simonw

7 घंटे पहलेdiscuss

It might be worth recreating the git history from scratch in a way that excludes the markdown files - I've used Claude Code and OpenAI Codex to do that in the past with git-filter-branch. Lets you preserve the important history but clean out all the junk.

simonw

15 घंटे पहलेdiscuss

This is an intimidating amount of code! 12,303 lines of C and 244,740 lines of Python, which looks to be a ton of monkeypatching plus huge amounts of test code.

Only one commit added all of that, just two hours ago.

The published numbers are impressive, but its hard to evaluate how much trust can be put in a project of this complexity at this early stage.

simonw

कलdiscuss

The WebAssembly demo that runs in your browser is a really neat touch: https://pgrust.com

simonw

कलdiscuss

The test coverage of sqlite-utils is solid - pytest-cov reports 95% total. The project has 9,973 lines of implementation code and 14,860 of test code.

Here's the delete_where() test: https://github.com/simonw/sqlite-utils/blob/7a52214624ae0e2c...

The problem with the test was that it asserted that the records were deleted inside of the same transaction as the delete, so it missed the changed behavior where the delete didn't commit properly (it had committed properly prior to the new transactions work).

simonw

कलdiscuss

Your comment here reminded me of a conversation I had six months ago where I argued passionately for normalizing the idea of people writing on their own personal sites and linking to it where relevant... it turns out that argument was with you! https://news.ycombinator.com/item?id=46367224#46370862

simonw

कलdiscuss

Honestly that's the main value I get from it myself - making a pelican means I have to figure out API keys and how to talk to the provider, or how to run it locally for the local models.

simonw

कलdiscuss

A previous employer hit the problem where there were a ton of legacy features that didn't have clear owners and so it wasn't clear where to route bug reports.

Their solution was to build a catalog of every feature and then assign EVERY one of them to an existing team.

Teams might end up responsible for features that they had never seen before and had no knowledge of... but that was fine, because every other team was in the same situation.

It worked great. Bugs got fixed. Teams figured it out.

simonw

कलdiscuss

It does feel like a chore in weeks like this one where there are new models landing every day.

I'm also increasingly worried that I'm not providing enough value in my model reviews. It's really hard to get a useful and credible idea for the strengths of the new models.

simonw

कलdiscuss

My blog genuinely is a day job now, I make enough from the (unobtrusive, cookie-free) sponsorship banner that I no longer regret not having a proper software engineering job.

simonw

कलdiscuss

The first time I did this was actually less than two years ago - in October 2024 - and it's fun seeing how much better they've got since then: https://simonwillison.net/2024/Oct/25/pelicans-on-a-bicycle/

simonw

कलdiscuss

Someone told me that a model said "oh, the classic" when they asked for this recently. I think that was Opus 4.8.

simonw

कलdiscuss

I haven't tried this in a few months, but last time I tried a loop that rendered the pelican and asked for improvements the results were actually quite disappointing. Be interesting to try that again against GPT-5.6 at Claude Fable 5 though.

simonw

कलdiscuss

It's part of the pelican tradition at this point.

simonw

कलdiscuss

Here are 18 pelicans - six each for Luna, Terra and Sol at the six different reasoning effort levels (plus the price to generate each one): https://static.simonwillison.net/static/2026/gpt-5.6-pelican...

Or if you want to see some in 3D, OpenAI featured a pelican riding a tricycle, bicycle, pony and another pelican in their livestream this morning: https://www.youtube.com/live/Wq45rvPGNHs?t=1070s

simonw

कलdiscuss

I just clicked "Upgrade" in the macOS Codex Desktop app and it relaunched with a new name, "ChatGPT". My existing install of the macOS ChatGPT app seems to have been renamed "ChatGPT Classic".

simonw

परसोंdiscuss

Pelican from a few days ago: https://simonwillison.net/2026/Jul/6/hy3/ - I was using the free tier on OpenRouter, which expires on July 21st.

I tried the preview model 41 days ago and got a pelican with a "change pelican color" button: https://static.simonwillison.net/static/2026/hy3-preview-pel...

simonw

परसोंdiscuss

A comparison I find useful here is Excel (and spreadsheets in general). Those enabled huge numbers of non-programmers to build software-like things, while the demand for expert developers grew enormously at the same time.

I'm hoping vibe-coding plays out the same way.

simonw

परसोंdiscuss

I had a few days of preview access, which was long enough to put together a plugin for LLM. You can try the model out in the terminal like this:

  uv tool install llm
  llm install llm-meta-ai
  llm keys set meta-ai
  # paste API key here
  llm -m meta-ai/muse-spark-1.1 "Generate an SVG of a pelican riding a bicycle"

Here's the result: https://tools.simonwillison.net/markdown-svg-renderer#url=ht...

For comparison, here's the pelican I got from Muse Spark 1: https://simonwillison.net/2026/Apr/8/muse-spark/

simonw

परसोंdiscuss

If you're going to accuse someone of "an outright fabrication" it's on you to check that you're not wrong before you say that.

simonw

परसोंdiscuss

You want to see him address being "a stinky manager", having "beginner energy", choosing to take VC as opposed to "a solid living via crowdfunding", or "already writing slop well before he had access to LLMs"?

Those are all opinions where arguing about them isn't going to be productive.

Countering the accusation of "an outright fabrication" on the other hand is worthwhile because it's a claim that can be countered.

If somebody called me a liar for something that demonstrably wasn't a lie I wouldn't let that stand, either.

Submissions

Show HN: Shot-scraper video tool for recording YAML-defined webapp feature demos

AI and Liability

The Minimum Viable Unit of Saleable Software

I think Anthropic and OpenAI have found product-market fit

Show HN: Datasette Agent

Your AI Use Is Breaking My Brain

Extract PDF text in the browser with LiteParse for the web

Changes in the system prompt between Claude Opus 4.6 and 4.7

Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7

Anthropic's Project Glasswing sounds necessary to me

Mr. Chatterbox is a (weak) Victorian-era ethically trained model

Ask HN: What are you using to run dev environments safely on macOS these days?

Profiling Hacker News users based on their comments

AI should help us produce better code

Something is afoot in the land of Qwen

Show HN: Showboat and Rodney, so agents can demo what they've built

StrongDM's AI team build serious software without even looking at the code

Distributing Go binaries like SQLite-scanner through PyPI using go-to-wheel

The Voxel Is a Cutting-Edge Theater Experiment

ChatGPT Containers can now run bash, pip/npm install packages and download files

comments