Live Last read · last published · next check
Claude Fable spent $4* to tell me that a long background job might cost me $4 in expired cache. *not four real dollars I was refining a testing skill with Fable in one Claude Code session, and exercising it with Opus in another. I asked what would happen if the other agent's background job took a long time to return. CLI, version 2.1.220 Fable: This is a caching-mechanics question — let me check…
I thought I'd try semantic search on my playground wiki using an embedding model, but as it turns out, you have to plan how to embed stuff to suit your use case, which takes a lot more concentration than I was planning to allocate. Instead, I decided to give some local LLMs a search tool and ask them to find the right thing. THIS IS NOT A TUTORIAL, unless you want to build local search that takes…
Thomas Ptacek says everybody Should Write An Agent , because It's Incredibly Easy . You can indeed have your very own agent in a matter of a few dozen (pretty-printed!) lines of Python plus API access to a tool-call-capable LLM, per Simon Willison's definition: "an LLM agent runs tools in a loop to achieve a goal" . Thomas illustrates this with a chat client for the OpenAI Responses API that lets…
Say you have a minimal LLM chat client that does the following: Wait for the user to input a prompt Add a message to chat history containing the user input Send any system prompt (or none) + full chat history to the model (via API) Add the completion from the model to chat history Repeat Here's mine in a gist. To transform that into an agent: Write a schema for each tool, to tell the model what…
Image: crop of Figure 10 from Teletype's 33 KEYBOARD GENERAL DESCRIPTION AND PRINCIPLES OF OPERATION ( 7.6MB PDF at deramp.com ) I have a personal TUI text-editor app thingy that runs in a terminal emulator. Made with the Ratatui library, using (a fork of) the tui-textarea widget for editing. One of my main ambitions for this program was that it should be intuitive to use, for my personal value of…
Writing is hard. I usually overthink it. Late one night, after mindlessly feeding the highlights of a day hike into a Slack thread, I had a punch-drunk inspiration: writing under similar constraints and conveniences, could I barf out a blog post almost as easily? Rather than compose my next article in Slack DMs with myself, I went for the second-most-practical proof of principle: creating a new…
I've been building an application to exercise some features of Phoenix/LiveView and Fly Machines. It's a button . You push the button. It makes an API call. A new virtual machine pops up on some Fly.io metal in the data centre nearest to you. Nearest, that is, to the Fly.io edge server you hit using the app's Anycast IP address. If your ISP and its BGP friends are having a bad day, your request…
The other day, I accidentally got Claude 3.7 Sonnet to generate a thousand-line, Req -based Elixir API client from the OpenAPI spec for Fly Machines . I was exploring the options for structuring such a module, more out of curiosity than any urgent need, and asked Claude on a whim if it could produce functions for all the endpoints. It did. Forty-odd functions, complete with typespecs and detailed…
iex -S mix phx.server : it starts up my Phoenix dev server under Elixir's interactive shell program, IEx , so I can call functions from my app and whatnot . One day, it started to bug me unreasonably much that I didn't really understand how this command causes that to happen. Perhaps culpable: a touch of delirium, downstream of the flu. There were a lot of reasons for my mystification (i.e. a lot…
Erlang docs home OTP design principles - Supervision trees, behaviours, applications, releases, release handling Learn you some Erlang for great good - the classic by Fred Hebert The OTP team blog - good resource on how some things work
