shad42's submissions | Hacker News

1.		Automating the engineering work that isn't your product (mendral.com)
		2 points by shad42 3 days ago \| past \| discuss
2.		How we know if our agent is right (mendral.com)
		3 points by shad42 9 days ago \| past \| discuss
3.		Not update your dependencies in 2026 (mendral.com)
		1 point by shad42 18 days ago \| past
4.		Supply chain attacks don't wait for CVEs (mendral.com)
		3 points by shad42 22 days ago \| past
5.		We built an agent for CI despite using Claude Code for everything else (mendral.com)
		2 points by shad42 23 days ago \| past
6.		We built an agent specialized for CI (using the 3 Claude models) (mendral.com)
		2 points by shad42 29 days ago \| past
7.		How we know if our agent is right (mendral.com)
		2 points by shad42 34 days ago \| past
8.		How we know if our agent is right (mendral.com)
		5 points by shad42 40 days ago \| past
9.		The agent harness belongs outside the sandbox (mendral.com)
		182 points by shad42 42 days ago \| past \| 121 comments
10.		We decreased our LLM costs with Opus (mendral.com)
		106 points by shad42 46 days ago \| past \| 31 comments
11.		Multi-player agents don't fit in the sandbox (mendral.com)
		2 points by shad42 49 days ago \| past
12.		We built our AI agent, for analyzing CI logs (mendral.com)
		1 point by shad42 59 days ago \| past
13.		Same LLM, different agent: a CI debugger built on Claude (mendral.com)
		2 points by shad42 60 days ago \| past
14.		Agent Harness: Inside vs. Outside the Sandbox (mendral.com)
		3 points by shad42 63 days ago \| past
15.		Same LLM but different output: we built a CI specialist (mendral.com)
		1 point by shad42 67 days ago \| past
16.		We upgraded our agent to Opus and our costs went down (mendral.com)
		2 points by shad42 68 days ago \| past
17.		Same LLM, Different Agent: What Changes When You Specialize for CI (mendral.com)
		3 points by shad42 75 days ago \| past
18.		We decreased our LLM costs by switching to Opus (mendral.com)
		2 points by shad42 85 days ago \| past
19.		What CI looks like at a 100-person team (PostHog) (mendral.com)
		56 points by shad42 3 months ago \| past \| 30 comments
20.		We upgraded to a frontier model and our costs went down (mendral.com)
		1 point by shad42 3 months ago \| past
21.		We gave terabytes of CI logs to an LLM (mendral.com)
		233 points by shad42 3 months ago \| past \| 111 comments
22.		Anatomy of a Production AI Agent (mendral.com)
		2 points by shad42 3 months ago \| past
23.		What CI Looks Like at a 100-Person Team (mendral.com)
		3 points by shad42 3 months ago \| past
24.		What CI looks like at a 100-person team (mendral.com)
		4 points by shad42 4 months ago \| past
25.		Evals as Code: CI for LLMs with Dagger (dagger.io)
		2 points by shad42 10 months ago \| past \| 1 comment
26.		CPython internals: A 10 hour walk through the Python interpreter source (2014) (pgbovine.net)
		9 points by shad42 on June 2, 2015 \| past
27.		DockerBoot: Boot your machine with a fig.yml and docker (github.com/samalba)
		2 points by shad42 on March 1, 2015 \| past
28.		IPython 2.0 released (ipython.org)
		1 point by shad42 on April 3, 2014 \| past \| 1 comment
29.		The Key Rules Behind Every Great Startup Idea (businessinsider.com)
		5 points by shad42 on Jan 1, 2014 \| past \| 2 comments
30.		OpenStack 2013.2 ("Havana") is released (openstack.org)
		8 points by shad42 on Oct 17, 2013 \| past \| 2 comments
		More