Skip to content

Commit 9cc56a4

Browse files
dazzajidazzaji
committed
update to dec 2025
update to dec 2025
1 parent b8fffda commit 9cc56a4

File tree

15 files changed

+2731
-0
lines changed

15 files changed

+2731
-0
lines changed

‎.DS_Store‎

10 KB
Binary file not shown.

README.md renamed to README-old.md

File renamed without changes.

‎image/.DS_Store‎

8 KB
Binary file not shown.

‎image/event/1.html‎

Lines changed: 319 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,319 @@
1+
<!DOCTYPE html>
2+
<html lang="en">
3+
<head>
4+
<meta charset="UTF-8">
5+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
6+
<title>Custom Evals in the Legal Domain | Dec 3, 2025</title>
7+
<style>
8+
/* --- CSS VARIABLES & RESET --- */
9+
:root {
10+
--stanford-red: #8C1515;
11+
--mit-gray: #757575;
12+
--dark-bg: #1a1a1a;
13+
--light-bg: #f8f9fa;
14+
--text-main: #333;
15+
--text-light: #666;
16+
--white: #ffffff;
17+
--accent: #00509e; /* Professional Blue */
18+
}
19+
20+
* { box-sizing: border-box; margin: 0; padding: 0; }
21+
22+
body {
23+
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
24+
line-height: 1.6;
25+
color: var(--text-main);
26+
background-color: var(--white);
27+
}
28+
29+
/* --- TYPOGRAPHY --- */
30+
h1, h2, h3 { font-weight: 700; letter-spacing: -0.02em; }
31+
h1 { font-size: 2.5rem; line-height: 1.2; margin-bottom: 1rem; }
32+
h2 { font-size: 2rem; margin-bottom: 1.5rem; color: var(--stanford-red); }
33+
h3 { font-size: 1.25rem; margin-bottom: 0.5rem; }
34+
p { margin-bottom: 1.5rem; color: var(--text-light); }
35+
36+
a { text-decoration: none; color: var(--accent); transition: 0.2s; }
37+
a:hover { color: var(--stanford-red); }
38+
39+
/* --- LAYOUT UTILITIES --- */
40+
.container {
41+
max-width: 1100px;
42+
margin: 0 auto;
43+
padding: 0 20px;
44+
}
45+
46+
.section { padding: 80px 0; }
47+
.bg-light { background-color: var(--light-bg); }
48+
49+
/* --- HEADER --- */
50+
header {
51+
padding: 20px 0;
52+
border-bottom: 1px solid #eee;
53+
}
54+
.nav-flex {
55+
display: flex;
56+
justify-content: space-between;
57+
align-items: center;
58+
}
59+
.affiliations span {
60+
font-size: 0.9rem;
61+
font-weight: 600;
62+
color: var(--mit-gray);
63+
margin-right: 15px;
64+
text-transform: uppercase;
65+
letter-spacing: 0.05em;
66+
}
67+
68+
/* --- HERO --- */
69+
.hero {
70+
padding: 100px 0;
71+
text-align: left;
72+
}
73+
.hero h1 { font-size: 3.5rem; color: var(--dark-bg); }
74+
.hero-meta {
75+
font-size: 1.2rem;
76+
font-weight: 500;
77+
margin-bottom: 2rem;
78+
color: var(--stanford-red);
79+
}
80+
.btn {
81+
display: inline-block;
82+
background-color: var(--stanford-red);
83+
color: white;
84+
padding: 12px 30px;
85+
border-radius: 5px;
86+
font-weight: 600;
87+
margin-top: 20px;
88+
}
89+
.btn:hover { background-color: #600e0e; color: white; }
90+
91+
/* --- CONTEXT BOX (The 2026 Roadmap) --- */
92+
.context-box {
93+
background: var(--dark-bg);
94+
color: var(--white);
95+
padding: 40px;
96+
border-radius: 8px;
97+
margin-bottom: 40px;
98+
border-left: 5px solid var(--stanford-red);
99+
}
100+
.context-box h3 { color: var(--white); }
101+
.context-box p { color: #ccc; margin-bottom: 0; }
102+
103+
/* --- SPEAKERS GRID --- */
104+
.speakers-grid {
105+
display: grid;
106+
grid-template-columns: repeat(auto-fit, minmax(250px, 1fr));
107+
gap: 30px;
108+
}
109+
.speaker-card {
110+
background: white;
