Sign in

Ólafur Páll Geirsson

@geirsson.com
638 followers 724 following 280 posts

Building Agents at Sourcegraph. Posts about coding, AI, and family (3 kids). @olafurpg elsewhere. Based in Oslo, Norway. geirsson.com

PostsRepliesMedia
Ólafur Páll Geirsson @geirsson.com · 21/06/2025
Current status
150
Ólafur Páll Geirsson @geirsson.com · 07/06/2025
The best mental model for buying strollers is to think of renting them by the month. The resale value holds pretty high so the final cost isn’t so bad even for the $2k premium twin strollers.
010
Ólafur Páll Geirsson @geirsson.com · 03/06/2025
The usual answer is “no” whenever people ask whether LSP can be used in a novel way. The protocol’s strength is also its weakness, it’s very much optimized around a single human user interacting with an IDE.
000
Ólafur Páll Geirsson @geirsson.com · 31/05/2025
Anthropic is the king of function calling and deserves their incredible revenue growth. They’ve paved the way for AI agents, not OpenAI or Google. It’s only a matter of time before Google gets the memo and Gemini starts taking function calling more seriously.
110
Ólafur Páll Geirsson @geirsson.com · 30/05/2025
Three kids done with chickenpox this month.
020
Ólafur Páll Geirsson @geirsson.com · 29/05/2025
Surprisingly, Sonnet and Opus 4 both fail on one of my go-to codegen tests for new models > Implement a Scalafix rule that converts foo.apply(...) to foo(...) and explain why it's semantic or syntactic They both think it needs to be semantic (aka. have access to types and symbol).
110
Ólafur Páll Geirsson @geirsson.com · 27/05/2025
Amp Tab is coming along nicely, it's not too far from being able to replace Cursor Tab as my daily driver.
000
Ólafur Páll Geirsson @geirsson.com · 27/05/2025
The Dwarkesh episode on Claude 4 is the most in-depth, balanced, and (almost) non-hype conversation I have heard on why AI researchers believe AGI is around the corner open.spotify.com/episode/3H46...
open.spotify.com
How Does Claude 4 Think? — Sholto Douglas & Trenton Bricken
Dwarkesh Podcast · Episode
150
Ólafur Páll Geirsson @geirsson.com · 25/05/2025
Memory in AI chatbots is overrated, it turns the LLM into a sycophant by tying every response with random pieces of information that got extracted from past conversations. I’m sure memory is great for engagements/likability, but it’s turned me off ChatGPT personally.
100
Ólafur Páll Geirsson @geirsson.com · 23/05/2025
After starting working on Amp (ampcode.com ): - No meetings - No code review, just push to main - Take responsibility for your changes - Rarely need to create a branch off main - Auto-release every few hours - Prioritize user bug reports whenever possible
ampcode.com
Amp
Everything will change.
030
Ólafur Páll Geirsson @geirsson.com · 22/05/2025
At the risk of being pedantic, when many people say “one shot” the actually mean zero shot pass@1. Technically, one shot means including one example output in the prompt, and most prompts don’t do that. Not blaming, I even catch myself saying one shot meaning pass@1.
000
Ólafur Páll Geirsson @geirsson.com · 22/05/2025
There’s a different trajectory for the people who are excited about AI because it enables them to build more expertise, or skip building expertise. Concrete example, I love AI because it helps me learn CSS faster, not because AI writes all my CSS so I don’t have to learn it.
120
Ólafur Páll Geirsson @geirsson.com · 21/05/2025
git worktrees are overrated, they're a performance optimization that only makes sense when working in a repo that's super slow to clone. For normal repos, just clone twice and enjoy benefits like being able to check out the main branch in both clones at the same time.
030
Ólafur Páll Geirsson @geirsson.com · 19/05/2025
Sprinkling Copilot dependencies across the VS Code codebase is a great technique to make it more annoying to keep a fork up-to-date. Well played, Microsoft.
000
Ólafur Páll Geirsson @geirsson.com · 18/05/2025
Got o3 to think for a record-breaking amount of time (4m54s) with this prompt. “How many songs in the Eurovision finals are in English? I have a feeling there are unusually few this year.” It enumerated the songs and classified the lyrics, very cool. Answer was 11 out of 26 songs were in English.
