RAG was supposed to be the way out on that, and ended up being mostly abandoned.

Unless you're a contracting agency!

Did wonder about the review, it probably sold well in the news papers and part of me thinks that the Odyssey team might even agree with her, but IMHO it's mostly overblown? The movie is good an wildly successful, and maybe I've gotten less jaded, but felt like her criticism did not land ( saying that as someone who loves to poke holes at things and reading a good polemic).

She's entitled to her views, and others are entitled to think, like you, that her review is overblown.

My view is she has some good points about script and plot, given her expertise is in writing, but she's under-emphasising the importance of the visual arts.

Remember that Slashdot's review of the iPod was "No wireless. Less space than a nomad. Lame.". Not everybody has to like the popular thing.

I quite like watching Yahtzee's Fully Ramblomatic reviews. He's known for giving most games a kicking, but he does highlight what's good in a game as well as its bad points. I'd rather hear what he has to say than get a adverising puff-piece review from IGN. Even for games that I strongly enjoyed, he usually raises good points about them that I'd agree with.

Just overfit ad infinitum:)

Shower thought: But how often per week do you run the pelican these days? And do you have it automated at this point or would the automation take out the meaning of the benchmark?

My automation is pretty simple. I use my https://llm.datasette.io tool where I have a template saved:

  llm "Generate an SVG of a pelican riding a bicycle" --save pelican

When a model comes out I first make sure LLM can talk to it - usually by updating the relevant plugin, but if it's on OpenRouter I can use it directly with https://github.com/simonw/llm-openrouter - sometimes I use this mechanism instead, for OpenAI-compliant API models: https://llm.datasette.io/en/stable/other-models.html#configu...

Then I run something like this:

  llm -m gpt-6-astra -m pelican

Then I grab the most recent log export as markdown:

  llm logs -cu | pbcopy

-c means most recent conversation, -u includes token usage

I paste that into https://gist.github.com and then paste the resulting Gist URL into the URL tab on https://tools.simonwillison.net/markdown-svg-renderer

If the model supports multiple reasoning levels I run it once per level and put those in the same file.

I really should automate this a bit more.

Love the investigation and write up.

Took me down some rabbit holes, but interesting to see the chatter about the fix here:

https://github.com/python/cpython/issues/80233

Initially you could reassign True,False but that was verboten with the switch to python 3! The walrus operator was the one simply an oversight.

https://python-history.blogspot.com/2013/11/story-of-none-tr...

Explanation from Guido himself

This is a nice follow up to the other SIMD article that was posted here a week or so ago hah.

Was hoping for a process diagram on how refactoring removes bottlenecks during software developement and allows you to ship faster etc :)

Still a nice writeup and love how these meta analysises (presumeably) done via AI can now easily capture metrics that inform your workflow.

Try some of the suggestions there and see what works vs doesn't, hell feed it to an LLM and ask what in there is correct.

You most likely are referring to the local jsonl files where claude has your sessions etc stored.

It could just be the memory features.

In my enterprise-seated account I see slightly different options available (vs. my personal account) in the Capabilities section:

  Search and reference chats
  Allow Claude to search for relevant details in past chats.

  Generate memory from chat history (Legacy)
  Allow Claude to remember relevant context from your chats. Memory includes your entire chat history with Claude.

The first option was defaulted to on, if I recall.

But it kind of conflicts with the contract we have with them. My company has an enterprise contract that says "no data retention" but then each user can decide to enable it unilateral?

If you're talking about Claude Code it's in ~/.claude/projects/<encoded dir name>/memory/MEMORY.md. So they're not really retaining it, it's just something that your harness loads in.

Not Claude Code. Claude in the browser

When using the browser, what Anthropic calls Claude.ai, the memory is stored on your account on their servers.

Claude code stores memory locally on the device, similar to how a developer stores notes.

Data retention is about storing your raw conversation data.

Capabilities and Privacy settings are used to manage memory and data retention.