kingcauchy

I know there's a lot of GitHub annoyed people out there but after investigating a lot of the instances of outages it does seems like A) They're abusing ElasticSearch in a way is was never meant to be used B) They've seen an unprecedented increase in scale and now have to provide agent slop a lot of free action minutes until they figure out how to separate commercial support from free support C) Who knows how many other systems were never meant to see this scale there

Still grateful for a lot of the free services and the semblance of community that GitHub still offers. It does seem like it's still the yellowpages of tech.

How did overall memory footprint look during ingestion vs Redis? Have any tradeoff graphs as the dataset gets larger and with mixed workloads?

It really depends on the post anymore. Have had a lot of really thoughtful discussions about the nuance that came out of HN convos. Seems like most businesses and people are still just trying to figure out.

Probable being reserved for the OpenBrandSherryDaquiri rebranding.

Also Dark Money by Jane Mayer

This is definitely a level of universal paper clips we’re on…

This is the level where the AI develops quantum computing to make itself smarter (in the game)

yeah especially because it's not very easy to configure everything sensibly for a multi-use case setup, they really need better mac containers on the mac itself

It would be very surprising if they weren't working on even more long-context injection, an agent these days could very easily have a single http call get the markdown/http for a whole page that's essentially injection/propaganda. It seems like the agents have been trained on wrapping responses in tails/cats from `.log` calls or other tool calls, in which case the model training will implicitly be trained on the trustworthiness of context within the tool call tokens.

I think the https://news.ycombinator.com/item?id=50043026 Terence Tao post was much more hopeful and along the lines you're suggesting.

Yeah agreed, especially for legal and healthcare models.

[edit] I'd go one step further too and say the training data should be explicitly requestable too so third parties can verify (freedom of information act styles).

It might be the people that are being acquired too, at huge inflated ai researchers salaries.

Acquired in the vc sense… not literal exit.

Does Cloudflare already use Deno under the hood then? Like the Anthropic -> Bun aquisition

This would seem to be important for proof of work between agents (see https://martin.kleppmann.com/2026/10/07/centre-for-cryptogra...).

I'm curious about these agent harness frameworks that release their harness before they've released a good agent on top. It's a little cart before the horse.

Yeah can't push or create PRs yet for me.

I'm distinctly reminded of the game Universal Paperclips

link in the comments of the article is also interesting https://www.lesswrong.com/posts/bfwH88cFEm3r7PWfv/what-lawye...

Like farming, engines, computers before it.

Probably should also have spend controls for gambling too but seems like we're a long ways off from good legislation there.

It'd be nice if more than AI spend worked this way, autoscaling is almost a mixed blessing because unpredictable pricing can be worse than the cost savings...

What that's awesome? Yeah they definitely waited until the competitors did it first...

Edit: sadface

I'm pretty sure we're living in the prequel to Minority Report right now.

Limits have been decently comparable to 6.1 Sol anecdotally. Although it's subagent eagerness can make then comparison ebb/flow.

The notable difference to me is tokens/sec are still much higher on 6.1 Sol

I've had troubles with it getting stuck "waiting" for a day on some hook or something in CC that never completed and during a task that was waiting on an orphaned process. That maybe saves token money on checks waiting for long-running processes but makes it hard to trust for long-horizon work.

It's been amazing at making sure OOMs for multiple heavy builds on my machine don't happen, adding queues and locks to make sure performance measurements are isolated and gpu stays clean during experiments.

It's also way more able to execute subagent tasks all at once than GPT 6.1 I tried to give it 10 different subtasks all at once that were overlapping and unrelated issues and it did a good job spinning up isolated worktees, agents and then coordinating the merge back together and then verifying them with agents in batches.

Yeah the pdf alone is awesome as a learning tool.

This seems so oddly specific, seems like an integration with canva would be a better direction.

I understand, maybe one day I'll have the chance to hear the blog posts' worth of thought on the matter!

https://codeberg.org/ziglang/zig/issues/37060 I opened the issue and can give you the agent generated RCA on the matter if you all want it in issue 604 on antfly's github but I understand that's against policy and totally respect that.

Appreciate all the work you guys do and have been following the whole Zig project since inception fwiw!

Might be my favorite comment ever now.

Thanks for the clarification here!

So for instance because of the size of our codebase our project has pushed Zig to some of the edges, specifically we end up hitting a bug when using llvm and zig on arm64 (Mac and Linux) where it seems to be caused by some configuration Zig passes through to LLVM. I’ve used codex and claude to help me diagnose and find the bug (we use nix’s glibc zig to circumvent the problem now). I now understand the root cause but am not sure what the proper fix would be. But I’ve not known whether or not even raising the issue would break the terms of contributing? Would raising the issue break the implicit agreement?