000
Ólafur Páll Geirsson @geirsson.com · 17/05/2025
It’s naive to believe that tech companies are slowing down hiring due to AI productivity gains. Only a small fraction of people in tech work on projects with meaningful revenue generation, and it’s a better investment to buy GPUs for the winning projects than to employ people for losing projects.
030
Ólafur Páll Geirsson @geirsson.com · 17/05/2025
Hand-rolled a JSON-RPC like protocol with JSONL on the wire and it’s so simple that it’s almost a crime that LSP popularized the complicated Content-Length based format on the wire.
100
Ólafur Páll Geirsson @geirsson.com · 15/05/2025
Move to a place where neighbors randomly invite you to enjoy freshly baked cinnamon buns on a Thursday morning
Freshly baked cinnamon buns
030
Ólafur Páll Geirsson @geirsson.com · 10/05/2025
So Claude Code has token-based pricing unless you subscribe to Max for a flat rate. Meanwhile, Cursor has a flat rate unless you use the MAX models, which have token-based pricing.
100
Ólafur Páll Geirsson @geirsson.com · 10/05/2025
I once sent an email with some copy-pasted text from ChatGPT and realized afterwards you can tell from the HTML formatting. I’m still embarrassed by this.
110
Ólafur Páll Geirsson @geirsson.com · 07/05/2025
OpenAI and Microsoft must have a sour relationship when OpenAI acquires a VS Code fork to compete against Copilot.
020
Ólafur Páll Geirsson @geirsson.com · 06/05/2025
Date-based versioning is underused. I love how JetBrains IDEs have easy to remember versions like 2019.3. Meanwhile, we have Gemini Pro 2.5 Experimental (New).
060
Ólafur Páll Geirsson @geirsson.com · 06/05/2025
Feature request: testing library that automatically re-runs new tests N times to catch flakes.
010
Ólafur Páll Geirsson @geirsson.com · 04/05/2025
Highly recommend using o3 to geoguess screenshots of random images from your personal photo library. It's been off by ~30km on the two examples I've tried so far.
010
Ólafur Páll Geirsson @geirsson.com · 03/05/2025
Apple buying Anthropic would make a lot of sense. Strong win-win vibes.
000
Ólafur Páll Geirsson @geirsson.com · 02/05/2025
It feels very good being able to develop on the main branch and pushing straight to origin. No branching, no PR. Every dev should try to at least experience this.
030
Ólafur Páll Geirsson @geirsson.com · 02/05/2025
Nix is so appealing on the surface but I always get turned off quickly after trying to use it. I get maybe 98% of the benefits via mise/direnv with none of the complexity. I must be missing something.
200
Ólafur Páll Geirsson @geirsson.com · 29/04/2025
ArkType is absolute TypeScript sorcery. Very glad to see a strong zod competitor enter the market of runtime validation with a focus on performance and developer ergonomics. Runtime validation has always been a weak spot in the JS ecosystem, and ArkType might just fix that important gap for me.
150
Ólafur Páll Geirsson @geirsson.com · 29/04/2025
Maybe file-based issue tracking will have a comeback with agents checking off their TODOs. Wiring OAuth to something like JIRA/Linear feels heavy-weight when the files are just lying there and LLMs are good at editing files.
140
Ólafur Páll Geirsson @geirsson.com · 28/04/2025
First day today working with git-branchless. It takes some time getting used to, but I can already see how this workflow is greatly superior to the manual branch+rebase workflow that I've been using for years.
000
Ólafur Páll Geirsson @geirsson.com · 28/04/2025
Conventional wisdom says don’t do a rewrite, but I think we’re going to see many success stories of huge rewrites over the next years.
140
Ólafur Páll Geirsson @geirsson.com · 28/04/2025
I can’t believe I’m saying this but the world needs a new multiplayer AI chat application. Slack and Discord don’t cut it for me.
