#Agent

2025-06-04

The Darwin Gödel Machine - AI that improves itself by rewriting its own code #ai #agent #sakana luisquintanilla.me/feed/sakana

Kevin Karhan :verified:kkarhan@infosec.space
2025-06-04

@hanse_mina if that's not evidence that #Trump-led #USA is a #Agent for #Russia then IDK what is.

#USpol #EUpol

𝔱𝔯𝔷𝔶𝔤𝔩𝔬𝔴 :lattentacle:trzyglow
2025-06-03

lamenting what could've been.

IndieAuthors.Social Newsindieauthornews@indieauthors.social
2025-06-03

Alas, You Have Reached the Wrong Susan Fletcher

What's a well-published author to do when there's another well-published author in demand with their same name (first and last).
The post Alas, You Have Reached the Wrong Susan Fletcher appeared first on Writer's Digest.
writersdigest.com/alas-you-hav

#BeInspired #TheWritersLife #agent #BookPublishingIndustry #writerlife
@indieauthors

Hacker Newsh4ckernews
2025-05-31

I built an AI agent that turns ROS 2's turtlesim into a digital artist

github.com/Yutarop/turtlesim_a

Hacker Newsh4ckernews
2025-05-31

Leap – Full-stack AI developer agent that deploys to AWS

leap.new

Bebe13Bebe13
2025-05-30

Hat jemand von euch schon manus ausprobiert?
Manus? Seit Mai per App frei zugänglich.
KI-Agent aus China, entwickelt vom Start-up Monica, der als einer der ersten vollständig autonomen KI-Agenten gilt. Er kann komplexe Aufgaben eigenständig erledigen – von Datenanalysen über das Erstellen von Webseiten bis hin zu umfassenden Recherchen und Berichten.

Im Unterschied zu ChatGPT soll erAufgaben von Anfang bis Ende ohne weitere Nutzereingaben abwickeln können.
Ich probiere aus.

2025-05-30

The Curious Case of the Talking CSV: Building an AI-Powered Java Agent with Quarkus
Follow a Java detective as they investigate a suspicious CSV file with a little help from Quarkus, LangChain4j, and a local LLM.
myfear.substack.com/p/ai-java-
#Java #Quarkus #Langchain4j #Agent #CSV

2025-05-28

Playing with AI Agents

Reading Time: 2 minutes

Yesterday evening I was at a talk about AI. The person had written an AI agent that scrapes news sources for information, and reads reports, and then provides a summary of this information as a report.

We often think of AI as a chat where we ask a question, and then get an answer. This does work well, when you do something once, or twice. If you do something a dozen times per day then agents become interesting.

Both Le Chat by Mistral and Gemini by Google have agents that are focused on specific roles. These include a data analyst, a personal tutor, a universal summariser and a writing assistant for Le Chat. Gemini has something similar.

The idea is that, with an AI agent, you load a set of presets into the LLM to get it to behave a specific way, to give answers in a specific format.

With Le Chat you can click customise to see what the AI is told it is, and you can tweak it to be specific to what you want.

For an example conversation here is a sample conversation with the AI chat agent.

The instructions for the agent are:

In practice a web form or a template would achieve the same result.

If you find yourself giving the same instructions in an LLM chat, then using agents will save you time and effort. With a few lines of code you can tell an LLM about the role, the things it should know about, and how you want the answer to be formatted.

This can save you time, as well as save you having to repeat yourself.

#agent #AI #behaviour #instructions

View of Valangin
2025-05-28

Почему твой await fetch тормозит — и как это исправить

Привет, Хабр! В этой статье рассмотрим, почему безобидная строчка await fetch() неожиданно превращается в тормоз, где именно она зарывает драгоценные миллисекунды — и что можно сделать с этим.

habr.com/ru/companies/otus/art

#js #fetch #await #undici #agent

2025-05-27

Почему твой await fetch тормозит — и как это исправить

Привет, Хабр! В этой статье рассмотрим, почему безобидная строчка await fetch() неожиданно превращается в тормоз, где именно она зарывает драгоценные миллисекунды — и что можно сделать с этим.

habr.com/ru/companies/otus/art

#js #fetch #await #undici #agent

Erik C. Thauvinethauvin
2025-05-27
2025-05-25

I shipped thread compaction for [magenta.nvim](github.com/dlants/magenta.nvim), my #neovim #nvim #ai #llm #agent plugin,

By starting your message with `@compact`, the agent will start work in a new thread, and summarize your thread so far in the initial message.

This is a great way to continue working on a longer project without getting into large context window lengths, and keep things focused, snappy (and cheap).

I also cleaned up the issue tracker, and added a bunch of small issues with a "good first issue" label, to help folks get started with contributing!

Please consider contributing, and also send me feedback. Especially if you like magenta, it's really motivating to know folks are using it.

Cheers!

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst