eterps

Consensus Statements:
- Climate change requires immediate action (strong agreement)

Divisive Statements:
- Nuclear power is necessary for clean energy
- Carbon tax should be implemented globally
- Individual actions matter for sustainability
- Companies should be held liable for emissions

Group Positions:

eterps

require 'sinatra'
require 'json'

TECH_TAGS = %w[javascript python ruby java rust golang react vue angular typescript]

get('/') { erb :index }
get('/suggest') { TECH_TAGS.grep(/#{params[:q]}/i).to_json }
get('/search') { erb :_results, layout: false, locals: { tags: params[:tags].to_s.split(',').reject(&:empty?) } }

__END__

eterps

<h1>I blog with minimal HTML</h1>

<p>published: 10/02/25 (dd/mm/yy)<br>
updated: not yet

<p>Inspired from <a href=https://devpoga.org/i-blog-with-raw-html">I blog in raw HTML</a>

<p>The blog you're reading is written in minimal HTML.

<p>This (english) blog is at it's first incarnation, the longest lived one (so far). But I have a french blog available too.

eterps

  {
    "mason-org/mason-lspconfig.nvim",
    opts = {
      ensure_installed = { 'basedpyright', 'ruff', 'prettierd', 'prettier', 'shfmt',
        'mdformat', 'standardrb', 'stylua', 'terraform-ls', 'tflint', 'yamlfmt' },
      automatic_enable = {
        exclude = { "lua_ls", "basedpyright" },
      }
    },
    dependencies = {

eterps

Understanding aico history: Managing the AI's Focus

The aico history commands are a powerful feature for controlling the context sent to the AI. Every time you run aico ask or aico edit, your entire active conversation history is sent along with your new prompt. This is how the AI "remembers" what you've discussed, such as a plan you created in a previous step.

However, as a conversation gets longer, the context can become very large. This has two main effects:

1. It increases cost and token usage. More history means a larger payload for the API call.
2. It can distract the AI. Early brainstorming or corrected mistakes might not be relevant to the current task, but the AI will still see them.

The aico history subgroup lets you solve this by telling aico: "For the next prompt, only use the conversation starting from this specific point." The older messages are not deleted; they are simply ignored for future API calls until you decide otherwise.