Hacker News: jrvarela56

New comment by jrvarela56 in "Ask HN: How to solve the cold start problem for a two-sided marketplace?"

jrvarela56 — Mon, 20 Apr 2026 16:04:32 +0000

A key term is ‘single player value’. One type of user needs to get benefits out of this marketplace as a tool so that you can use that engagement to solve the chicken and egg problem.

New comment by jrvarela56 in "Changes in the system prompt between Claude Opus 4.6 and 4.7"

jrvarela56 — Mon, 20 Apr 2026 07:06:04 +0000

Not sure if you mean 1) sub-agent definitions (similar to skills in Claude Code) or 2) CLI scripts that use other coding agents (eg claude calling gemini via cli).

For (1) I'm trying to come up with a simple enough definition that can be 'llm compiled' into each format. Permissions format requires something like this two and putting these together some more debugging.

(2) the only one I've played with is `claude -p` and it seems to work for fairly complex stuff, but I run it with `--dangerously-skip-permissions`

New comment by jrvarela56 in "Changes in the system prompt between Claude Opus 4.6 and 4.7"

jrvarela56 — Mon, 20 Apr 2026 06:49:41 +0000

I implemented a client for each so that the session history is easy to extract regarding the agent (somewhat related to progress of goal).

Context: AGENTS.md is standard across all; and subdirectories have their AGENTS.md so in a way this is a tree of instructions. Skills are also standard so it's a bunch of indexable .md files that all agents can use.

New comment by jrvarela56 in "Changes in the system prompt between Claude Opus 4.6 and 4.7"

jrvarela56 — Mon, 20 Apr 2026 06:48:03 +0000

I'm leaning in this direction. Recently slopforked pi to python and created a version that's basically a loop, an LLM call to openrouter and a hook system using pluggy. I have been able to one-shot pretty much any feature a coding agent has. Still toy project but this thread seems to be leading me towards mantaining my own harness. I have a feeling it will be just documenting features in other systems and maintaining evals/tests.

New comment by jrvarela56 in "Changes in the system prompt between Claude Opus 4.6 and 4.7"

jrvarela56 — Mon, 20 Apr 2026 05:35:51 +0000

The past month made me realize I needed to make my codebase usable by other agents. I was mainly using Claude Code. I audited the codebase and identified the points where I was coupling to it and made a refactor so that I can use either codex, gemini or claude.

Here are a few changes:

1. AGENTS.md by default across the codebase, a script makes sure CLAUDE.md symlink present wherever there's an AGENTS.md file

2. Skills are now in a 'neutral' dir and per agent scripts make sure they are linked wherever the coding agent needs them to be (eg .claude/skills)

3. Hooks are now file listeners or git hooks, this one is trickier as some of these hooks are compensating/catering to the agent's capabilities

4. Subagents and commands also have their neutral folders and scripts to transform and linters to check they work

5. `agent` now randomly selects claude|codex|gemini instead of typing `claude` to start a coding session

I guess in general auditing where the codebase is coupled and keeping it neutral makes it easier to stop depending solely on specific providers. Makes me realize they don't really have a moat, all this took less than an hour probably.

New comment by jrvarela56 in "Creating West Coast Buddhism (2024)"

jrvarela56 — Mon, 30 Mar 2026 04:54:45 +0000

I guess then if you did not receive instruction from the Buddha himself you cannot call yourself a true buddhist.

New comment by jrvarela56 in "Claude Code runs Git reset –hard origin/main against project repo every 10 mins"

jrvarela56 — Sun, 29 Mar 2026 23:52:12 +0000

It’s a feature not a bug!

New comment by jrvarela56 in "LLM Architecture Gallery"

jrvarela56 — Sun, 15 Mar 2026 23:47:43 +0000

Would be awesome to see something like this for agents/harnesses

New comment by jrvarela56 in "Claws are now a new layer on top of LLM agents"

jrvarela56 — Sun, 22 Feb 2026 06:52:03 +0000

Agree, i was going the vaultwarden route and figured this pattern seems better: https://fly.io/blog/tokenized-tokens/

Secrets are encrypted and the proxy decrypts on the fly if destination is whitelisted for that token.

