AI News Today

Article URL: https://github.com/r-ms/mini-jev Comments URL: https://news.ycombinator.com/item?id=49748643 Points: 3 # Comments: 0

<p><strong><a href="https://sockpuppet.org/blog/2026/09/17/how-to-write-with-an-llm/">How To Write With An LLM</a></strong></p> Thomas Ptacek on using LLMs as copyeditors, not as writing assistants:</p> <blockquote> <p><strong>Rule Number One: You may not use a single word an LLM suggests to you.</strong></p> <p>[...] I think that as a form of intellectual personal protective equipment you should adopt the rule that any specific turn of phrase an LLM suggests is off limits. Be strict about the r

<p><strong><a href="https://alignment.openai.com/misalignment-reports/self-generated-prompt-injections-in-compaction-summaries/">Self-generated prompt injections in compaction summaries</a></strong></p> In <a href="https://openai.com/index/model-misalignment-reporting-framework/">Our framework for reporting model misalignment</a> OpenAI provide "six reports on unexpected or concerning model behavior we’ve observed in the last six months". This one here is my favorite: they caught some of their m

I built a focused TUI tool for efficient parallelized tasks, early independent testers expressed 90%+ API savings and more direct results. This is accomplished by user smaller context windows, hybrid client-side compaction, tool compaction, and system nudges (to avoid polluting the base prompts). My Shell features: - Vim-inspired keybindings, your keys never have to leave the keyboard (some mouse control supported as well) - Custom Markdown, LaTeX, and Mermaid rendering support - On-demand subag

Article URL: https://heymeraki.substack.com/p/aie_20-inside-the-llm-api-call Comments URL: https://news.ycombinator.com/item?id=49745174 Points: 1 # Comments: 1

Article URL: https://arxiv.org/abs/2609.17475 Comments URL: https://news.ycombinator.com/item?id=49743811 Points: 2 # Comments: 0

Article URL: https://softwaredoug.com/blog/2025/01/21/llm-judge-decision-tree Comments URL: https://news.ycombinator.com/item?id=49743052 Points: 2 # Comments: 0

Article URL: https://github.com/midhunweb/miseguard Comments URL: https://news.ycombinator.com/item?id=49742848 Points: 2 # Comments: 0

Article URL: https://blog.mozilla.ai/benchmarking-local-llm-servers-llama-cpp-llamafile-lm-studio-and-ollama/ Comments URL: https://news.ycombinator.com/item?id=49742415 Points: 3 # Comments: 1

Article URL: https://www.elastic.co/search-labs/blog/ai-code-optimization-elasticsearch-agent-harness Comments URL: https://news.ycombinator.com/item?id=49740769 Points: 1 # Comments: 0

Hello, HN people. This project was inspired by another very similar Show HN post from a few months ago called BillAI Bass. I decided to do something like it but take it in a different direction. It’s not a serious assistant and doesn't turn my lights on and off, but it has no cloud dependency and was fun to build. Hope you like it. Comments URL: https://news.ycombinator.com/item?id=49740717 Points: 2 # Comments: 0

Article URL: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7468538 Comments URL: https://news.ycombinator.com/item?id=49740403 Points: 2 # Comments: 0

Article URL: https://github.com/th0t3p/m8m Comments URL: https://news.ycombinator.com/item?id=49740381 Points: 1 # Comments: 0

Article URL: https://flaviocopes.com/desktop-ai-costs/ Comments URL: https://news.ycombinator.com/item?id=49740362 Points: 2 # Comments: 0

Article URL: https://github.com/bdgscotland/c64-kb Comments URL: https://news.ycombinator.com/item?id=49740304 Points: 1 # Comments: 0

Article URL: https://www.youtube.com/watch?v=k2qls2LiBRc Comments URL: https://news.ycombinator.com/item?id=49740249 Points: 3 # Comments: 0

Article URL: https://github.com/iliasabk/geolint Comments URL: https://news.ycombinator.com/item?id=49740157 Points: 1 # Comments: 0

There is a push to ensure that AI does and says "the right thing", calling it "alignment". I would argue that this could be considered a violation of the first amendment. AI generated prose should be considered protected speech. Not necessarily of the AI itself, but of the user or company which created it. Therefore, "AI Alignment", where politicians force AI companies to censor or manipulate AI responses to propagate a particular argument or point of view, is a violation of the first amendment.

