31–40 of 87 posts
2 weeks rebuilding in Swift is absolutely crazy. Wonder if they're using production Opus 5 for this or their internal Mythos (if they even use it internally)
31:09 He flubs the questioning. His first says "Raise your hand if 100% of your code uses agents." Then he says, "What about more than 50%". You can see the same audience members who raised the first time shrug and also raise the second time. He then says "Slightly less hands," which just means he sees what he wants to see. Don't believe this man.
The TL;DR of the fragment at around 6:57 in the video, for those who don't want to watch, is that Boris recommends to delete all the customizations, CLAUDE.md, skills, and other stuff you had for older models, and try using the new models without all that, because the new models can surprise you.
Tried out Opus 5 and it's been a super annoying experience out of the box.
The TL;DR of the fragment at around 6:57 in the video, for those who don't want to watch, is that Boris recommends to delete all the customizations, CLAUDE.md, skills, and other stuff you had for older models, and try using the new models without all that, because the new models can surprise you.
Somewhat like AWS CloudFormation templates start with something like TemplateVersion: 2017-10-01
But maybe that's old school thinking still.
So maybe SKILL.md and CLAUDE.md should have model version pinned? Somewhat like AWS CloudFormation templates start with something like TemplateVersion: 2017-10-01 But maybe that's old school thinking still.
So maybe SKILL.md and CLAUDE.md should have model version pinned? Somewhat like AWS CloudFormation templates start with something like TemplateVersion: 2017-10-01 But maybe that's old school thinking still.
we keep the AGENTS.md simple and monorepo quirk focussed, no instructions for specific agents or models
Earlier quoted context omitted.
This is not accurate. Most LSPs do provide text editing tools, which the Language Server Protocol calls "code actions". These actions do things like: reorganizing imports, expanding macros, extracting a selection into a function, or converting one type of control flow into another (e.g. if to match). Common LSPs, like rust-analyzer and Ruff (Python) support code actions. Editors also expose code actions: Zed, for ins…
Come on what are we talking about. Ruff is a linter. Can you show me any LSP server that can move an arbitrary function from file1.ts to file2.ts based on calling it on the command line?
https://go.dev/gopls/features/transformation
it does look to have a method for moving a function to a new file
I give my agent access to go pls and find it overall beneficial, based on vibes eval. Its way easier to ask LSP everywhere a function or field is used versus grep, saves a lot of tokens
The TL;DR of the fragment at around 6:57 in the video, for those who don't want to watch, is that Boris recommends to delete all the customizations, CLAUDE.md, skills, and other stuff you had for older models, and try using the new models without all that, because the new models can surprise you.
All of these harnesses should support pinning config files and tools to specific models or families of models. It's really tiring to have to tweak everything with each model release and then watch those changes mess up cheaper models in the process.