Peter Björkmarker

[Peter Björkmarker @peterbjorkmark]

@tamaybes Given the jump wouldn’t we expect it to solve at least one currently unsolved research question. If not why?

[Peter Björkmarker @peterbjorkmark]

@mmjukic Agreed. My 2 cents. You will always need to give an LLM a quite large and specific context for how to operate. This makes them much more useful than you might think but also much less impressive.

[Peter Björkmarker @peterbjorkmark]

@perrymetzger Yeah I can attest to it being challenging on multiple levels…. What would you suggest we do? Given we want to build rather than sit in meetings…

[Peter Björkmarker @peterbjorkmark]

@JagersbergKnut Hope you are correct! However, given LLMs ability to also produce vast lengths of text without actual information it might also end up being the opposite. https://t.co/kImPwj8GiH

[Peter Björkmarker @peterbjorkmark]

@simonw @emollick Agree! OpenAI will have trouble getting enough context to do that. Regardless of superintelligent capability “perfect” does not contain much information. A privacy focused Apple could potentially know a lot more about what “perfect” means to you. Context wins in the long run.

[Peter Björkmarker @peterbjorkmark]

@simonw We use it to take lazy/ambiguous user questions, add more specific context and ask the llm output a more “better” question. We feed this question to a texttosql llm.

[Emad @EMostaque]

There will be no edge in talent in AI
There will be no edge in compute in AI
There will be no edge in models in AI

Will be

Data
Distribution
Integration

Google et al will drive generalised AI to zero marginal cost & we will make open variants of cutting edge open & available

[gfodor.id @gfodor]

A big change for me in programming in GPT-4 is I now don't factor in the overhead of using an unfamilar language or library in spiking out solutions to most problems. For rapid prototyping, exploration, and throwaway scripting, this is an absolutely insane change.

[Peter Björkmarker @peterbjorkmark]

@bindureddy https://t.co/NqmZdyTgaE ☝️

[David Deutsch @DavidDeutschOxf]

I suspect that there's no explanatory theory linking those proxies to anything that would reasonably be regarded as competence in practical applications.

No doubt slide-rule test scores have decreased too.

What causes moral panics? I don't know. Not iPhones.

[Erik Bernhardsson @bernhardsson]

I don't even know if you could design software non-iteratively today. Almost all the issues I run into these days is things like "I guess this vendor has an undocumented rate limit so we'll have to refactor and make requests in batches" and how do you plan for that?

[Peter Björkmarker @peterbjorkmark]

@ddlabar The way to test it. Skip explicit dispose. Put the API under a bit of load and you will get very strange behavior and exceptions.

[Peter Björkmarker @peterbjorkmark]

@ddlabar I have not been able to reuse the same container consistently across multiple plugin executions. I do not think you can as plugins need to be stateless.

[Peter Björkmarker @peterbjorkmark]

@ddlabar Me…

[Peter Björkmarker @peterbjorkmark]

@ddlabar You interpreted my correct! Just pointing it out for people less experienced in plug-in development who may read this… Relevant doc https://t.co/s45nUuH7M0 (info section below)

[Peter Björkmarker @peterbjorkmark]

@ddlabar Note that you have to instantiate and explicitly dispose the container in the execute method as the platform does not always run the plugin constructor (happens often under a bit of load)

[Peter Björkmarker @peterbjorkmark]

@ddlabar New try!

https://t.co/Ex0x2LROXh is what I suggested to you the last time around I think?

Works well and allows for simplifying the code base into small services as needed as lifetime management.
….

[Peter Björkmarker @peterbjorkmark]

@ScottDurow @aprildunnam @laskewitz Congrats!!!

[Peter Björkmarker @peterbjorkmark]

@benedictevans Surprised this pattern isn't useful for you: https://t.co/SHOqGhG0GI

[Ethan Mollick @emollick]

I gave Claude the descriptions of 400 of the latest Y Combinator startups & asked it to generate on-trend startup concepts based on them. Some interesting ideas.

(As a general principle, this type of few-shot prompting, where you give the AI examples, is an effective technique)