Stefan Li @autoconfig

Holy smokes Anthropic is so back

In medieval times, within the arms race of ever more demonic torture devices, some sadistic genius came up with the idea of the Little Ease. This was a prison cell built so small in every dimension that a grown man could not stand upright in it nor lie down at full length nor properly sit. The pain is relentless and without relief and inflicted by one's own body. Prisoners were known to go insane within a few days. A stay at the Little Ease was considered even more cruel than the rack, the thumbscrew, and the other ghoulish machinery of the Tower of London. A breeding pig will spend her whole life in a version of that box. These are social, roaming creatures (more intelligent than dogs) who will never leave this corset of steel. They have been selectively bred to be bigger than their frames can support. Yet we put them in cells so confined that they cannot comfortably sit, and their attempts to do so (for example, by sneaking their limbs into adjacent stalls) reliably lead to fractures and sprains. They cannot sweat, yet have nothing to roll around in to cool themselves off. Except their own manure, which (contrary to the common misconception) they are so averse to (thanks to their strong sense of smell) that new sows will often suffer from constipation to avoid soiling the space from which they eat and sleep. Here is how the writer Matthew Scully described what saw at one of Smithfield’s “gestation barn”: > “Sores, tumors, ulcers, pus pockets, lesions, cysts, bruises, torn ears, swollen legs everywhere. Roaring, groaning, tail biting, fighting, and other “Vices,” as they’re called in the industry. Frenzied chewing on bars and chains, stereotypical “vacuum” chewing on nothing at all, stereotypical rooting and nest building with imaginary straw. And “social defeat,” lots of it, in every third or fourth stall some completely broken being you know is alive only because she blinks and stares up at you … creatures beyond the power of pity to help or indifference to make more miserable, dead to the world except as heaps of flesh into which the [insemination] rod may be stuck once more and more flesh reproduced.” — The Save Our Bacon Act is trying to unroll the few state protections we have against this barbaric cruelty - for example California’s Prop 12 - which banned the sale of pork from pigs kept in gestation crates. It’s incredibly important we don’t end up with this sort of federal preemption. SOB will not only kill the most important animal welfare related laws in the US of the past decade, but more importantly, it will also restrict ALL future legislative progress (aka how the animal welfare movement has gotten its biggest wins). The Senate is currently deciding whether to add the SOB Act to the Farm Bill. With relatively little money now, we can discourage the most pivotal senators in the Ag committee from backing this amendment. Defeating this bill is even more important given the amount of philanthropic funding I expect to come online in the next year or two. It will plausibly be over 10x more expensive to repeal SOB than to prevent it from passing in the first place. All that money that could be spent transforming our society's relationship to mass animal suffering will instead have to be spent just getting us back to where we are right now. That's why money spent now fighting this bill (and I mean right NOW) is so effective. If you’re in a position to donate six figures, please DM me.

How to make codex not write like a freak

could not agree more

CheesyPotato (Julie) @CheesiestPotato

2 weeks ago

i do not gaf about your cube-cheating bullshit gcc cabal nonsense. i do not ever want zadig. i swear to god let me turn that off. i want to play ON XBOX and engage with MULTIPLE BUMPERS i do not want to FLIP THE MAYFLASH and engage with SNAPBACK

0 7 28 1K 1

@stewfortier Yeah classic “unable to hold multiple thoughts at once” problem: - Some can work very long hours productively for years / decades. - Not everyone can / needs / wants to. - Startup founders making 996 their whole personality are obnoxious. Can all be true at the same time.

@jjpcodes first lesson: never use passkeys

Opus 4.8 (max effort) mega failed on my first try. Claimed a core feature that was specced was missing on a large branch. Back to Codex + 5.5. It's genuinely head scratching to me how the gap can be this big. Still love that Claude Code CLI though.

Google is catching a lot of flak for the messy keynote but I'd much rather see them trying many things than over-indexing on having a cohesive story.

These building blocks will allow you to do basically anything when combined with custom agents. Workers for deterministic code, external agents for any long running agentic work, and custom agents as the orchestrator that triggers when you want and speaks native Notion.

