Hacker News: joshmlewis

New comment by joshmlewis in "Audio is the one area small labs are winning"

joshmlewis — Mon, 16 Feb 2026 16:27:00 +0000

Speechify has been good for me although there might be better / cheaper alternatives I'm not aware of.

New comment by joshmlewis in "Claude Opus 4.6"

joshmlewis — Thu, 05 Feb 2026 22:57:41 +0000

I think the OP was implying that it's probably already baked into its training data. No need to search the web for that.

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

joshmlewis — Fri, 30 Jan 2026 15:48:03 +0000

"They" being the guy (Peter Steinberger) who created it as a personal project that he open sourced.

New comment by joshmlewis in "How to code Claude Code in 200 lines of code"

joshmlewis — Thu, 08 Jan 2026 22:47:40 +0000

This is cool but as someone that's built an enterprise grade agentic loop in-house that's processing a billion plus tokens a month, there are so many little things you have to account for that greatly magnify complexity in real world agentic use cases. For loops are an easy way to get your foot in the door and is indeed at the heart of it all, but there are a multitude of a little things that compound complexity rather quickly. What happens when a user sends a message after the first one and the agent has already started the tool loop? Seems simple, right? If you are receiving inputs via webhooks (like from a Slack bot), then what do you do? It's not rocket science but it's also not trivial to do right. What about hooks (guardrails) and approvals? Should you halt execution mid-loop and wait or implement it as an async Task feature like Claude Code and the MCP spec? If you do it async then how do you wake the agent back up? Where is the original tool call stored and how is the output stored for retrieval/insertion? This and many other little things add up and compound on each other.

I should start a blog with my experience from all of this.

New comment by joshmlewis in "Claude Memory"

joshmlewis — Thu, 23 Oct 2025 22:39:33 +0000

This just feels like the whole complicated TODO workflows and MCP servers that were the hot thing for awhile. I really don't believe this level of abstraction and detailed workflows are where things are headed.

New comment by joshmlewis in "Claude Memory"

joshmlewis — Thu, 23 Oct 2025 22:36:30 +0000

This should not really be necessary and is more of a workaround for bad patterns / prompting in my opinion.

New comment by joshmlewis in "Claude Memory"

joshmlewis — Thu, 23 Oct 2025 22:35:48 +0000

How big is your claude.md file? I see people complain about this but I have only seen it happen in projects with very long/complex or insufficient claude.md files. I put a lot of time into crafting that file by hand for each project because it's not something it will generate well on its own with /init.

New comment by joshmlewis in "Slack has raised our charges by $195k per year"

joshmlewis — Thu, 18 Sep 2025 03:08:17 +0000

It's also not a coincidence that Slack is neutering the ability to access channel history via the API very soon. With a very generous rate limit of 2 requests per minute I believe it was and a max of ~10 messages. This is already enforced for new marketplace apps and will apply to all apps starting in March according to their docs.

New comment by joshmlewis in "We put a coding agent in a while loop"

joshmlewis — Mon, 25 Aug 2025 16:11:19 +0000

One of the biggest nuggets people need to take away from this:

> At one point we tried “improving” the prompt with Claude’s help. It ballooned to 1,500 words. The agent immediately got slower and dumber. We went back to 103 words and it was back on track.

Keep your prompts / agent instructions short. Focus on the wide view, not specifics.

New comment by joshmlewis in "Tidewave Web: in-browser coding agent for Rails and Phoenix"

joshmlewis — Wed, 20 Aug 2025 14:30:39 +0000

As someone who builds AI products and having used agentic coding tools since they came out (often with Rails projects), I don't get this. There was a similar project called Rails MCP Server which said:

> "This Rails MCP Server implements the MCP specification to give AI models access to Rails projects for code analysis, exploration, and assistance."

And again I don't get the value. I can see some slight benefits to having a tight browser integration but I don't think that's worth leaving the IDE / CLI tools and the workflows they bring. You can also use Playwright MCP or just screenshot easily for more context. Claude Code can now run your server in the background and view logs as well. In a perfect world where LLM's can one shot whole features, maybe. But I can't let Claude Code go 10 minutes without it introducing a bad pattern and having to stop it. Reducing that visibility even further with this does not seem like a good combo.

I'm not wanting to tear down others projects either, just giving my perspective. I should try it to see how it does in the wild but the Copilot license or Anthropic API key requirement also deters me as well as having to have a project specific dependency.

New comment by joshmlewis in "GPT-5"

joshmlewis — Fri, 08 Aug 2025 04:49:57 +0000

It is funny how it can be like this sometimes. I think a lot depends on coding styles, languages, prompting, etc.

New comment by joshmlewis in "GPT-5 for Developers"

joshmlewis — Fri, 08 Aug 2025 04:49:20 +0000

Cursor

GPT-5 really likes tool calling

joshmlewis — Fri, 08 Aug 2025 00:30:10 +0000

Article URL: https://promptslice.com/share/b-2ap_rfjeJgIQsG

Comments URL: https://news.ycombinator.com/item?id=44832066

Points: 2

# Comments: 0

New comment by joshmlewis in "GPT-5"

joshmlewis — Thu, 07 Aug 2025 22:21:57 +0000

When it came out on Tuesday I wanted to throw my laptop out of the window. I don't know what happened but results were total garbage earlier this week. It got better the past couple days but so far with gpt-5 being able to solve problems without as much correction I'm going to use it more.

New comment by joshmlewis in "GPT-5"

joshmlewis — Thu, 07 Aug 2025 22:05:36 +0000

Whoosh, it went right over my head.

New comment by joshmlewis in "GPT-5"

joshmlewis — Thu, 07 Aug 2025 22:02:46 +0000

The data is made up, the point is to see how models respond to the same input / scenario. You're able to create whatever tools you want and import real data or it'll generate fake tool responses for you based on the prompt and tool definition.

Disclaimer: I made PromptSlice for creating and comparing prompts, tools, and models.

New comment by joshmlewis in "Cursor CLI"

joshmlewis — Thu, 07 Aug 2025 22:01:11 +0000

I would highly doubt it. Even when you BYOK inside of Cursor they still say it's routed through their servers.

New comment by joshmlewis in "Cursor CLI"

joshmlewis — Thu, 07 Aug 2025 22:00:34 +0000

I noticed it was taking awhile on the first large-ish task I gave it. I'm assuming it was just a bit overloaded at the moment.

New comment by joshmlewis in "GPT-5"

joshmlewis — Thu, 07 Aug 2025 21:57:01 +0000

Where'd you get 720 from?

New comment by joshmlewis in "GPT-5"

joshmlewis — Thu, 07 Aug 2025 21:54:53 +0000

Did I say GPT-5? I said o3. :) That was a rebuttal to you saying you have never needed to add your key to use an OpenAI model before.