Founder @litvue building real autonomous legal work product
Joined September 2017
- Tweets8.2K
- Following727
- Followers924
- Likes18.8K
I spent 4-6 months of this year exploring this concept deeply only to conclude it was a giant waste of time. Maybe I should revisit.
At @harvey, we're expanding our investment in structured legal data with Fact Graph: facts, sources, and relationships that stay linked as evidence changes. This foundation will let our models work through complex matters over many steps, grounded in the record.
harvey.ai/blog/fact-graph-fo…
Finally caught up with @abraham_jmb live today and it was 1000% better than I expected (and my expectations were highhh)
Spend enough time close to legal work and ai adoption and you realize that all of this is deeply intimate to the firms and lawyers and no solution (read, vendor products) is truly one size fits all.
There's a lot of vague posting in legal tech right now. "We'll automate this." "This does it end to end, perfectly, every time." The reality is a lot more nuanced, and you see very few real examples.
Estate planning for example is easier to automate. They were already templates. The context per engagement is limited and the rules are basically if then statements.
Most of law isn't like that. When the answer is "it depends," the model needs a lot more context to fill in the blanks about what it depends on and models getting smarter is partly a detriment here.
They now know when a dependency sits outside the context they were given, so instead of guessing, the output stalls or goes off track.
That's why the big legal tech companies are sitting on older models. One of the biggest was defending still using Gemini 2.5 pro a few months ago. It isn't cost. They tuned a consistent result with the harness and the context they built at the time, and every new frontier model means redoing all of that harness engineering.
My prediction is a plateau in publicly released models. Anthropic keeps giving the frontier away. Kimi K3.1 Pro is distilled from Opus 5.5. It's the soul of it, doing Opus 5.5 quirks.
Kimi is an amazing model. The cost per unit of intelligence value is phenomenal.
So we hit a fork. Do we want more intelligence, or a model that's better at the task and context we're actually asking it to handle?
We'll pay more for the second one, even while the cost per unit of intelligence per token plummets.
What we want is predictable intelligence: a system that doesn't change every three weeks. In legal, you can't redo your harness engineering every three weeks. And it's not unique to legal. It's all of us pushing the frontier day after day looking for consistency.
#legaltech
For knowledge work we’re at the stage where your initial question should be asking how a human would do this task and then work backwards to apply an agent to it.
This works especially well greenfield tasks.
A lot of my success working with agents I attribute to being a naturally curious person. Most of my sessions begin with a series of questions that prime the context and I build on until I’m happy with the result.
My initial impressions of @claudeai Duet are very positive. Quick thoughts:
1) great name
2) smooth and polished ui/ux
3) organizing around tasks as a primitive is excellent and I expect widespread adoption among other tools
4) the tie in with “make” as the third tab also aligns with how I think about using ai agents
5) still not sure how to use channels
6) i think a tie in with the new projects beta is much needed and should probably replace channels
Great work @ClaudeDevs
I was too early lawlint.com
maybe I'll rewrite it using Jev
Datacenter development but everyone living in an X mile radius gets free power for life. Anyone tried this yet?
Seth Fenster retweeted
There are so many heartbreaking stories to be reread and remembered on this anniversary of Oct 7th. Not sure there is much one can add to find or create meaning. Except one thing, every time.
Am Yisroel Chai!