Notion @NotionHQ

a month ago

BIG one for devs today. Introducing the Notion Developer Platform: - Notion CLI, ntn (Notion in your terminal) - Workers (run code on Notion's infra) - Database sync (any data source into Notion) - Agent tools (build any workflow) - Webhook triggers (trigger Notion from any app)

92 228 2K 969K 1K

Every person has a story to tell, and AI can help them tell it. We're seeing this firsthand at @typedotai. We now serve writers ranging from NY Times bestsellers, to top 10 podcasters, to nearly 10k passionate independent authors. We've been ~doubling revenue each quarter and active subscribers now spend 7+hours/week in our editor. So we made this video to honor the intensely creative people we serve. Here's to the storytellers :)

🚀

Ivan Zhao @ivanhzhao

a month ago

Closed Q1 last week. Revenue is accelerating for the 7th straight quarter. AI now counts for 60% of our business. Cash flow positive. The transition from software to AI is not easy, but can be done! I am proud of our teams!

47 41 949 111K 111

Wow can't wait to try this out!

Gustav Söderström @GustavS

a month ago

Hey. This one is for all you early adopters out there! Like I’m sure many of you do, every morning an agent preps me for my day - calendar, news, last 24hrs of Slack - in a morning briefing. But mine lands in my Spotify library, so I can listen to it on my commute. Same app,

36 24 344 695K 394

I said it in Jan and I'll say it again: If your eval doesn't rank GPT 5.5 in codex on top, then your eval is wrong. If you're not using GPT 5.5 for coding then you're not using a frontier model.

Xander Dunn @xanderai

5 months ago

If your eval doesn't rank Claude Opus 4.5 in Claude Code on top, then your eval is wrong. You're measuring the wrong thing or you're measuring it incorrectly.

1 0 8 10K 1

First bakeoff between CC opus 5.7 xhigh and codex gpt 5.4 xhigh on non-trivial real world task. Winner: gpt 5.4. It is impossible to know which harness / model is more capable from twitter vibes and benchmarks. Do your own comparisons.

@zachtratar @jigarmistry24 @NotionHQ Hey @jigarmistry24 you can do that via the instructions menu.

We’re working hard to improve the speed of Notion. One aspect of that? Creating and joining meetings rapidly in fewer clicks. So a couple engineers just shipped some improvements. Announcing… quick join + quick create! Here’s how they work. 👇

The victory of the opposition in Hungary yesterday, like the Polish election in 2023, is a victory for democracy, not just in Europe but around the world. Most of all, it’s a testament to the resilience and determination of the Hungarian people – and a reminder to all of us to keep striving for fairness, equality and the rule of law.

Wow. @NotionHQ Custom Agents is incredibly underrated. It's probably the most approachable AI Agent platform out there today. I just built an entire e-commerce customer service agent for @mylongboi that answers all of our emails, recommends products and sizes to customers, and triages return / refund requests for us... (soon it will PROCESS these requests for us too). There are Shopify Apps literally charging $300-800 per MONTH for this kind of AI Agent. Notion is incredible too because we already used it for our ticket system and it's super easy for my wife (who is non-technical) to use and customize the agent without any coding experience. And with a bit of technical experience, I was able to build a custom MCP connection for our Shopify Admin API with just a few prompts with Claude Code, which then deployed it to Notion Workers in an afternoon. I'm so excited about this, I think I'm going to have to make a video explaining the full setup. Who would be interested in this?

Suing over dark mode!? You can't make this shit up 😂

Bevel @bevel_health

2 months ago

Whoop filed a lawsuit against us, and this is our response. TL;DW: - June 2024: Whoop's Corp Dev reached out wanting to "explore collaboration" - 5 months later: cease and desist letter - Their demands: disable dark mode (ours defaults to light mode), rename common words like

77 174 2K 571K 646

Claude Code's current lead is in my experience not in its harness but in the overall polish and UX of the CLI. E.g. try resizing Codex and see how messed up everything gets. Maybe the main valuable thing that has leaked here is how to build a great reactive / responsive TUI.

Apparently Cursor harness > Codex harness > Claude Code harness (consistently found Codex to be stronger than CC myself). I can't see how there is much "secret agent sauce" that have leaked here that the competitors are interested in given that the leaked sauce is weaker.

edwin @edwinarbus

3 months ago

Matt Maher tested frontier models in Cursor v. other harnesses. Cursor boosted model performance by 11% on average: Gemini: 52% → 57% GPT-5.4: 82% → 88% Opus: 77% → 93% His benchmark measures how well models implement a 100-feature PRD. @cursor_ai consistently outperformed.

125 125 1K 911K 845