Mastodawn

Doin的赛博空间

1h ago

一些 #阴谋论在中文互联网上流传，认为一些失踪人口的意识被上传，以用于开发豆包等大语言模型。

https://www.zhihu.com/question/2022623696783774161
https://xcancel.com/YesterdayOrange/status/2038891964415037591

#conspiracy #internetmysteries #missingperson #AI #互联网谜团 #失踪人口 #人工智能 #大语言模型 #llm #llms

Fabian Transchel 1h ago

So #Claude #Code is exactly the hot mess I expected it to be.

The mental image I have of any "#Agent Layer" on top of #LLMs is always the same: a barrel battered by bullets fixed with (ineffective) #bandaids making it leak *a little slower*.

The #injection safeties are as ridiculous as they are insightful, the "#sentiment analysis" is a blacklist... c'mon.

Raising #billions for this is most definitely quite the #achievement.

Enola Knezevic 3h ago

Question for native speakers of English: Does "cancelled" being spelled with 2 "l"s mean that Claude Code was not developed by USians? It was either underpaid labour in the Global South or people on H-1B visa? Or was that also vibe coded?

https://neuromatch.social/@jonny/116326861737478342

#language #english #AI #noAI #LLM #LLMs #vibeCoding #claudeCode

jonny (good kind) (@[email protected])

Attached: 3 images OK i can't focus on work and keep looking at this repo. So after every "subagent" runs, claude code creates *another* "agent" to check on whether the first "agent" did the thing it was supposed to. I don't know about you but i smell a bit of a problem, if you can't trust whether one "agent" with a very big fancy model did something, how in the fuck are you supposed to trust another "agent" running on the smallest crappiest model? That's not the funny part, that's obvious and fundamental to the entire show here. HOWEVER RECALL [the above JSON Schema Verification thing](https://neuromatch.social/@jonny/116325123136895805) that is unconditionally added onto the end of every round of LLM calls. the mechanism for adding that hook is... JUST FUCKING ASKING THE MODEL TO CALL THAT TOOL. second pic is registering a hook s.t. "after some stop state happens, if there isn't a message indicating that we have successfully called the JSON validation thing, prompt the model saying "you must call the json validation thing" this shit sucks so bad they can't even ***CALL THEIR OWN CODE FROM INSIDE THEIR OWN CODE.*** Look at the comment on pic 3 - "e.g. agent finished without calling structured output tool" - that's common enough that they have a whole goddamn error category for it, and the way it's handled is by just pretending the job was cancelled and nothing happened.

neurospace.live

Matěj Kastner 3h ago

#Fajne #Prompty 2️⃣ byly boží, protože byli o lidech!

Naprosto TOP akce pro lidi zdaleka nejen z technologického světa v #Ostrava 👌 @[email protected] nezklamali! 🥳

Fakt díky, že děláte akce postavené na lidech 👏 Takhle si představuju, že může být #AI #LLM a #agenti fakt přínosní!

👉 Díky celé partě organizátorů a hlavně - všem, co jste vystoupili a přišli!

💡Jo! A pokud jste v #IT nebo pracujete s #Daty, využíváte #DB #AI #LLMs, rád se s váma potkám na 🟣 #DATA #CIRCLE v po 13.4. u nás v @company 🖐

Patrick Wyatt 3h ago

How do you ensure success when collaborating with AI agents? I broke down my go-to techniques at the O'Reilly AI conference last month, and the video + presentation notes are now available. Check it out here: https://www.codeofhonor.com/library/ #LLMs #Coding #AI

https://www.codeofhonor.com/snippets/creating-guardrails-for-ai-agents/

Code of Honor

Game design, programming and more

Code of Honor

lmorchard's links 4h ago

Model Context Protocol Server - Home Assistant

"The Model Context Protocol is an open protocol that standardizes how applications provide context to LLMs. The Model Context Protocol Server (MCP) integration enables using Home Assistant to provide context for MCP LLM Client Applications. For example, you can control your lights from Claude Desktop"

https://www.home-assistant.io/integrations/mcp_server/

#ai #homeassistant #iot #llms #mcp #smarthome

Model Context Protocol Server

Instructions on how to add a Model Context Protocol Server to Home Assistant.

Home Assistant

Wayne Radinsky 7h ago

"AI is an incredibly lonely experience", says Dennis Lemm.

"I find myself holding on to a work reality that was shaped by coding together, solving problems together -- and yes, the occasional Nerf gun battle or foosball game was a welcome break for passively mulling over a bug, which back at your desk would often get solved pretty quickly."

"I just discussed the best solution to the problem with my agent."

https://www.lemm.dev/blog/en/dev/26-03-17-ailone/

#solidstatelife #ai #genai #llms #codingai

Ai-lone

A sentence from Salma Alam-Naylor about AI and loneliness hits close to home. On remote work, vanishing office culture, and what we lose when we replace colleagues with agents.

lmorchard's links 10h ago

Mr. Chatterbox, or, The Modern Prometheus

"A few days ago, I posted about a personal project that I've been working on for the last few weeks: Mr. Chatterbox, a chatbot trained from scratch on Victorian-era literature. I have to admit, I was totally blown away (and a little frightened!) by the reception. Whenever I post about personal projects, I'm used to them being politely ignored. The fact that this wasn't ignored surprised me mightily. I also received lots of questions about how Mr. Chatterbox had been trained, what tools I have ..."

https://www.estragon.news/mr-chatterbox-or-the-modern-prometheus/

#ai #literature #llms

Mr. Chatterbox, or, The Modern Prometheus

A few days ago, I posted about a personal project that I've been working on for the last few weeks: Mr. Chatterbox, a chatbot trained from scratch on Victorian-era literature. I have to admit, I was totally blown away (and a little frightened!) by the reception. Whenever I post about

Estragon