Axel Logan

DMs open if you want to say 👋

[Axel Logan @Axel_Logan__]

@RMFrench_ @cemcemyt ptdr

[Axel Logan @Axel_Logan__]

@CordierAlice2 @revuelta_es ptdr c'est podemos au pouvoir de quoi tu parles ?

[Axel Logan @Axel_Logan__]

@cryptonerd75 do not give up

[Axel Logan @Axel_Logan__]

@WXelka on est 400 sur le chat à attendre qu'il revienne et on vois ça :

[Axel Logan @Axel_Logan__]

@vinvan @yannglt wen content.js ser?

[Axel Logan @Axel_Logan__]

cool :) https://t.co/tYBusAJE8z

[Axel Logan @Axel_Logan__]

@ankur_maker @langchain @hwchase17 dm'd !

[Axel Logan @Axel_Logan__]

Why nobody keep the autocritisism output on #AutoGPT ?

[Axel Logan @Axel_Logan__]

This guy built a GPT4 AI that followed a prompt to find and call a Pizza Co and order a pizza without them realizing it was a bot. #AI is doubling its power every 3 months. Scary to think where we will be 6 months from now... #GPT4 #AutoGPT Full video: https://t.co/YPL0Jtwd5Q

[Axel Logan @Axel_Logan__]

ah ouais 🥶
https://t.co/e4SeNOO4I5

[Axel Logan @Axel_Logan__]

@albapastoriza_ quel frigo ?

[Axel Logan @Axel_Logan__]

ben c'était sur arte https://t.co/D1YEdrecKz

[Axel Logan @Axel_Logan__]

La paresse et la lâcheté sont les causes qui font qu'une si grande partie des humains préfèrent rester mineurs toute leurs vie, affranchis depuis longtemps par la nature de toute tutelle étrangère

L'écart creusé, constituera une hiérarchie naturel dont il faudra être digne

[Axel Logan @Axel_Logan__]

Les situations sont instables, incertaines
L'esprit critique demande le courage de travailler (avec un grand t) à réduire l'écart entre ce qui est et ce qui devrait être

[Axel Logan @Axel_Logan__]

about the actual hype imma be reasonable before sayin anything

[Sam Whitmore @sjwhitmore]

I’ve been building stuff w agents for ~3 months. Some scattered thoughts on the current agent hype:

On agent reliability:
before you get too scared or hyped about autonomous agents, try running one yourself

they have flashes of clarity and then tend to rabbit hole / get stuck / go off course. they need intense guardrails to reliably perform a task. They can be very random

They are looping computer programs that have a 5-15% failure rate every time you execute a new loop

People are assuming this will be trivial to fix but I actually think it’s quite hard because there is inherent non determinism in the LLM which is multiplied at each loop of execution

On agents seeming alarming:
agents have as much power as you give them w tools / API access, if you give them access to search the internet you’re building yourself a web scraper, which is cool, but not dangerous. If you give them REPL access, maybe they’ll run rm rf, so probably don’t do that. In general running agent-generated code without serious safety checks is not a good idea for a production app, just like you wouldn’t run random code a stranger sent you without reading it

The agent doesn’t have goals / abilities of its own beyond what’s baked into the LLM and the APIs you provide it. It’s as if you are running a python script that continues to generate as you run it. It can do what a python script w access to specific APIs can do. It does not have superpowers to do anything beyond that.

Not saying it’s not cool / exciting to see the agent programs self assemble! I like playing with them too. :)

[Axel Logan @Axel_Logan__]

@tarasowski music but without drums not too loud

[Axel Logan @Axel_Logan__]

@NanouuSymeon depend how recent mine is

[Axel Logan @Axel_Logan__]

@metaintro 😎 🚀

[Axel Logan @Axel_Logan__]

one day you're young and cool and the next you're thinking about Web3, b2b SaaS and Ai assisted tools

[Axel Logan @Axel_Logan__]

@ProductHunt gpt chat