#Tag · bonfire.cafe

"I built a free tool for researchers to check if their code repository is ready for someone else to reproduce. 24 questions. 5 mins. Nothing tracked." #openscience #opencode

👉 https://topeuph-ai.github.io/ValiChord/at-home.html
(via: https://x.com/CeriEuph/status/2023004090176008227)

X (formerly Twitter)

View

ValiChord at Home

André Vatter | @avatter

@avatter@mastodon.social · last week

X (formerly Twitter)

View

ValiChord at Home

Travis F W boosted

Dusty

@d1@autistics.life · 4 weeks ago

I approve of @nlnet holding their ground on requiring the logging of LLM chats:

https://nlnet.nl/foundation/policies/generativeAI/archive/feedback/

"We are open to feedback and we also have to learn ourselves. This is a fast-changing field with many moving parts."

I have feedback!

1) Thanks for having a spine.

2) OpenCode has a convenient feature to export chat logs (in a nice, git-friendly Markdown format). Awesome I say! See Screenshot; the feature is called "Export session transcript" (shortcut: ctrl+x x). Avail yourself of it, my dudes!

#OpenSource #OpenCode #LLM #prompt

OpenCode has a convenient feature to export chat logs (in a nice, git-friendly Markdown format). The feature is called "Export session transcript" (shortcut: ctrl+x x)

NLnet; Write-up on the GenAI Policy Feedback Session

Dusty

@d1@autistics.life · 4 weeks ago

I approve of @nlnet holding their ground on requiring the logging of LLM chats:

https://nlnet.nl/foundation/policies/generativeAI/archive/feedback/

"We are open to feedback and we also have to learn ourselves. This is a fast-changing field with many moving parts."

I have feedback!

1) Thanks for having a spine.

#OpenSource #OpenCode #LLM #prompt

NLnet; Write-up on the GenAI Policy Feedback Session

Hacker News

@h4ckernews@mastodon.social · 2 months ago

Agent-of-empires: OpenCode and Claude Code session manager

https://github.com/njbrake/agent-of-empires

#HackerNews #AgentOfEmpires #OpenCode #ClaudeCode #SessionManager #GitHub #Technology

GitHub

GitHub - njbrake/agent-of-empires: Manage all your agents

Manage all your agents. Contribute to njbrake/agent-of-empires development by creating an account on GitHub.

Hacker News

@h4ckernews@mastodon.social · 2 months ago

Unauthenticated remote code execution in OpenCode

https://cy.md/opencode-rce/

#HackerNews #Unauthenticated #remote #code #execution #OpenCode #security #vulnerability #cybersecurity #hacking #news

Unauthenticated Remote Code Execution in OpenCode

Hacker News

@h4ckernews@mastodon.social · 2 months ago

Anthropic bans use of API in OpenCode CLI tool

https://github.com/anomalyco/opencode/issues/7410

#HackerNews #Anthropic #OpenCode #API #ban #CLI #tool #news #technology #AI

JCLS

@jcls@fedihum.org · 3 months ago

By randomizing #LLM prompts and analyzing moral #keywords via co-occurrence #networks and hierarchical clustering, @andrewpiper uncovers latent “moral communities” across 20th–21st century #English-language #fiction.
https://doi.org/10.48694/jcls.4168

Relative frequency of moral clusters by decade, comparing hierarchical and network-based clustering methods. Each line represents a moral cluster labeled by its most frequent keyword, with vertical position indicating the proportion of total moral keyword mentions assigned to that cluster in each decade.

JCLS

@jcls@fedihum.org · 3 months ago

As always: #OpenData and #OpenCode persistently available at: https://doi.org/10.5683/SP3/0EYY0T.
And the article: https://doi.org/10.48694/jcls.4168

Journal of Computational Literary Studies

Towards a Perspectival Moral History of the Novel Using LLMs

This paper introduces a new framework for studying the moral history of the novel through the lens of large language models (LLMs). Drawing on over 9,000 Wikipedia plot summaries of 20th- and 21st-century novels, it demonstrates how LLMs can surface the implicit life lessons – or story morals – encoded in narrative summaries at scale. Building on recent work in moral inference and narrative abstraction, the study proposes a reflexive, perspectival approach that emphasizes interpretation over taxonomy. To account for the semantic variability of LLM-generated morals, the study employs a randomized prompt assignment strategy and analyzes the resulting moral keywords using co-occurrence networks and hierarchical clustering, enabling the identification of latent moral communities and comparison across modeling approaches and time. Taken together, the findings argue for the value of LLMs not only in extracting narrative values, but in enabling a new, culturally situated view of literary history through computational means.

Konrad Förstner 💻🧬🦠 boosted

Felix Kronlage-Dammers

@fkr@social.tchncs.de · 4 months ago

#FOSDEM 2026 will have a “Building Europe’s Public Digital Infrastructure” devroom that is jointly organized by the @zendis and us from @SCS. The CfP for the devroom has been published:

https://lists.fosdem.org/pipermail/fosdem/2025q4/003688.html

We're looking forward to many interesting submissions:

https://lists.fosdem.org/pipermail/fosdem/2025q4/003688.html

#scs #sovereigncloudstack #zendis #openCode #openDesk

[FOSDEM] Call for Participation: “Building Europe’s Public Digital Infrastructure” devroom

Felix Kronlage-Dammers

@fkr@social.tchncs.de · 4 months ago

#FOSDEM 2026 will have a “Building Europe’s Public Digital Infrastructure” devroom that is jointly organized by the @zendis and us from @SCS. The CfP for the devroom has been published:

https://lists.fosdem.org/pipermail/fosdem/2025q4/003688.html

We're looking forward to many interesting submissions:

https://lists.fosdem.org/pipermail/fosdem/2025q4/003688.html

#scs #sovereigncloudstack #zendis #openCode #openDesk

[FOSDEM] Call for Participation: “Building Europe’s Public Digital Infrastructure” devroom