Jean-Michel Lemieux

7.2K posts

Jean-Michel Lemieux banner
Jean-Michel Lemieux

Jean-Michel Lemieux

@jmwind

Full time apprentice human. Building at @SpellbookLegal

Ottawa ⮕ 🇨🇦 Katılım Mart 2009
214 Takip Edilen49K Takipçiler
Sabitlenmiş Tweet
Jean-Michel Lemieux
Jean-Michel Lemieux@jmwind·
Joined a new AI-native company this week and it’s kind of wild how different it feels already. The laptop arrived, I logged in, and an agent basically took over from there. It set up my dev env, pulled repos, fixed dependency issues, got permissions approved, pointed me at the backlog, linked the architecture docs, and surfaced the Slack debates I actually needed to read before touching production. When I needed context on something, I asked the agent and it found the exact thread from months ago explaining why a decision was made, who owned it, the related Linear issues, and the PRs connected to it. I’ve only been here 3 days but it honestly feels like I’ve worked here for a year because the usual friction and scavenger hunt for context just isn’t there anymore. We should probably stop calling this “onboarding” and rename it to “mounting” because this feels a lot more like mounting a distributed filesystem called “institutional memory” than slowly getting drip-fed context over 6 months.
English
274
409
6.3K
1M
Jean-Michel Lemieux
Jean-Michel Lemieux@jmwind·
Happy Canada Day!! Sorry if all the stereotypes turned out to be true 🇨🇦
Jean-Michel Lemieux tweet media
English
2
2
47
4.8K
Jean-Michel Lemieux
Jean-Michel Lemieux@jmwind·
Fable 5 still with 30-day retention, no ZDR for enterprises. Keep away from your code base.
Jean-Michel Lemieux@jmwind

Fable 5 is a Trojan horse. I thought everyone saw it. After a bunch of conversations with CTOs and CEOs this week, I realized many didn't. Anthropic has been one of the best platform partners in AI. They understood something early that others missed: nobody is going to build serious enterprise software on top of you without trust. Audited ZDR, strong enterprise controls, clear boundaries around customer data. That trust paid off and we built on them because of it. At the same time, this is a brutally competitive market. Anthropic has great models, great marketing, strong distribution, and enormous mindshare. But there is no world where model performance stays differentiated forever. Token costs will fall. Inference gets optimized. New models arrive. The model layer is a knife fight. So where do you go next? You move up the stack. They didn't hide this at all and they started working on it. They realized it’s a hard problem. Business workflows, the software up the stack isn’t trivial. Our APIs aren’t text in, text out. We have build businesses around the messy way in which the world works. I think they realized that it's harder than they thought. Now enter Mythos. They launched it as a too good to share because it finds vulnerabilities in your code. The pitch is almost impossible for a CTO to ignore: point it at your codebase and it will find vulnerabilities, security issues, and bugs that your team missed. They beat that drum for a few months. They even leaked some of the findings to the large tech companies, which would pull the smaller ones into security war-rooms with them to make plans on how to use Mythos when it launches. The frenzy was building. The first thing most software companies will do when it launches is exactly that. They won't upload customer data. They'll upload their source code. Their crown jewels. Then Fable 5 is released, ZDR is altered, what do you think every CTO did? Insane.

English
2
0
37
19.2K
Jean-Michel Lemieux
Jean-Michel Lemieux@jmwind·
I've spent the last few weeks buried in this codebase and it's been fascinating building a system which is essentially invisible. Our goal is that contracts shouldn't wait for a human to open it, but also involves a human deeply when needed. This is one of the more interesting engineering problems I've worked on.
Scott Stevenson@scottastevenson

Today we're launching @SpellbookLegal's biggest thing yet: Autonomous Contract Management It’s the first end-to-end AI infrastructure for contracts The world is speeding up. We are in one of the biggest investment cycles in decades. Behind every rocket launch, FIFA game, and datacenter, lies a web of hundreds of agreements. Agreements are the invisible threads that allow us to work together. We have infrastructure for finance (Stripe, Ramp), eCommerce (Shopify) and many business functions. But agreement infrastructure is lacking. This creates a painful bottleneck on our ability to work together. Online purchases take milliseconds. But agreements still take weeks. CLMs were supposed to be the answer, but were designed in a pre-AI era. AI fundamentally changed how computers can accelerate agreements. Spellbook is the most used AI contract review tool in the world, with ~5,000 customers in 80 countries Now we are expanding to deliver the first end-to-end, AI native stack for contracts. From the moment a deal lands in your inbox, to the day it renews years later, Spellbook’s AI supports teams every step of the way, across all business teams. It runs 24/7. While you sleep, it's reading the deals that came in overnight, flagging the parts that actually need a lawyer, and clearing the busywork that used to kill mornings. Nothing gets handed off between systems or slips after signature, and the intelligence stays with you for the life of the contract. AI for lawyers is great. There are 20 million lawyers in the world, and many are our users. But there are billions who touch contracts. We're excited to help everyone move faster and do more of what they love, by building the best AI-powered contract infrastructure in the world. Get early access: spellbook.com/acm