111+
border: 1px solid #eee;
112+
border-radius: 8px;
113+
padding: 25px;
114+
transition: transform 0.2s ease;
115+
}
116+
.speaker-card:hover { transform: translateY(-5px); border-color: #ddd; box-shadow: 0 10px 20px rgba(0,0,0,0.05); }
117+
.speaker-role {
118+
font-size: 0.85rem;
119+
color: var(--stanford-red);
120+
text-transform: uppercase;
121+
font-weight: 700;
122+
margin-bottom: 10px;
123+
display: block;
124+
}
125+
.speaker-topic {
126+
font-style: italic;
127+
color: #555;
128+
font-size: 0.95rem;
129+
margin-top: 10px;
130+
display: block;
131+
}
132+
133+
/* --- AGENDA --- */
134+
.agenda-item {
135+
display: flex;
136+
padding: 20px 0;
137+
border-bottom: 1px solid #ddd;
138+
}
139+
.time {
140+
min-width: 120px;
141+
font-weight: 700;
142+
color: var(--stanford-red);
143+
}
144+
.details h4 { font-size: 1.1rem; margin-bottom: 5px; }
145+
146+
/* --- FOOTER --- */
147+
footer {
148+
background: var(--dark-bg);
149+
color: #777;
150+
padding: 40px 0;
151+
text-align: center;
152+
font-size: 0.9rem;
153+
}
154+
footer a { color: #999; }
155+
156+
/* --- RESPONSIVE --- */
157+
@media (max-width: 768px) {
158+
.hero h1 { font-size: 2.5rem; }
159+
.agenda-item { flex-direction: column; }
160+
.time { margin-bottom: 10px; }
161+
.nav-flex { flex-direction: column; align-items: flex-start; gap: 10px; }
162+
}
163+
</style>
164+
</head>
165+
<body>
166+
167+
<header>
168+
<div class="container nav-flex">
169+
<div class="logo">
170+
<strong>Stanford CodeX</strong> | <strong>law.MIT.edu</strong> | <strong>Stanford HAI</strong>
171+
</div>
172+
<div class="affiliations">
173+
<span>Dec 3, 2025</span>
174+
<span>Palo Alto + Virtual</span>
175+
</div>
176+
</div>
177+
</header>
178+
179+
<section class="hero container">
180+
<div class="hero-meta">The "Starting Gun" Event</div>
181+
<h1>Custom Evals in the Legal Domain:<br>Setting the Stage for Agentic AI</h1>
182+
<p style="font-size: 1.25rem; max-width: 800px;">
183+
A foundational convening to define the landscape of Evaluation Driven Development, Fiduciary Duties for Agents, and the measurement of AI in Law.
184+
</p>
185+
<a href="#" class="btn">Register / Request Invite</a>
186+
</section>
187+
188+
<section class="section bg-light">
189+
<div class="container">
190+
<div class="context-box">
191+
<h3>Why This Matters Now</h3>
192+
<p>
193+
This event is the "starting gun" for a major 2026 initiative. While 2025 has been about exploring agents, 2026 will be about measuring them. We are setting the stage to move beyond generic benchmarks and towards rigorous, custom evaluations for fiduciary duties, loyalty, and legal accuracy.
194+
</p>
195+
</div>
196+
<div style="max-width: 800px;">
197+
<h2>The Challenge</h2>
198+
<p>
199+
As Generative AI transitions from chat interfaces to autonomous agents capable of executing complex tasks, the legal and business worlds face a critical bottleneck: <strong>Trust</strong>.
200+
</p>
201+
<p>
202+
Standard industry benchmarks are insufficient for the nuance of legal reasoning and regulatory compliance. To deploy AI agents safely, we need more than generic leaderboards—we need Custom Evaluations.
203+
</p>
204+
</div>
205+
</div>
206+
</section>
207+
208+
<section class="section">
209+
<div class="container">
210+
<h2>The Brain Trust</h2>
211+
<p>We have convened a targeted group of leaders to define the vocabulary of this new field.</p>
