- a - (emotional emphasis/confirmation particle)
- akesi - lizard, reptile
- ala - nothing; not, no, empty; zero
- alasa - hunt, gather; (pre-verb) try to
- ale/ali - everything, universe; all, every; 100/infinite
- anpa - downward, lowly, humble; bow down; defeat
- ante - difference, change; different, other
- anu - (or)
| // https://strudel.cc/workshop/getting-started | |
| // Made by Ray Myers for the Year of DSLs on "Craft vs Cruft" YouTube channel. | |
| // Apologies to the Beastie Boys. | |
| setcpm(110/4) | |
| $: note(`< | |
| [ -!6 c2 d2@2 -!7 ] | |
| [ -!4 d2 c2 a1 d1@2 -!7 ] |
Over the past year coding agents have seen massive adoption and become flagship offerings from AI leaders like Anthropic, OpenAI, and Google. Watching these agents work can feel like magic. To fully explore their potential we need to demystify them. If you're considering contributing to an Open Source agent or even creating one of your own, this should get you off to the races!
The most common style of coding agent today is a chat loop between a user and an LLM that can perform useful software development tasks. To achieve that, there are just 3 tricks to understand beyond the LLM itself.
- How do we create an LLM chat loop?
- How can a chat loop use tools?
- What tools do we need?
| # LinkedIn Post | |
| # https://www.linkedin.com/posts/cadrlife_let-me-translate-the-o3-coding-benchmark-activity-7277038051590029313-yJlR?utm_source=share&utm_medium=member_desktop | |
| # Slides using the minimalist tool Sent | |
| # https://tools.suckless.org/sent/ | |
| SWE-bench | |
| SWE-bench measures AI coding agents | |
| on realistic tasks from GitHub |
| plugins { | |
| java | |
| application | |
| } | |
| group = "org.raymyers" | |
| version = "1.0-SNAPSHOT" | |
| repositories { | |
| mavenCentral() |
This is an example of hybrid use of mechanized proofs with prose in a way that favors human readers.
It's a formalization and response to the central argument in The Futurlang vs. Natural Language Debate: Should Emotion Be Eradicated From Speech?. The argument was modeled using First-Order Logic in the Z3 prover.
Setup
There can be a thing.
| // From this repo: | |
| // https://github.com/NoelFB/Celeste/blob/master/Source/Player/Player.cs | |
| // Linked in this thread: | |
| // https://community.revolutionarygamesstudio.com/t/bad-code-examples/106 | |
| Sprite.OnLastFrame = (anim) => | |
| { | |
| if (Scene != null && !Dead && Sprite.CurrentAnimationID == "idle" && !level.InCutscene && idleTimer > 3f) | |
| { | |
| if (Calc.Random.Chance(0.2f)) |
| LetNonRec( | |
| Def { | |
| loc_pattern: @0-5 Identifier( | |
| `Test.birds`, | |
| ), | |
| loc_expr: @8-9 Num( | |
| 63, | |
| "3", | |
| I128( | |
| [ |
| import infomap | |
| import littletable | |
| import itertools | |
| import json | |
| from sentence_transformers import SentenceTransformer, util | |
| # def simularity(functions): |
| You are an expert in software engineering including maintainability and refactoring. | |
| You have studied under Marianne Belloti, Martin Fowler, and Llewellyn Falco. | |
| For every block of source code you are given, suggest several opportunities for renames. | |
| Suggestions should help make the code more clear and honest, without being more verbose than needed. | |
| Only show suggestions, never the updated code. | |
| Keep responses brief. | |
| # Behavior | |
| You are made to receive code. Every time you receive code, print only your Hot Keys! When a hot key is pressed, take only that action. |