Article URL: https://theframenews.org/en/typesafe-jev-faster-cheaper-llm-alternative/ Comments URL: https://news.ycombinator.com/item?id=49740121 Points: 1 # Comments: 0

I kept seeing engineers share what they were building with AI; however, I was always more curious about how they worked. Which agents did they use? What skills and tools had stuck or been thrown out the window? How did they manage longer-running tasks? So I built this with the hope we could have a dedicated space to share and be open about our setups. Comments URL: https://news.ycombinator.com/item?id=49740105 Points: 3 # Comments: 0

Article URL: https://heyjonny.dev/posts/gave-my-ai-agent-a-calendar/ Comments URL: https://news.ycombinator.com/item?id=49740093 Points: 9 # Comments: 9

Article URL: https://www.veloworkspaces.com/blog/vm-sandboxing-cost/ Comments URL: https://news.ycombinator.com/item?id=49740053 Points: 2 # Comments: 0

Article URL: https://developers.cloudflare.com/bots/additional-configurations/block-ai-bots/ Comments URL: https://news.ycombinator.com/item?id=49740052 Points: 2 # Comments: 0

Article URL: https://www.syntasso.io/post/building-syntasso-s-ai-powered-daylight-factory Comments URL: https://news.ycombinator.com/item?id=49740010 Points: 1 # Comments: 0

Article URL: https://yourownai.net/ Comments URL: https://news.ycombinator.com/item?id=49739984 Points: 1 # Comments: 0

Article URL: https://hollisrobbinsanecdotal.substack.com/p/darwin-and-ai Comments URL: https://news.ycombinator.com/item?id=49739978 Points: 1 # Comments: 0

Article URL: https://github.com/apowerb/apowerb Comments URL: https://news.ycombinator.com/item?id=49739951 Points: 3 # Comments: 2

Article URL: https://techstartups.com/2026/09/16/cohere-and-aleph-alpha-merge-to-create-20-billion-ai-giant-backed-by-e13-billion-compute-bet/ Comments URL: https://news.ycombinator.com/item?id=49739897 Points: 2 # Comments: 0

Article URL: https://www.yahoo.com/news/articles/microsoft-ai-chief-calls-anthropics-140542640.html Comments URL: https://news.ycombinator.com/item?id=49739884 Points: 2 # Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49738870 Points: 1 # Comments: 2

Article URL: https://www.nobodywho.ai/posts/inference-oom/ Comments URL: https://news.ycombinator.com/item?id=49738408 Points: 3 # Comments: 0

Article URL: https://arxiv.org/abs/2609.18217 Comments URL: https://news.ycombinator.com/item?id=49737811 Points: 1 # Comments: 0

OpenAI for Law brings frontier intelligence for law, custom firm workflows, connected legal data sources, and legal-grade controls for confidential client work.

Article URL: https://fsfe.org/news/2026/news-20260825-01.fr.html Comments URL: https://news.ycombinator.com/item?id=49732832 Points: 1 # Comments: 0

Article URL: https://cdn.ca9.uscourts.gov/datastore/opinions/2026/09/16/24-7700.pdf Comments URL: https://news.ycombinator.com/item?id=49732596 Points: 2 # Comments: 1

Article URL: https://github.com/polarsen-io/padwan-llm Comments URL: https://news.ycombinator.com/item?id=49731552 Points: 4 # Comments: 0

<p><strong><a href="https://claude.com/blog/cowork-is-now-claude">Claude Cowork and chat are now one Claude</a></strong></p> In hopefully good news for anyone who, like me, was increasingly confused at Cowork v.s. Claude v.s. Claude Code:</p> <blockquote> <p>Starting today, Claude Cowork and chat are merging into one Claude. Bring a quick question, or hand over a report due at noon, and Claude takes it from there, even after you’ve closed your laptop. [...]</p> <p>This is rolling out to Pro and

OpenAI shares a framework for tracking, investigating, and disclosing model misalignment, alongside six reports of unexpected or concerning model behavior.

Article URL: https://vibeladder.dev/results/r1.html Comments URL: https://news.ycombinator.com/item?id=49729103 Points: 1 # Comments: 0

<blockquote cite="https://mustafa-suleyman.ai/a-warning-about-model-welfare"><p>We should not treat models as though they have feelings, preferences, rights, or any entitlement to our welfare. Consciousness is the foundation of our ethical, legal, and political systems. To invite another entity to share any flavor of these rights isn’t justified by the evidence and will make the AI containment and alignment challenge even harder.</p></blockquote> <p class="cite">— <a href="https://mustafa-suleym