English
1
1
21
8.2K
Jean-Michel Lemieux
Jean-Michel Lemieux@jmwind·
It's actually a small change. Pre-ai-epoch me would have been embarrassed to open this size of PR. @graphite is growing on me.
Jean-Michel Lemieux tweet media
English
1
2
19
5.1K
Jeromy Sonne
Jeromy Sonne@JeromySonne·
@jmwind Mostly sentiment. How bombastic they speak versus how hedged the language in their filings are. Lots of hiding behind complexity and jargon too. (WIP progress so possibly other signals too)
English
1
0
1
123
Jean-Michel Lemieux
Jean-Michel Lemieux@jmwind·
New startup idea. An ETF that shorts companies solely based on the quality of their SEC fillings? This one is gold: angry note mid-clause signed by CFO, filed with SEC, and left on EDGAR 20+ years. The bank was shut down by regulators in 2019. Make of that what you will. Anyone want to work on this with me? spellbook.com/labs
Jean-Michel Lemieux tweet media
English
13
4
89
25K
Brendan Samek
Brendan Samek@brendan_samek·
@jmwind It's crazy what you find when you actually read the things. I've been doing some work to automatically extract all the KPIs that governments put out and then graph it and some of the shit is nuts when you look at the whole story instead of a snapshot
English
1
0
3
571
Jeromy Sonne
Jeromy Sonne@JeromySonne·
@jmwind I actually have noticed a massive delta in fraud rates between how the CEO and CFO speak publicly versus the language used in their public filings. Working on getting an AI agent to flag this sort of thing as anomalous inside my product.
English
2
0
2
733
Jaseem Hasib
Jaseem Hasib@Jaseemh·
@jmwind Track CEOs that are talking about specific goals and give updates. What metrics they talk about tracking. Track excuses they give for why they don't hit numbers. Find how they talk about employees and the stories they tell.
English
1
0
4
117
Jean-Michel Lemieux
Jean-Michel Lemieux@jmwind·
@MattMickiewicz sometimes correlation is really funny. we found a few other egregious examples, no scientific backtesting yet.
English
0
0
4
504
Jaseem Hasib
Jaseem Hasib@Jaseemh·
@jmwind Been working with NLP on SEC filings and earnings transcripts for a while. Interesting ways to extract insights for sure.
English
2
0
5
707
Jean-Michel Lemieux
Jean-Michel Lemieux@jmwind·
Hey @karrisaarinen, friendly heads-up from the field. I've received 6+ emails from someone on your sales team with comical AI-slop. Wrong company name & already a customer, etc... Always love a good laugh, but you may want to skip-level this one?
Jean-Michel Lemieux tweet media
English
8
0
704
163.7K
Jean-Michel Lemieux
Jean-Michel Lemieux@jmwind·
@the_mewc @karrisaarinen Like outages, we all have them. Not trying to blame one person. We have to share our lessons as we will have to write the SRE equivalent book so that we're protected as we increase AI usage everywhere.
English
2
0
11
1.3K
Jean-Michel Lemieux
Jean-Michel Lemieux@jmwind·
Thanks!!! I've been thinking we should treat slop as "incidents" like we did with outages. When you're ready, would love to hear a retro on the issue. I've been checking our outreach process as well to ensure we didn't have anything like this happening with our BDR team. The challenge is that everyone has Cowork hooked up to their emails and it's out of control.
English
4
0
93
12.3K
Karri Saarinen
Karri Saarinen@karrisaarinen·
@jmwind Thanks and apologies. Not ideal, will check with the team what caused this. Agree that emailing existing customers and 6 times is the dumbest thing
English
3
0
186
17.9K