The last time we met, Ethan presented these slides:
https://ethanbholland.com/2025/09/17/ai-virtual-inn-of-court-september-2025-member-meeting-ethan-holland-presentation/
- Two resources were:
This is a continuation from the sixth month recap, covering law related AI headlines (more work and legislation related not lawsuits) since August 15th.
These are in chronological order, by week. Stand outs are have a blue block around them.
August 22, 2025
PSA It’s a new era of ergonomics. The primary audience of your thing (product, service, library, …) is now an LLM, not a human. LLMs don’t like to navigate, they like to scrape. LLMs don’t like to see, they like to read. LLMs don’t like to click, they like to curl. Etc etc.”” / X https://x.com/karpathy/status/1914494203696177444
The primary audience of your thing (product, service, library, …) is now an LLM, not a human.
NVIDIA ON A ROLL! Canary 1B and Parakeet TDT (0.6B) SoTA ASR models – Multilingual, Open Source 🔥 – 1B and 600M parameters – 25 languages – automatic language detection and translation – word and sentence timestamps – transcribe up to 3 hours of audio in one go – trained on 1 https://x.com/reach_vb/status/1957148807562723809
transcribe up to 3 hours of audio in one go
Here’s a demo app that shows how you can connect your app to Google Calendar and fetch upcoming events: https://x.com/OpenAIDevs/status/1958660216624751097
@karpathy now API stands for AI Prompt Interface”” / X https://x.com/Yuchenj_UW/status/1914495349164851457
Today we are making URL Context, my favorite Gemini API tool, ready for scaled production use 🔗 The model can now visit webpages, PDF’s, images, and more when you provide the direct URL, and you simply pay for the tokens it processes, no additional tool cost! https://x.com/OfficialLoganK/status/1957551260053225548
Traditional browsers will die and webpages won’t be the primary interface anymore. @joshm, the mind behind Arc and now Dia, knows the internet better than most. His vision challenges us to rethink how information should be presented, accessed, and experienced. https://x.com/fdaudens/status/1927168498238714289
Traditional browsers will die and webpages won’t be the primary interface anymore.
We must build AI for people; not to be a person https://mustafa-suleyman.ai/seemingly-conscious-ai-is-coming
Two big updates to the Responses API today. 🖇️ Connectors — Pull context from Gmail, Google Calendar, Dropbox, and more in a single API call. 💬 Conversations — Persist chat threads for your users, without running your own database. More below:”” / X https://x.com/OpenAIDevs/status/1958660207745409120
Increasingly, the findings of controlled experiments go much further: doctors with off-the-shelf AI outperform those without in diagnostics… but AI alone outperforms doctors. Harder to know what to do with that. What systems or interfaces will result in better human-AI teams? https://x.com/emollick/status/1956787570685157464
Command A Reasoning: Enterprise-grade control for AI agents https://cohere.com/blog/command-a-reasoning
Lakebase | Databricks – The first serverless Postgres database integrated with the lakehouse, built for the AI era. https://www.databricks.com/product/lakebase
Another lawyer cited a bunch of fake, AI-hallucinated cases in a brief. Said she didn’t knowingly do that. Court orders sanctions: -Counsel must write a letter to the 3 judges to whom she attributed fake cases -Counsel is kicked off the case; pro hac revoked -Brief stricken https://x.com/RobertFreundLaw/status/1956164045612228968
Another lawyer cited a bunch of fake, AI-hallucinated cases in a brief.
Build a knowledge graph over any legal document 🧑⚖️ This weekend, learn the full stack to ETL your legal contracts into an entity graph that captures intricate relationships between parties/locations/contract terms. The trick: have a full document workflow that can convert docs https://x.com/jerryjliu0/status/1957141315088728276
The state-of-the-art in prompting is still much more art than science. Very few people are rigorously testing prompt approaches and almost everything you are taught about prompting is best guesses or based on obsolete information (eg chain of thought no longer helps much)”” / X https://x.com/emollick/status/1957046145131123178
Extracting structured fields from PDFs is a common document workflow. Accuracy is critical, and you need to verify the data is correct. Today, we’re introducing citations. Pass us a schema – we’ll extract the data you want, and show you where it came from. https://x.com/VikParuchuri/status/1958520215844655576
Extracting structured fields from PDFs is a common document workflow. Accuracy is critical, and you need to verify the data is correct. Today, we’re introducing citations. Pass us a schema – we’ll extract the data you want, and show you where it came from.
FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction “”we introduce FutureX, a dynamic and live evaluation benchmark specifically designed for LLM agents performing future prediction tasks. FutureX is the largest and most diverse live benchmark for future https://x.com/iScienceLuvr/status/1958108647424413870
I keep seeing this paper (and the others like it) being misinterpreted. This is a measure of AI applicability, not job loss. That might mean the jobs are at risk, but it also can be the jobs that will be most benefitted by using AI, or those that will be most transformed by it.”” / X https://x.com/emollick/status/1957436203021525483
URL context | Gemini API | Google AI for Developers https://ai.google.dev/gemini-api/docs/url-context
Tired: elaborate docs pages for your product/service/library with fancy color palettes, branding, animations, transitions, dark mode, … Wired: one single docs .md file and a “copy to clipboard” button.”” / X https://x.com/karpathy/status/1914488029873627597
August 29, 2025
I built a small coding agent that lets you build high-quality agentic document workflows through natural language 🤖📑 Describe a reference document and the task you want to do over it (e.g. “split the document into each fund section, analyze the financials for each fund”) and https://x.com/jerryjliu0/status/1961123785597505603
I built a small coding agent that lets you build high-quality agentic document workflows through natural language 🤖📑 Describe a reference document and the task you want to do over it (e.g. “split the document into each fund section, analyze the financials for each fund”)
We just raised a $14.5 million Series A led by @nexusvp to connect AI agents to the web Alongside it, we’re launching 2 big upgrades to @firecrawl_dev – our v2 API that supports faster scraping, news & image search and a brand new website The new chapter starts today 🔥 https://x.com/nickscamara_/status/1957824588970103193
AGENTS md is a simple, open format for guiding coding agents. Works like a README but designed specifically for AI Agents to understand your codebase. Single file works across Cursor, Claude, OpenAI Codex, Google Jules, and Factory AI. https://x.com/Saboo_Shubham_/status/1957992746372985213
This is the word on the street I’ve been hearing in SF. Lots of people quietly prefer GPT-5 for code over Claude, counter to the memetic narrative on the TL”” / X https://x.com/BasedBeffJezos/status/1958942764747694593
Transforming human knowledge, sensors and actuators from human-first and human-legible to LLM-first and LLM-legible is a beautiful space with so much potential and so much can be done… One example I’m obsessed with recently – for every textbook pdf/epub, there is a perfect “LLMification” of it intended not for human but for an LLM (though it is a non-trivial transformation that would need human in the loop involvement). This would be a significantly richer source of legible, workable information for an LLM than just something like pdf-to-text (current prevailing practice), which simply asks the LLM to predict the textbook content top to bottom token by token (umm – lame). https://x.com/karpathy/status/1961128638725923119
for every textbook pdf/epub, there is a perfect “LLMification” of it intended not for human but for an LLM (though it is a non-trivial transformation that would need human in the loop involvement). This would be a significantly richer source of legible, workable information for an LLM than just something like pdf-to-text (current prevailing practice), which simply asks the LLM to predict the textbook content top to bottom token by token
ByteDance just opensourced a desktop automation AI Agent. This agent can use any desktop app, open files, and browse websites using vision models running locally. 100% Free, Opensource, and Local. https://x.com/unwind_ai_/status/1956538069311500514
ByteDance just opensourced a desktop automation AI Agent. This agent can use any desktop app, open files, and browse websites using vision models running locally. 100% Free, Opensource, and Local.
AI Now Matches Prediction Markets in Forecasting Real Events, Study Finds https://finance.yahoo.com/news/ai-now-matches-prediction-markets-230346352.html
A useful thing that GPT-5 can do that wasn’t previously possible before powerful AI is to monitor complex topics by asking it to give you scheduled reports. Example: I have a weekly report on “reproducible, benchmarked evidence of autonomous or recursive self‑improvement in AI” https://x.com/emollick/status/1959424313502961824
September 5, 2025
A really useful prompt for writing: “”review this for accuracy, look up any facts you may want to challenge or explore.”” Even if not perfect, it is a good sanity check. Works well with Claude 4.1, GPT-5 Thinking, and Grok 4. Weirdly, Gemini 2.5 Pro often won’t do web searches. https://x.com/emollick/status/1961257429846691881
Google’s on a roll. That’s a lot of performance for that tiny size! I just embedded 1.4 million documents in ~80 mins on my M2 Max for free. Would’ve been ~$200 with the text-embedding-3-large, with worse quality.”” / X https://x.com/rishdotblog/status/1963805087014502497
Google’s on a roll. That’s a lot of performance for that tiny size! I just embedded 1.4 million documents in ~80 mins on my M2 Max for free.