New comment by jrvarela56 in "Claws are now a new layer on top of LLM agents"

jrvarela56 — Sun, 22 Feb 2026 06:25:39 +0000

the LLM can use types just like the human

New comment by jrvarela56 in "Claude Code for Infrastructure"

jrvarela56 — Thu, 05 Feb 2026 08:44:12 +0000

The problem we have as software engineers (from an entrepreneur's pov) is that we mostly struggle with stuff that's removed from the client's problem.

I mean it in terms of owning the solution to a problem, being accountable/responsible for something working e2e not just the software or even the product - the service/experience of the customer that makes them want to give you money. Once you put on another hat - guess what - you'd probably be the star of some operations team or a great supervisor of some department. You would automate everything around you to a point others think you're the most capable person they've ever seen in that role.

New comment by jrvarela56 in "Claude Code for Infrastructure"

jrvarela56 — Wed, 04 Feb 2026 20:32:45 +0000

I’ve been a year deep into my first job out of tech. There is a never ending slew of problems where being able to code, specially now with AI, means you have wizard-like powers to help your coworkers.

My codebase is full of one-offs that slowly but surely converge towards cohesive/well-defined/reusable capabilities based on ‘real’ needs.

I’m now starting to pitch consulting to a niche to see what sticks. If the dynamic from the office holds (as I help them, capabilities compound) then I’ll eventually find something to call ‘a product’.

New comment by jrvarela56 in "Deno Sandbox"

jrvarela56 — Wed, 04 Feb 2026 08:32:57 +0000

Just wrapped up my own module for this. Remixed my worktree workflow with a lima wrapper. I wanted to go head first to giving Claude Code full autonomy but realized capability and prevention need to go hand in hand

Next step for me is creating a secrets proxy like credit card numbers are tokenized to remove risk of exfiltrating credentials.

Edit: It’s nice that Deno Sandbox already does this. Will check it out.

New comment by jrvarela56 in "Anthropic blocks third-party use of Claude Code subscriptions"

jrvarela56 — Fri, 09 Jan 2026 06:17:43 +0000

If they believe it would get them AGI they would risk it.

New comment by jrvarela56 in "Wrapping my head around AI wrappers"

jrvarela56 — Thu, 20 Nov 2025 14:09:56 +0000

I agree with you in spirit but this harms the potential for these new products to emerge. You’re saying you don’t want them to be able to accrue a data moat. It sounds good for user privacy and optionality later on but it makes it harder for these services to get started as they dont see that model as possible.

New comment by jrvarela56 in "Hard drives on backorder for two years as AI data centers trigger HDD shortage"

jrvarela56 — Wed, 12 Nov 2025 07:00:52 +0000

If every other PC is more expensive, they will just increase prices.

New comment by jrvarela56 in "Uv is the best thing to happen to the Python ecosystem in a decade"

jrvarela56 — Thu, 30 Oct 2025 07:12:21 +0000

I have a directory called workspace where there’s a projects directory and the main area is for messing around. Just setup workspace once as a project.

New comment by jrvarela56 in "Context engineering is sleeping on the humble hyperlink"

jrvarela56 — Sat, 25 Oct 2025 02:46:49 +0000

Spot on, this is a solid abstraction to build upon. I always felt MCP was a misstep in comparison to OpenAI’s focus on OpenAPI specs. HATEOAS is the principle that has become more useful as agents drive applications.

New comment by jrvarela56 in "Some graphene firms have reaped its potential but others are struggling"

jrvarela56 — Mon, 13 Oct 2025 13:01:55 +0000

The AI of chemical engineering/material science?

New comment by jrvarela56 in "The death of industrial design and the era of dull electronics"

jrvarela56 — Mon, 06 Oct 2025 05:04:20 +0000

I think it’s a mix of social media and risk aversion, this article touches on the broader discussion as it impacts many kinds of design

https://www.alexmurrell.co.uk/articles/the-age-of-average