bestcoder69

no profile record

Submissions

Technical Details of My LLM-Generated Book

mattbruenig.com

3 pointsby bestcoder695 bulan yang lalu0 comments

RedPajama 7B (an Apache 2.0-licensed LLaMa) is now available

85 pointsby bestcoder693 tahun yang lalu25 comments

What to Do About AI-Driven Job Displacement?

peoplespolicyproject.org

6 pointsby bestcoder693 tahun yang lalu3 comments

comments

tahun laludiscuss

Llamafile: https://github.com/Mozilla-Ocho/llamafile

2 tahun yang laludiscuss

permitted to force RTO without any data != ought to force RTO without any data

2 tahun yang laludiscuss

I can already use multiple backends by writing different code. The value-add langchain would need to prove is whether i can get better results using their abstractions compared to me doing it manually. Every time I’ve looked at how langchain’s prompts are constructed, they went wayyy against LLM vendor guidance so I have doubts.

Also the downside of not being able to easily tweak prompts based on experiments (crucial!)

And not to mention the library doesn’t actually live up to this use case, and you immediately (IME) run into “you actually can’t use a _Chain with provider _ if you want to use their _ API”, so I ultimately did have to care about whats supposed to be abstracted over

2 tahun yang laludiscuss

They’ve been growth hacking the whole time pretty much, optimizing for virality. Eg integrating with every ai thing under the sun, so they could publish a seo-friendly “use gpt3 with someVecDb and lang chain” page, but for every permutation you can think. Easy for them to write since langchains abstractions are just unnecessary wrappers. They’ve also had meetups since very early on. The design seems to make langchain hard to remove since you’re no longer doing functional composition like you’d do in normal python - you’re combining Chains. You can’t insert your own log statements in between their calls so you have to onboard to langsmith for observability (their saas play). Now they have a DSL with their own binary operators :[

VC-backed, if you couldn’t guess already

2 tahun yang laludiscuss

openai cookbook! Instructor is a decent library that can help with the annoying parts without abstracting the whole api call - see it’s docs for RAG examples.

2 tahun yang laludiscuss

They released chat and non-chat (completion) versions of 3.5 at the same time so not really; the switch to chat model was orthogonal.

e: actually some of the pre-chatgpt models like code-davinci may have been considered part of the 3.5 series too

2 tahun yang laludiscuss

[flagged]

2 tahun yang laludiscuss

[flagged]

2 tahun yang laludiscuss

limewire teens were pioneers too

2 tahun yang laludiscuss

together.xyz, although they’re .ai now

3 tahun yang laludiscuss

Newt Gingrich proposed once that we make kids do this, but it was just gonna be for the poor kids.

3 tahun yang laludiscuss

Tesla could just negotiate instead of being antagonistic.

3 tahun yang laludiscuss

Prosecutors need snitches.

3 tahun yang laludiscuss

> This extreme scenario is unlikely to happen in the short term because of the high costs associated with additional AI servers and bottlenecks in the AI server supply chain, de Vries says.

If we suddenly start ignoring the costs, it could get very expensive, indeed.

3 tahun yang laludiscuss

Prompts:

- does this API design make sense?

- my team thinks __ is a good pattern, what are some cons?

- what’s a good name for a class that does x,y,z

- is this code snippet readable?

- write a bash script to automate this very tiny thing

- upload quickjs binary to the advanced data analysis model and ask it to micro benchmark a couple of approaches to the same thing

3 tahun yang laludiscuss

A cleaner policy would be to ban cars. Probably need a transition in between, but that's definitely the destination. In the year 3000 our asses better not be sitting in traffic in single-passenger vehicles w/ 3 seats empty still for some reason.

3 tahun yang laludiscuss

Maybe workers will strike for... more detailed information about each worker's individual profit margin?

3 tahun yang laludiscuss

And if I could breath underwater I wouldn't need a scuba tank.

3 tahun yang laludiscuss

He's analyzing what looks good in marketing copy.

3 tahun yang laludiscuss

Maybe if you have a model with a large context window, you stuff a document in the prompt as a prefix, then ask a bunch of different questions about the document?