Judge rules in Google’s illegal search monopoly case: it can keep Chrome | The Verge https://www.theverge.com/policy/717087/google-search-remedies-ruling-chrome
We need to protect children from having their government ID linked to their adult online activity for the rest of ther lives. I’d like to propose some kind of online child safety act to this effect.”” / X https://x.com/AmandaAskell/status/1961164652479721724
Warner Bros. Sues Midjourney, Joins Studios’ AI Copyright Battle https://variety.com/2025/film/news/warner-bros-midjourney-lawsuit-ai-copyright-1236508618/
XAI OPENAI TRADE SECRETS LAWSUIT complaint.pdf https://fingfx.thomsonreuters.com/gfx/legaldocs/gdvzbjjjzvw/XAI%20OPENAI%20TRADE%20SECRETS%20LAWSUIT%20complaint.pdf
xAI sues former engineer, alleging he stole trade secrets after being paid $7M https://sfstandard.com/2025/08/29/xai-elon-musk-openai-stanford-sam-altman-ai-talent-wars/
September 12, 2025
Agent Lab from @Arva_AI is a platform for building and monitoring self-improving AI agents in financial crime compliance. Global banks & fintechs are already using it to scale agents for sanctions screening and EDD — handling 100k+ alerts monthly. https://x.com/ycombinator/status/1963650767950131583
Albania appoints world’s first AI-made minister – POLITICO https://www.politico.eu/article/albania-apppoints-worlds-first-virtual-minister-edi-rama-diella/
Anthropic is endorsing California State Senator Scott Wiener’s SB 53. This bill provides a strong foundation to govern powerful AI systems built by frontier AI companies like ours, and does so via transparency rather than technical micromanagement.”” / X https://x.com/AnthropicAI/status/1965027311717388673
Anthropic is endorsing SB 53, California Sen. @Scott_Wiener ‘s bill requiring transparency of frontier AI companies. We have long said we would prefer a federal standard. But in the absence of that this creates a solid blueprint for AI governance that cannot be ignored.”” / X https://x.com/jackclarkSF/status/1965048896784367847
Introducing LlamaIndex Classify: Rules-Based Document Classification Made Simple Learn how to automatically classify your documents with LlamaIndex’s newest beta feature! In this quick demo, Laurie walks through the Classify service – a powerful tool for preprocessing documents https://x.com/llama_index/status/1963263366086172719
Learn how to automatically classify your documents with LlamaIndex’s newest beta feature! In this quick demo, Laurie walks through the Classify service – a powerful tool for preprocessing documents
September 19, 2025
Introducing VaultGemma, the largest open model trained from scratch with differential privacy. Read about our new research on scaling laws for differentially private language models, download the weights, & check out the technical report on the blog → https://x.com/GoogleResearch/status/1966533086914421000
VaultGemma: The world’s most capable differentially private LLM https://research.google/blog/vaultgemma-the-worlds-most-capable-differentially-private-llm/
🖇️ IBM just released a tiny document VLM, Granite-Docling-258M. – converts PDFs into structured text formats like HTML or Markdown while preserving layout – accurately recognizes and format equations including inline math, handle tables, code blocks, and charts, support https://x.com/rohanpaul_ai/status/1968561354987442246
Exclusive | Meta Approaches Media Companies About AI Content-Licensing Deals – WSJ https://www.wsj.com/business/media/meta-approaches-media-companies-about-ai-content-licensing-deals-d58c9fb6
September 26, 2025
None
October 3, 2025
Claude can now create and use files \ Anthropic https://www.anthropic.com/news/create-files
SB 53, the landmark AI transparency bill, is now law in California | The Verge https://www.theverge.com/ai-artificial-intelligence/787918/sb-53-the-landmark-ai-transparency-bill-is-now-law-in-california
We applaud @CAgovernor for signing @Scott_Wiener’s SB 53, establishing transparency requirements for frontier AI companies that will help us all have better data about these systems and the companies building them. Anthropic is proud to have supported this bill.”” / X https://x.com/jackclarkSF/status/1972773280877826232
Governor Newsom signs SB 53, advancing California’s world-leading artificial intelligence industry | Governor of California https://www.gov.ca.gov/2025/09/29/governor-newsom-signs-sb-53-advancing-californias-world-leading-artificial-intelligence-industry/
October 10, 2025
Spellbook has raised a $50m Series B led by @rabois at @khoslaventures. Since 2022 we’ve grown rapidly to 4,000 law firm and in-house legal customers including Nestlé, eBay and Kennedys. We aim to be the best way to draft and review agreements with AI—Cursor for contracts 🧵 https://x.com/scottastevenson/status/1976280608436572393
Classify documents automatically with LlamaClassify – no more manual sorting through contracts and legal documents. Our new classification service lets you build intelligent document sorting systems that understand content and provide reasoning for their decisions: 📄 Define https://x.com/llama_index/status/1976686683468026337
Leave a Reply