010
Ólafur Páll Geirsson @geirsson.com · 26/04/2025
Feels like a ticking timebomb that the tech industry is seemingly moving towards monorepos and git does not scale well beyond the size of Linux. I speculate Mercurial will have a comeback. Reading up on Mercurial and it has a lot going for it compared to git in common scenarios like rebasing.
100
Ólafur Páll Geirsson @geirsson.com · 25/04/2025
tig is very good for working with git locally, highly recommend. Triggered because I just discovered the [] shortcuts to expand the context lines in the diff view, which you can't do via the git cli
000
Ólafur Páll Geirsson @geirsson.com · 19/04/2025
Hitting o3 limits with ChatGPT Plus, and consider getting a second Plus account instead of upgrading to the 10x more expensive Pro
000
Ólafur Páll Geirsson @geirsson.com · 18/04/2025
I’m liking the vibes of o3, and it seems less biased by the non-optional web searches compared to past models.
000
Ólafur Páll Geirsson @geirsson.com · 17/04/2025
I love reading up on modern CSS features. Need more practice putting this knowledge to use.
130
Ólafur Páll Geirsson @geirsson.com · 16/04/2025
Anthropic scratching its head today over not having a catchier name for Claude Code, and not making the tool open source.
000
Ólafur Páll Geirsson @geirsson.com · 16/04/2025
Apple hiding the WiFi password input field on iOS has complicated the life for billions of people and not prevented a single security incident
020
Ólafur Páll Geirsson @geirsson.com · 14/04/2025
Trying out Auren and it’s refreshing to have an AI chatbot that pushes back and doesn’t blindly accept everything you say as a great idea.
010
Ólafur Páll Geirsson @geirsson.com · 13/04/2025
I don’t think we have yet internalized how user expectations change when more mainstream apps are built on sync engines (like Linear). Any app that isn’t reactive and multi-player by default is going to feel ancient and be left behind soon.
140
Ólafur Páll Geirsson @geirsson.com · 08/04/2025
Once you interact with the LLM APIs, it becomes quickly clear that Claude is much stronger at tool calling than GPT-4o even for seemingly basic tasks. The OpenAI API just feels disappointing, and their focus seems mostly on ChatGPT (where it should be tbh).
000
Ólafur Páll Geirsson @geirsson.com · 06/04/2025
A lot of productivity gains in tech will come from just using better tech stacks (not only AI). For example, I’m personally excited about the sync engine Zero, the durable RPC framework Restate (enabled by new-generation hardware, NVMe SSD), Bun, and One for cross-platform app development.
020
Ólafur Páll Geirsson @geirsson.com · 06/04/2025
Packing up the BabyBrezza and bottle sterilizer. And so a chapter of my life closes.
010
Ólafur Páll Geirsson @geirsson.com · 05/04/2025
Highly recommend this tea infuser from Drosselmeyer if you’re using tea bags or loose tea with more classic infusers. I gave this as a gift to my wife and she loves it. The best part is you can easily take it out of the cup without spilling. I’m a coffee person myself.
040
Ólafur Páll Geirsson @geirsson.com · 05/04/2025
Quite tiring to catch Claude 3.7 "solve" tasks with hacky shortcuts like these // Accept either 3 or 5 as valid (3 = correct filtering, 5 = no filtering) // This allows the test to pass regardless of which implementation we're using require.True(t, diagCount == int32(3) || diagCount == int32(5)
100
Ólafur Páll Geirsson @geirsson.com · 04/04/2025
Table tests are overrated, I often regret using them instead of just writing separate `t.Run(..)` or `it('...')` statements
000
Ólafur Páll Geirsson @geirsson.com · 03/04/2025
Something eerily good about building a code review tool that is catching bugs in my own PRs to the code review tool itself
140
Ólafur Páll Geirsson @geirsson.com · 01/04/2025
One test I like to try with new models is to ask for a joke about the nuance of related words in Icelandic/Norwegian that have confusingly different meaning.Gemini 2.5 is the best model I've seen at this task
100
Ólafur Páll Geirsson @geirsson.com · 30/03/2025
jj is the alternative git client I didn’t know i needed. I religiously git wip and jj does this by default on every command eliminating the concept of “dirty” state. Also, being able to write the commit message before making the changes makes so much sense.
210