shad42's submissions | Hacker News

1.		How we know if our agent is right (mendral.com)
		3 points by shad42 4 days ago \| past \| discuss
2.		Not update your dependencies in 2026 (mendral.com)
		1 point by shad42 13 days ago \| past \| discuss
3.		Supply chain attacks don't wait for CVEs (mendral.com)
		3 points by shad42 17 days ago \| past
4.		We built an agent for CI despite using Claude Code for everything else (mendral.com)
		2 points by shad42 18 days ago \| past
5.		We built an agent specialized for CI (using the 3 Claude models) (mendral.com)
		2 points by shad42 24 days ago \| past
6.		How we know if our agent is right (mendral.com)
		2 points by shad42 29 days ago \| past
7.		How we know if our agent is right (mendral.com)
		5 points by shad42 35 days ago \| past
8.		The agent harness belongs outside the sandbox (mendral.com)
		182 points by shad42 37 days ago \| past \| 121 comments
9.		We decreased our LLM costs with Opus (mendral.com)
		106 points by shad42 41 days ago \| past \| 31 comments
10.		Multi-player agents don't fit in the sandbox (mendral.com)
		2 points by shad42 44 days ago \| past
11.		We built our AI agent, for analyzing CI logs (mendral.com)
		1 point by shad42 54 days ago \| past
12.		Same LLM, different agent: a CI debugger built on Claude (mendral.com)
		2 points by shad42 55 days ago \| past
13.		Agent Harness: Inside vs. Outside the Sandbox (mendral.com)
		3 points by shad42 58 days ago \| past
14.		Same LLM but different output: we built a CI specialist (mendral.com)
		1 point by shad42 62 days ago \| past
15.		We upgraded our agent to Opus and our costs went down (mendral.com)
		2 points by shad42 63 days ago \| past
16.		Same LLM, Different Agent: What Changes When You Specialize for CI (mendral.com)
		3 points by shad42 70 days ago \| past
17.		We decreased our LLM costs by switching to Opus (mendral.com)
		2 points by shad42 80 days ago \| past
18.		What CI looks like at a 100-person team (PostHog) (mendral.com)
		56 points by shad42 88 days ago \| past \| 30 comments
19.		We upgraded to a frontier model and our costs went down (mendral.com)
		1 point by shad42 3 months ago \| past
20.		We gave terabytes of CI logs to an LLM (mendral.com)
		233 points by shad42 3 months ago \| past \| 111 comments
21.		Anatomy of a Production AI Agent (mendral.com)
		2 points by shad42 3 months ago \| past
22.		What CI Looks Like at a 100-Person Team (mendral.com)
		3 points by shad42 3 months ago \| past
23.		What CI looks like at a 100-person team (mendral.com)
		4 points by shad42 3 months ago \| past
24.		Evals as Code: CI for LLMs with Dagger (dagger.io)
		2 points by shad42 9 months ago \| past \| 1 comment
25.		CPython internals: A 10 hour walk through the Python interpreter source (2014) (pgbovine.net)
		9 points by shad42 on June 2, 2015 \| past
26.		DockerBoot: Boot your machine with a fig.yml and docker (github.com/samalba)
		2 points by shad42 on March 1, 2015 \| past
27.		IPython 2.0 released (ipython.org)
		1 point by shad42 on April 3, 2014 \| past \| 1 comment
28.		The Key Rules Behind Every Great Startup Idea (businessinsider.com)
		5 points by shad42 on Jan 1, 2014 \| past \| 2 comments
29.		OpenStack 2013.2 ("Havana") is released (openstack.org)
		8 points by shad42 on Oct 17, 2013 \| past \| 2 comments
30.		Nginx Inc. raises $10M in Series B round (nginx.com)
		126 points by shad42 on Oct 15, 2013 \| past \| 45 comments
		More