| Focus the search field | / or ff |
|---|---|
| Clear filter | ESC ESC or cf |
| Refresh filter | rf |
| Tags | # or tag: |
| Due | ^ or due: |
| Color (priority) | color: or priority: |
| Assignee | @ or assignee: |
| Open or closed tasks | in: |
| Time created | created: |
| Time updated | updated: or changed: |
| Attachment, note | has: |
Combine keywords with search parameters. E.g. type in: closed and changed: last week to see what you completed last week.
Press Enter twice to search in all your lists.
- LLMs today: How good are they?
- Solving coding challenges

- Single prompt at its max:

- Source:
- New Bard vs GPT-4 (2023-09-20):
- Using web technologies, create a simple 2D physical simulation of a solar system with one planet. The planet should orbit around the center of the system.
- Set up a simple 20 fps game engine using setInterval()!
- Set up an area (a ) on the page for displaying the simulation! The planet will be displayed using an anotherinside the area. You can avoid displaying the star. - The model of the planet is its P = (x,y) position and V = (vx, vy) speed vector. The center star is fixed at C = (starx, stary) For the sake of simplicity, you do not need to use SI units. Use pixel coordinates directly! - One step of the simulation is defined by the following formulas: x += vx y += vy // The position is modified with the speed. distance =sqrt((starx - x)2 +(stary - y)2) force = G / distance2 // G is the gravitational constant vx += force * (starx -x) / distance vy += force * (stary -y) / distance //The speed is modified with the gravitational force - Set up the P, V and C vectors and G constant at the start of the simulation so that it looks nice. (E.g.: C=(100, 100), P=(200, 100), V=(0, 1), G= 500)
- GPT-4 solves it at first trial
- Bard almost solves it, but the code throws errors (2x trial, different errors). After fixing by a new prompt, it works.
- Working memory (input token count, e.g. 4K, 32K)
- In the kilobyte range (vs humans?)
- They need some 'attention' mechanism to work on large codebases
- Cognitive load they can bear (attention head count (128+) and dimension)
- Number of distinct commands
- Junior: 13 fixed + task
- How far the model must go from its training knowledge
- E.g. coding in less popular frameworks like Solid.js
- Discrepancies between commanded format and the current state
- E.g. After changing code style: "JavaScript files should only export named entities, do not use default exports"
- Possible solution: Do not command style, leave the code as generated.
- Failure modes
- Incorrectly specified prompt
"Render" -> set styles needed
Without "Do not create new files" it tries to factor the common part out, but fails (its hard to factor out styles, especially without more context)

- Cognitive load, e.g. doing multiple things (e.g.: feature + refactor) in the same prompt
- But often it works, e.g.:

- Guess: Too much cognitive load leads to failing to give attention to part of the input
- But often it works, e.g.:
- Solution: Clearly defined baby steps
- Approaches to LLM Coding
- One Prompt Generators (Automated Waterfall)
- GPT-Engineer
- Iterative Systems
- A few design questions
- How to pinpoint relevant parts of large codebases
- ctags
- Embedding (Indexing) the source code
- Manually
- Map (refactor)
- sweep ai
- Interaction style (UX)
- Focus on code (typically vscode based)
- Rift
- Focus on requirements (typically github based)
- Sweep
- Focus on Human-AI interaction (own UI or CLI)
- aider (CLI)
- Junior
- Focus on code (typically vscode based)
- How to construct prompts
- From source code directly
- Treat them as configuration
- When and how to use error auto-feedback, prompt chains, actor/critic etc.
- How to pinpoint relevant parts of large codebases
- A few design questions
- Junior Demo
- Colin Raffel
- Krisztián Schäffer
- aijunior.dev
Loading page ...Lists are fun!💡Copy any structured text and Ctrl+V it here
to create a listDue date dd
Tags tt
- #{manage_items}
You need a PRO account to manage tags:
- Change tag colour
- Rename/merge tags
- Change tag visibility (make it private)
- Delete a tag with all its usages in one action
Print options
Expand or collapse list branches
Want checkboxes? Change the list style
List style:Display or hide list attributes
Expand & collapse ec
- Ctrl Shift ← Collapse all
- Ctrl Shift → Expand all
- Ctrl Alt . Expand a branch
- Ctrl Alt , Collapse a branch
- sn Show or hide all notes
Word count wc
Current selection Words: #{js-wc-sel} Characters with spaces: #{js-cc-space-sel} Characters without spaces: #{js-cc-sel} The whole list Words: #{js-wc} Characters with spaces: #{js-cc-space} Characters without spaces: #{js-cc} #{title}
List view options oo
- hc
- hf
- sd
- List style
- om
-
Print
Print this list out or save to PDF
-
Open in a new tab
Full browser page size
-
Save to your account
Log in or register to keep this list in your account
-
What is Checkvist?
Create and share lists online
This permalink allows to view the list as you've shaped it. It will preserve the state of:
- collapse/expand state
- focused list item and/or current filter
- list item numbers (if you choose View > Show as a numbered list)
- visibility of completed items (if you choose View > Hide completed)
You can also use options of the Share dialog to share the list in its current view.
Any email, forwarded to this address, will appear in beginning of this list.
Send an email to yourself and add the sender to Contacts for future use.- The email subject becomes the list item's text.
- The email body becomes the list item's note.
- All attachments from the email are attached to the list item (PRO only).
- In the subject, you can also add #tags, ^due dates, and @assignees with Checkvist's smart syntax.
You can also set up voice integration on mobile devices
- Using web technologies, create a simple 2D physical simulation of a solar system with one planet. The planet should orbit around the center of the system.
- Set up a simple 20 fps game engine using setInterval()!
- Set up an area (a
- Solving coding challenges