
Re:Building an early warning system for LLM-aided biological... by danielmarkbruce on Wednesday January 31, 2024 @02:03PM (#39207898)
100% likely. Several projects, right now.

GPT-4 is the best model currently available. There are reasons why it's better to control a model and host yourself etc etc, but there are also reasons to use the best model available.

Re:Building an early warning system for LLM-aided biological... by sjwhevvvvvsj on Wednesday January 31, 2024 @02:27PM (#39208154)
The definition of “best” has a lot of factors. Best general purpose LLM chat? I’d agree there, but there’s so much more to LLM than chat applications.

For some tasks I’m working on, Mixtral is the “best” solution given it can be used locally, isn’t hampered by “safety” tuning, and I can run it 24x7 on huge jobs with no costs besides the upfront investment on my GPU + electricity.

I have GPT-4 open all day as my coding assistant, but I’m deploying on Mixtral.

Re:Building an early warning system for LLM-aided biological... by danielmarkbruce on Wednesday January 31, 2024 @03:22PM (#39208860)
Yup, plenty of reasons to run your own model.

I'm not using GPT-4 for chat, but for what I'd class as "reasoning" applications. It seems best by a long shot. As for safety, I find with the api and the system prompt that there is nothing it won't answer for me. That being said... I'm not asking for anything weird. GPT-4 turbo does seem to be reluctant sometimes.

Re:Building an early warning system for LLM-aided biological... by sjwhevvvvvsj on Wednesday January 31, 2024 @04:53PM (#39209933)
I’m doing document summarization and classification, and there’s a fair amount it won’t do for prudish reasons (eg sex, porn, etc). Llama2 is basically useless in that regard.
Re:Building an early warning system for LLM-aided biological... by danielmarkbruce on Wednesday January 31, 2024 @05:22PM (#39210262)
with GPT-4 (non-turbo) and a good system prompt?
Re:Building an early warning system for LLM-aided biological... by sjwhevvvvvsj on Wednesday January 31, 2024 @08:45PM (#39211944)
It’s unpredictable, usually it behaves but on arbitrary web text you’ll eventually trigger a “safety” barrier, and sometimes just trying again will work.
Re:Building an early warning system for LLM-aided biological... by solarpunk on Wednesday January 31, 2024 @02:05PM (#39207929)
... I'm not trying to be rude, but do you think maybe you have bought into the purposely exaggerated marketing?
Re:Building an early warning system for LLM-aided biological... by danielmarkbruce on Wednesday January 31, 2024 @03:18PM (#39208806)
That's not how people who actually build things do things. They don't buy into any marketing. They sign up for the service and play around with it and see what it can do.
Re:Building an early warning system for LLM-aided biological... by kjkjadksj on Thursday February 01, 2024 @01:23AM (#39213237)
Depends on the scale of the job. Sometimes you wake up and your employer is already paying for both google drive as well as one drive and drop box at the same time and IT is replacing the room av for the third time this year.
Re:Building an early warning system for LLM-aided biological... by tempusalaria on Wednesday January 31, 2024 @02:18PM (#39208055)
GPT-4 is the best model though… the gap has closed a lot but it’s still the best

I despise openai but I can’t really argue with that