Hacker News: lyime

New comment by lyime in "Glaze by Raycast"

lyime — Wed, 04 Mar 2026 23:14:09 +0000

Moat? Maybe they built something they wanted?

New comment by lyime in "OpenClaw – Moltbot Renamed Again"

lyime — Fri, 30 Jan 2026 15:06:35 +0000

Read about hearbeat, that makes openclaw different than claude code.

New comment by lyime in "BYD builds fastest car"

lyime — Mon, 06 Oct 2025 04:14:13 +0000

China subsidies Byd. It would be bad for american car industry. So if US wants to create a fair competition, they would need to use tariffs or subsidies the US car industry players that could compete fairly with BYD.

Looks like US is using tariffs to compete.

New comment by lyime in "Claude’s memory architecture is the opposite of ChatGPT’s"

lyime — Thu, 11 Sep 2025 20:49:49 +0000

How do you define "LLMs don't understand concepts"?

How do you define "understanding a concept" - what do you get if a system can "understand" concept vs not "understanding" a concept?

New comment by lyime in "Dropbox Paper mobile App Discontinuation"

lyime — Tue, 09 Sep 2025 19:09:31 +0000

notion ate there lunch

New comment by lyime in "Show HN: An AI agent that learns your product and guides your users"

lyime — Thu, 31 Jul 2025 01:12:14 +0000

> 1. Invite agent@frigade.ai to your product. You can send multiple invitations based on distinct roles.

this is clever

New comment by lyime in "How and where will agents ship software?"

lyime — Wed, 16 Jul 2025 22:00:40 +0000

Have you tried Convex?

New comment by lyime in "Show HN: Magnitude – Open-source AI browser automation framework"

lyime — Fri, 27 Jun 2025 06:04:58 +0000

Are you sure? Couldnt you just just go back to the LLM if the script breaks? Pages changes but not that often in general.

It seems like a hybrid approach would scale better and be significantly cheaper.

New comment by lyime in "Meta Invests $14.3B in Scale AI to Kick-Start Superintelligence Lab"

lyime — Fri, 13 Jun 2025 17:51:04 +0000

Good hire.

New comment by lyime in "Ask HN: What API or software are people using for transcription?"

lyime — Mon, 09 Jun 2025 17:51:50 +0000

I would love to automate our Youtube channel videos and transcribe with speaker identification

New comment by lyime in "Ask HN: Has anyone quit their startup (VC-backed) over cofounder disagreements?"

lyime — Fri, 11 Apr 2025 17:26:25 +0000

Lots of founders go through this. You should have an honest conversation with your co-founder. Probably couples therapy. One option is to do it with another founder who has been there (me).

You both are going through a challenging time. Of-course you are going to find some things that are more interesting to you than your founder, and vice versa. Especially if you are pivoting every month (which is a whole different problem).

Going through tough times can build resentment, the way to get on the same page is to talk.

New comment by lyime in "Hacking Your Own AI Coding Assistant with Claude Pro and MCP"

lyime — Wed, 19 Mar 2025 14:22:23 +0000

You are not getting more than $25 of value?

New comment by lyime in "Hacking Your Own AI Coding Assistant with Claude Pro and MCP"

lyime — Wed, 19 Mar 2025 14:20:04 +0000

It seems fair for them to train on how people use their tools, so they can make the tools better for people who use them?

New comment by lyime in "Launch HN: Maritime Fusion (YC W25) – Fusion Reactors for Ships"

lyime — Wed, 26 Feb 2025 20:24:36 +0000

Great to see people trying to solve hard problems!

New comment by lyime in "Launch HN: Promptless (YC W25) – Automatic updates for customer-facing docs"

lyime — Wed, 19 Feb 2025 04:39:25 +0000

Pricing? Whats bespoke about it? Whats your pricing metric?

New comment by lyime in "Uchū · the color scheme for internet lovers"

lyime — Mon, 17 Feb 2025 01:59:45 +0000

I did not mind it.

Nudges can be helpful.

New comment by lyime in "AI systems with 'unacceptable risk' are now banned in the EU"

lyime — Tue, 04 Feb 2025 04:10:28 +0000

Do the same rules apply to the government entities luke law enforcement and security services?

New comment by lyime in "Skyvern Browser Agent 2.0: How We Reached State of the Art in Evals"

lyime — Fri, 17 Jan 2025 20:49:14 +0000

To your last point -- Humans make mistakes too. I asked my EA to order a few things for our office a few days ago, and she ended up ordering things that I did not want. In this case I could have wrote a better prompt. Even with a better prompt she could have ordered the unwanted item. This is a reversible decision.

So my point is, that while you might get some false positives, it's worth automating as long as many of the decisions are reversible or correctable.

You might not want to use this in all cases, but it's still worthwhile for many many cases. The use case worth automating depends on the acceptable rate of error for the given use case.

New comment by lyime in "Skyvern Browser Agent 2.0: How We Reached State of the Art in Evals"

lyime — Fri, 17 Jan 2025 20:28:15 +0000

This is an impressive tool. I especially like the observability around the workflow and the steps it takes to achieve the outcome. We are potentially interested in exploring this if we can get the cost down at scale.

New comment by lyime in "Nvidia-Ingest: Multi-modal data extraction"

lyime — Fri, 10 Jan 2025 18:52:18 +0000

So who is going to deploy this and turn this into a service/API?