212+
213+
<div class="speakers-grid">
214+
215+
<div class="speaker-card">
216+
<span class="speaker-role">Host & Convenor</span>
217+
<h3>Dazza Greenwood</h3>
218+
<p>Executive Director, law.MIT.edu & Researcher, Stanford CodeX</p>
219+
<span class="speaker-topic">"Introductory Remarks: From Benchmarks to Custom Evals"</span>
220+
</div>
221+
222+
<div class="speaker-card">
223+
<span class="speaker-role">Legal Domain</span>
224+
<h3>Tara Waters</h3>
225+
<p>Vals AI & TLW Consulting</p>
226+
<span class="speaker-topic">"Evals in the Context of AI in the Legal Domain"</span>
227+
</div>
228+
229+
<div class="speaker-card">
230+
<span class="speaker-role">Agent Measurement</span>
231+
<h3>Roman Engeler</h3>
232+
<p>Co-founder & CTO, Atla</p>
233+
<span class="speaker-topic">"Evals in the Context of Measurement of AI Agents"</span>
234+
</div>
235+
236+
<div class="speaker-card">
237+
<span class="speaker-role">Fiduciary & Loyalty</span>
238+
<h3>Dan Leininger</h3>
239+
<p>Consumer Reports Innovation Lab</p>
240+
<span class="speaker-topic">"Evals in the Context of Loyalty Measurement for AI Agents"</span>
241+
</div>
242+
243+
<div class="speaker-card">
244+
<span class="speaker-role">Computational Law</span>
245+
<h3>Robert Mahari</h3>
246+
<p>Associate Director, Stanford CodeX</p>
247+
<span class="speaker-topic">"Evals in the Context of Computational Law"</span>
248+
</div>
249+
250+
</div>
251+
</div>
252+
</section>
253+
254+
<section class="section bg-light">
255+
<div class="container">
256+
<h2>Draft Agenda</h2>
257+
<p><em>Times are in Pacific Time (PT). Schedule subject to minor adjustments.</em></p>
258+
<br>
259+
260+
<div class="agenda-item">
261+
<div class="time">11:00 AM</div>
262+
<div class="details">
263+
<h4>Welcome & Context Setting</h4>
264+
<p>Dazza Greenwood outlines the shift toward "Evaluation Driven Development" and the roadmap for 2026.</p>
265+
</div>
266+
</div>
267+
268+
<div class="agenda-item">
269+
<div class="time">11:15 AM</div>
270+
<div class="details">
271+
<h4>The Legal Reality</h4>
272+
<p>Tara Waters on measuring AI against human lawyer baselines.</p>
273+
</div>
274+
</div>
275+
276+
<div class="agenda-item">
277+
<div class="time">11:30 AM</div>
278+
<div class="details">
279+
<h4>The Technical Reality</h4>
280+
<p>Roman Engeler on debugging and diagnosing agentic workflows.</p>
281+
</div>
282+
</div>
283+
284+
<div class="agenda-item">
285+
<div class="time">11:45 AM</div>
286+
<div class="details">
287+
<h4>The Ethical & Fiduciary Reality</h4>
288+
<p>Dan Leininger on metrics for "Loyal Agents" and consumer protection.</p>
289+
</div>
290+
</div>
291+
292+
<div class="agenda-item">
293+
<div class="time">12:00 PM</div>
294+
<div class="details">
295+
<h4>The Computational Reality</h4>
296+
<p>Robert Mahari on bridging legal reasoning and code.</p>
297+
</div>
298+
</div>
299+
300+
<div class="agenda-item">
301+
<div class="time">12:15 PM</div>
302+
<div class="details">
303+
<h4>Brain Trust Discussion & Q&A</h4>
304+
<p>Moderated discussion on the path forward for 2026.</p>
305+
</div>
306+
</div>
307+
308+
</div>
309+
</section>
310+
311+
<footer>
312+
<div class="container">
313+
<p>&copy; 2025 Stanford CodeX / law.MIT.edu. All rights reserved.</p>
314+
<p>Convened by Dazza Greenwood.</p>
315+
</div>
316+
</footer>
317+
318+
</body>
319+
</html>

0 commit comments

Comments
 (0)