Hacker News: bhl

New comment by bhl in "Get an AI code review in 10 seconds"

bhl — Mon, 22 Dec 2025 00:39:11 +0000

gh pr diff [num]

also works if you have the GitHub cli installed. Would setup an AGENTS.md or SKILL.md to instruct an agent on how to use gh too.

New comment by bhl in "Graphite is joining Cursor"

bhl — Fri, 19 Dec 2025 22:36:51 +0000

It does not matter what 80-90% of developers do. Code development is heavily tail-skewed: focus on the frontier and on the people who are able to output production-level code at a much higher pace than the rest.

New comment by bhl in "Graphite is joining Cursor"

bhl — Fri, 19 Dec 2025 22:35:09 +0000

Multi-agents.

New comment by bhl in "Daniel Kahneman opted for assisted suicide in Switzerland"

bhl — Sat, 11 Oct 2025 23:35:49 +0000

Not for us to question or answer though.

New comment by bhl in "LLMs are mortally terrified of exceptions"

bhl — Fri, 10 Oct 2025 03:43:25 +0000

What’s the solution here, reward code that works without try catch, reward code that errors and is caught, but penalize code that has try catch and never throws an error?

New comment by bhl in "Claude Code 2.0"

bhl — Mon, 29 Sep 2025 23:50:21 +0000

Cursor will pivot to a computer use company.

The gap between coding agents in your terminal and computer agents that work on your entire operating system is just too narrow and will be crossed over quick.

New comment by bhl in "Amazon has mostly sat out the AI talent war"

bhl — Wed, 03 Sep 2025 03:53:52 +0000

> Originally, it was all about quality data sources.

It still is! Lots of vertical productivity data that would be expensive to acquire manually via humans will be captured by building vertical AI products. Think lawyers, doctors, engineers.

New comment by bhl in "Amazon has mostly sat out the AI talent war"

bhl — Wed, 03 Sep 2025 03:52:42 +0000

Not all will become OSS. Some will become products, and that requires the best people.

New comment by bhl in "Amazon has mostly sat out the AI talent war"

bhl — Tue, 02 Sep 2025 06:44:08 +0000

The moat is people, data, and compute in that order.

It’s not just compute. That has mostly plateaued. What matters now is quality of data and what type of experiments to run, which environments to build.

New comment by bhl in "Flunking my Anthropic interview again"

bhl — Sat, 30 Aug 2025 06:10:21 +0000

Hiring is always a sh*tshow. The only thing that matters is survival: keep applying, keep grinding, keep growing.

And if there's any opportunity to show off, don't be shy :)

New comment by bhl in "GitHub is no longer independent at Microsoft after CEO resignation"

bhl — Mon, 11 Aug 2025 18:37:05 +0000

Stacked diffs is a huge one, and also where improving git would also improve LLM workflows. The bottleneck after code generation is PR reviews, and stacked diffs help break down large PRs into more digest-able pieces.

If you help humans collaborate better, you help LLMs collaborate better.

New comment by bhl in "Linear sent me down a local-first rabbit hole"

bhl — Fri, 08 Aug 2025 22:04:25 +0000

Mobile has really strong offline-primitives compared to the web.

But the web is primarily where a lot of productivity and collaboration happens; it’s also a more adversarial environment. Syncing state between tabs; dealing with storage eviction. That’s why local first is mostly web based.

New comment by bhl in "Automerge 3.0"

bhl — Wed, 06 Aug 2025 17:22:07 +0000

IIRC, Kleppmann built a prototype for it but it’s not included in Automerge yet.

New comment by bhl in "Automerge 3.0"

bhl — Wed, 06 Aug 2025 17:19:19 +0000

1. You can use TipTap with it: just have to wrap your existing schema with automerge attributes. Undo redo would also swap out.

New comment by bhl in "Reflections on OpenAI"

bhl — Tue, 15 Jul 2025 17:17:30 +0000

> The Codex sprint was probably the hardest I've worked in nearly a decade. Most nights were up until 11 or midnight. Waking up to a newborn at 5:30 every morning. Heading to the office again at 7a. Working most weekends.

There's so much compression / time-dilation in the industry: large projects are pushed out and released in weeks; careers are made in months.

Worried about how sustainable this is for its people, given the risk of burnout.

New comment by bhl in "OpenAI’s Windsurf deal is off, and Windsurf’s CEO is going to Google"

bhl — Fri, 11 Jul 2025 23:08:17 +0000

Cursor has custom tab and embedding models. And has a lot of distribution / paying users already.

Arguably they have the strongest product moat, and I wouldn’t be surprised if they beat OpenAI in a vertical coding model from that. Easy for them to have users generate evals and have model product feedback loop here.

New comment by bhl in "OpenAI’s Windsurf deal is off, and Windsurf’s CEO is going to Google"

bhl — Fri, 11 Jul 2025 22:15:03 +0000

I don't know anyone who heard or used Windsurf outside the Bay Area. Even Cursor feels very Bay Area bubbly (although that is the market to go after if you're in ai dev tools).

New comment by bhl in "Is there a half-life for the success rates of AI agents?"

bhl — Wed, 18 Jun 2025 23:24:36 +0000

I always referred it more as context degradation, but rot is more visceral.

New comment by bhl in "Meta invests $14.3B in Scale AI to kick-start superintelligence lab"

bhl — Fri, 13 Jun 2025 23:36:30 +0000

It's not a 2 year cliff: it's 6 months before vesting, then 2 years before you can sell.

New comment by bhl in "Reverse engineering of Linear's sync engine"

bhl — Sat, 31 May 2025 15:06:15 +0000

Ecosystem for local-first and mobile is pretty immature, at least for Swift.

In comparison to the web where there's so many libraries e.g. Zero, LiveStore, LiveBlocks, I've yet to find a good GRDB (sqlite abstraction) integration / client.

Offline-first is definitely very strong, but now how do I get data into a remote database with conflict resolution support?