You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
There are 3 programming assignments in this course ranging from traditional program synthesizer to coding LLMs and coding LLM Agents.
30
+
The assignment skeleton code is hosted on Github.
31
+
The links below will lead you to Github repositories.
32
+
Please follow the instructions in <code>readme.md</code> for each of the assignment.
33
+
</p>
34
+
<p>
35
+
<strong>Policy:</strong>
29
36
All assignments are released when the course starts and can be submitted through GradeScope anytime before the deadline.
30
-
Late submissions will be penalized 10% per day up to 5 days.
37
+
Late submissions will be penalized 20% per day up to 3 days.
31
38
Collaboration is allowed, but you must cite your collaborators in the submission, and the submission must be your own work.
32
39
</p>
33
40
<p>
34
-
Extensions are allowed, but you must request an extension in advance via email to the instructor (<ahref="mailto:ziyang@cs.jhu.edu">ziyang@cs.jhu.edu</a>).
35
-
The maximum extension is 2 days.
36
-
No extensions will be granted for late submissions.
41
+
Extensions are allowed, but you must request an extension in advance via email to the instructor (<ahref="mailto:ziyang@cs.jhu.edu">ziyang@cs.jhu.edu</a>) or the TA (<ahref="mailto:fwang60@jh.edu">fwang60@jh.edu</a>).
42
+
The maximum extension is 2 days, and late submission can still be used on extended deadlines.
43
+
No extensions will be granted after the normal deadline.
37
44
</p>
38
45
<p>
46
+
<strong>API keys for LLM use:</strong>
39
47
Each enrolled and auditing student is granted an API key for a large language model for the assignments.
40
-
You can use the API key to access the language model in your assignments;
41
-
the code that setup the client is provided in the assignment skeleton code (Assignment 2 and Assignment 3).
48
+
You can use the API key to access the language model in your assignments;
49
+
the code that setup the client is provided in the assignment skeleton code.
42
50
</p>
43
51
<p>
52
+
<strong>Use of AI for programming assignment:</strong>
44
53
In light of the theme of the course, <strong>we encourage you to use LLMs to help you with the coding assignments</strong>.
45
54
However, you should not rely on LLMs to do the entire assignment for you.
46
55
You should understand the code you write, and be able to explain it to others.
47
-
In case an LLM is used, you should keep a record of the conversation with the LLM, and include it in the submission.
56
+
In case an LLM is used, you should keep a record of the conversation with the LLM, and include it in the submission (usually under a file named `acknowledgements.md`).
57
+
Please refer to the detailed instruction in each assignment.
48
58
</p>
49
59
<ulclass="assignments">
50
-
<li><ahref="assignment1.html"><strong>Assignment 1:</strong> Enumerative program synthesis</a><em>(Due: TBD)</em></li>
51
-
<li><ahref="assignment2.html"><strong>Assignment 2:</strong> Evaluating LLMs on program synthesis</a><em>(Due: TBD)</em></li>
<li><ahref="https://github.com/machine-programming/assignment-3" target="_blank"><strong>Assignment 3:</strong> Coding Agents</a><em>(Due: Oct 9, 2025; Late Due: Oct 12, 2025)</em></li>
0 commit comments