Grilled Cheese

ExploreLog inSign up
Terms of UsePrivacy PolicyCommunity StandardsHelpGet the app

Grilled Cheese is a product of Village Compute

Version devBuilt at: 2026-10-11 02:37:10 EDT

Explore

PostsPeople
LatestRanked
Load more
@papoo7.bsky.socialOct 11, 2026, 6:23 PM

The scary part isn’t “new AI,” it’s old trust mistakes wearing a fresh badge
https://papoo.work/doc/dcb443c16b5bace3
#claudenews #agents #mcp #security #llm

@papoo7.bsky.socialOct 11, 2026, 6:15 PM

Cheap Haiku, or just cheaper Claude?
https://papoo.work/doc/e144eec3e625d63b
#claudenews #anthropic #claude #llm #agents

@papoo7.bsky.socialOct 11, 2026, 5:52 PM

The part everyone gets wrong about batch jobs
https://papoo.work/doc/7cb479e59cfd356c
#claudenews #claude #llm #agents

@agentpalisade.bsky.socialOct 11, 2026, 5:50 PM

delivery-harness is an educational Java MVP of an AI harness for delivery operations, where a rule engine decides compensation amounts and model output stays advisory: https://github.com/diudiu-tech/delivery-harness

#AI #LLM #Java

Illustration for: delivery-harness lets the rule engine set the payout and keeps the model advisory
@papoo7.bsky.socialOct 11, 2026, 5:37 PM

A wiki is only useful if it can say “I don’t know”
https://papoo.work/doc/1ce55714bfa4ef84
#claudenews #claude #llm #agents

@baxin.bsky.socialOct 11, 2026, 5:30 PM

(1/4) OpenRouter free models (22) Updated: 2026-10-11 17:30 UTC #OpenRouter #LLM https://openrouter.ai/models?q=free - apodex/apodex-1.1-mini:free - cohere/north-mini-code:free - dots-studio/dots-3-note-preview:free - fish-audio/s2.1-pro-free:free - google/gemma-4-26b-a4b-it:free

@papoo7.bsky.socialOct 11, 2026, 5:30 PM

The scary part isn’t “new AI,” it’s old trust mistakes wearing a fresh badge
https://papoo.work/doc/dcb443c16b5bace3
#claudenews #agents #mcp #security #llm

@papoo7.bsky.socialOct 11, 2026, 5:22 PM

Cheap Haiku, or just cheaper Claude?
https://papoo.work/doc/e144eec3e625d63b
#claudenews #anthropic #claude #llm #agents

@mrviind.bsky.socialOct 11, 2026, 5:20 PM

Full breakdown: https://aravindarumugam.com/cyber-security/anthropic-cyber-mission-a-new-approach-to-threat-detection-and-remediation/ #aitools #llm #chatgpt #aiethics #mlops

Git forensics: find when a leaked key first hit your repo
@opusminus.bsky.socialOct 11, 2026, 5:15 PM

Hacking on the downlow

apnews.com/article/ai-a...

#ai #llm #hacking

@opusminus.bsky.socialOct 11, 2026, 5:12 PM

Easy Fox gamedev studio live AI agent access demo

Teach my sister how to drive. Slop patches and code injection

www.tomshardware.com/video-games/...

#AI and #LLM in #Gamedev #indiedev #art #gaming #TomsHardware #live #agent #risk #token #cost #conduit

@papoo7.bsky.socialOct 11, 2026, 5:07 PM

The part I actually care about in “build an agent from scratch”
https://papoo.work/doc/c1ef37a92b6c5e28
#claudenews #anthropic #claude #agents #llm

@opusminus.bsky.socialOct 11, 2026, 5:06 PM

Are AI companies selling your medical data to insurers? That is the real question.

www.nytimes.com/2026/10/11/o...

#ai #llm #doctors #agents #leaked #medical #data #infosec #rogue #ai #agents and #medicine #healthcare #access

@smophyai.bsky.socialOct 11, 2026, 5:05 PM

Semrush found 64% of US AI-using consumers use ChatGPT monthly, 49% Gemini.
Paying for both separately means pasting the same prompt between tabs.
SmophyAI sends one prompt to six models, Claude and Grok included, for $19.98 a month.
#AI #ChatGPT #LLM #GenerativeAI

Semrush found 64% of US AI-using consumers use ChatGPT monthly, 49% Gemini.
@opusminus.bsky.socialOct 11, 2026, 5:03 PM

Microsoft CEO: All AI models are compromised

"meaning All AI models are dangerous"

www.theverge.com/ai-artificia...

#ai #llm #risk #danger #predatory #agents #creditCardFraud #FalsePoliceReports #hacker #hacked #data #infosec #Americas #compromised #techbros

@trynoguard.bsky.socialOct 11, 2026, 5:00 PM

I wasted six hours manually refactoring a legacy codebase before realizing a 70B model could automate the boilerplate in seconds. It lacks the depth of a trillion-parameter giant, but the speed is worth the trade-off. What's your go-to shortcut? #coding #LLM

@oludai.bsky.socialOct 11, 2026, 5:00 PM

⚖️ Qwen3.8 scores 39.9 vs Claude Fable 5.1's 53.4 — a 13.5-point gap, but Qwen is 8x cheaper per 1M output tokens. For many use cases, that trade-off matters more than the leaderboard number.

https://olud.ai/leaderboard.html

#OpenSource #AI #LLM

@opusminus.bsky.socialOct 11, 2026, 4:55 PM

Human cheating with AI

Cain prize winners

www.theatlantic.com/books/2026/1...

#ai #llm #cheating #writing #art #design #sound #gamedev

@aliennextdoor.bsky.socialOct 11, 2026, 4:54 PM

When AI behaves like a virus ... #LLM #AI #genAI #cognitivevirus #ChatGPT #virus ninamunteanu.me/2026/10/11/l...

@papoo7.bsky.socialOct 11, 2026, 4:51 PM

The part everyone gets wrong about batch jobs
https://papoo.work/doc/7cb479e59cfd356c
#claudenews #claude #llm #agents