Working on @percipient_co & @certeraAI. Lawyer. Dig music, hoops and the Cubs. Blockchain believer. Host of Technically Legal Podcast (@technicallylgl).
Joined August 2013
- Tweets1.5K
- Following608
- Followers441
- Likes672
Chad Main retweeted
This week's current Legal AI Leaderboard as taken from pairwise comparisons by vetted legal professionals is posted below. @GeminiApp models hold the top three spots this time around. @OpenAI and @Anthropic models round out the rest of the top 10. See the full leaderboard here: certera.ai/legal-llm-leaderb…
Chad Main retweeted
Argon is now live at certera.ai if you want to give it a spin to see how it does on legal work. Use one of our pre-built workflows, or run your own prompt. You can also select other models to compare it against.
Chad Main retweeted
Wonder is now live at certera.ai if you want to give it a spin to see how it does on legal work. Use one of our pre-built workflows, or run your own prompt. You can also select other models to compare it against.
We’re excited to introduce the Muse Wonder series with Muse Wonder and Muse Wonder Full, our most capable models yet. Both are frontier models, built to deliver state-of-the-art performance for personal and professional agentic tasks.
Muse Wonder is available today via the Meta Model API and Muse Code. Muse Wonder Full is available today for Muse Code subscribers. Muse Wonder will also soon power experiences in our personal agent product, Muse, rolling out first to subscribers.
Chad Main retweeted
Curious how Google's new @GeminiApp Argon actually performs on real legal tasks?
We just added it to Certera.ai. You can now run it through pre-built legal workflows, like contract comparisons, deposition summaries, and citation checks, and evaluate it blind, side-by-side against other leading LLMs.
Run a test and see how it handles your day-to-day legal work.
Open and free to use for all legal professionals (don't need to be a lawyer).
Find it here: certera.ai/
Chad Main retweeted
Mind Your Business: Can law schools learn from computer science programs in the debate on generative AI? ow.ly/xm3m50ZRZyK #businessoflaw #mindyourbusiness #legaleducation #legaltech @chad_main
We just added @Muse Wonder to @CerteraAI so it can be tested against other models for legal output. If you want to see it in action pitted against other LLMs, you can check it out at certera.ai/chat.
Want to see how @Muse Wonder does on legal tasks? We added it to Certera so you can see for yourself. Just choose custom or single mode and see how it does.
Open to legal professionals and free to use.
Try it now: certera.ai/chat
We ran 3 types of legal tasks 2000+ times across most LLMs to see what it really cost. For easier tasks, the quality of expensive models was markedly better than the least. But... and here is the interesting part--for more difficult and multi-step tasks, the difference in outputs was not crazy different from the most expensive to the cheapest, but the prices were for sure. Fable 5.1 was coming in at over $10 a task.
Relevant to this audience, @grok was always in the middle to less expensive range.
More info below and in the article linked.
Want to know what it really costs to do legal work on AI? There is a lot speculation, so we wanted to know for real. We ran more than 2000 prompts over most available LLMs to figure it out.
TL;DR:
• Simple query: <$0.01 to ~$0.10
• Client alert: ~$0.04 avg (up to $0.27)
• Insurance memo: $0.22 median / $1.43 avg—ranging from $0.004 (GLM Flash) to $10.47 (Fable 5.1)
Check out full breakdown here:
certera.ai/research/what-ai-…
C'mon on man. @Cubs really? You know what a lot of people think of us Cubs fans as it is, right?
JUST IN: The Chicago Cubs are releasing their own romantic comedy series on social media.
NINE INNINGS TO LOVE will follow two young fans who meet in the bleachers and spark a special connection.
The series will feature 17 short form episodes, all produced by the team’s creative arm Cubs Productions.
It premieres on September 4th on the @Cubs TikTok. ⚾️ ♥️
We added the new Qwens and GLMs to @CerteraAI. You can give them a spin on their own or pit them against other models to see how they do.
All the new @Zai_org and @alibaba_cloud models (GLM-5.3, GLM-5.3-Flash, Qwen3.8-Flash, and Qwen3.8-27B) are now available for use on Certera.AI. To see how they do on legal work against other LLMs, just use custom mode to select the other models you want to compare and choose which output you prefer. Check it out at certera.ai.
Big thanks to @bitcoin_wales for coming on the show to talk about AI regs and his latest book, The AI Legal Handbook. It is a good read. Thorough, succinct and accessible despite being a book about laws and regs. geni.us/Justin_Wales_AI
We connected @CerteraAI to @courtlistener so AI output accuracy can be verified even more deeply. Three ways to use: 1) Enable as a connector in original prompt); 2) if you don't do that, the app prompts user to verify cites if present in response; and 3) with Cite Checker Workflow, can check whole pleading/brief and get a table based output showing viability, precedential value and whether the cite actually supports legal prop for which it is used. More info below. No charge to use, just have to be in legal (don't have be attorney though).
We’ve integrated @courtlistener (powered by @FreeLawProject) directly into Certera.AI.
Here are 3 ways to use it:
1️⃣ Real-Time Data Connector: Enable CourtListener before prompting so LLMs pull directly from court dockets.
2️⃣ Automated Cite Checker: If an AI output includes a citation, Certera automatically prompts you to cross-reference and verify it against CourtListener.
3️⃣ Citation Checker Workflow: Upload entire legal briefs or pleadings to get a structured analysis on validity, proposition support, and controlling vs. persuasive authority.
Learn more here: certera.ai/research/courtlis…
A Canadian legal braintrust! @JacobRobinsonJD & @scottastevenson
"I think it is genuinely the best time to be a lawyer that there's ever been."
@scottastevenson on why lawyers embracing AI are less disillusioned with their jobs.
" One of the reasons I co-founded @SpellbookLegal was because almost every lawyer I knew privately admitted to me over a beer that, 'Wow, like practicing law wasn't quite what I expected.'"
We just added Claude Opus 5 to @CerteraAI. Leaderboard is now live too. All the new models seem to leapfrog each other and then settle in.
We added @Anthropic's latest, Opus 5, to certera.ai. Want to see how it does against other LLMs on legal related prompts? Use custom mode to choose other models you want to compare.
We just added the new Google Gemini models to @CerteraAI. If you want to see how they perform on legal queries, you can use custom mode and compare them against most other LLMs. #lawtwitter
@GeminiApp 3.6 Flash and 3.5 Flash-Lite are now at Certera.AI. Compare outputs for your legal prompts against any other model (or test new Gemini models against each other). Let us know what you think! Like they used to say in Chicago, vote early and vote often!
We added the new Kimi K3 model to @CerteraAI 👇
Some report that the new @Kimi_Moonshot K3 performs better than Fable on some legal tasks. Want to find out for yourself? Use custom mode at certera.ai and select any model to compare.
We released the leaderboard this week. If you are in legal, please check it out. More inputs and feedback will increase ranking precision. Working on a practice area leaderboard and will release that soon.
Leader board is live. If you are a legal professional (don't have to be an attorney, just work in the industry), please create an account and run some queries. More use=better accuracy. 56 models and counting including all new ones including Grok 4.5. certera.ai/leaderboard
Chad Main retweeted
The Replacements released ‘Pleased to Meet Me’ 39 years ago on July 7, 1987 | Listen to the album + revisit our tribute here: album.ink/RplcmntsPTMM @TheReplacements
