Baron

I don't entertain mediocrity

[Baron @brn_rdrg]

He who will not risk cannot win

[dom @dearooz]

new load-bearing internet comment just dropped

[Ivana @ivanainai]

Unpopular opinion: your results with AI depend heavily on how smart you are.

[Duncan Lutz @duncanthedev]

fellas, if your girl:
- is short
- is insecure
- is only 4

that's not your girl. that's an eMudhra private key

[Namo @lovesicknamo]

Indian Insta fmu 😭😭

[Sahil Bloom @SahilBloom]

I regret to inform you that nobody cares about your potential. Potential is nothing without execution. When you're young, everyone cares about your potential. You get used to focusing on it. But as you get older, no one cares about your potential. Just your delivery against it.

[the artidote @TheArtidote]

Now THAT is a reframe.

[Ossy Vincent @ossynoya]

I just love this denial stage you’re in now. Even we developers had that in 2023 too 😂😂😂

[lauren @poteto]

@santiagomed try /technical-writing

https://t.co/IVidtoiues

[Kenney @KenneyNL]

I've made 6 open-source @godotengine projects perfect for as a base for your first or next game. Completely human-made and easy to understand code & comments. All visuals and sounds included, CC0!

https://t.co/AoiHzF2zGU

[Leon Lin @LexnLin]

TasteSkill v2.1 is out!

this time we went all in on dashboards and the small details
go create better websites with tasteskill now and some dashboards :)

npx skills add Leonxlnx/taste-skill

[Odd ☆☆ @nemui_nekoooo]

AI is a mirror. lazy people get lazy results. curious people get superpowers.

[SumitX @Sumits_X]

WHAT ??

[ina @trinavere]

no cuz this is the most creative masterpiece i've ever seen on ph tv. after 12 years, this is still an iconic magpasikat performance for me. the way their faces went from confused to completely blown away. you just had to be there. ended the "yun na 'yon?" comment. 🤩💥

[Remirose 🫴🌹 | envtuber @deaddoremi]

WDYM 15 AMERICAN DOLLARS IS NOW EQUAL TO 1000 FILIPINO PESO WHAT THE FUCK

[Ben Davis @davis7]

It feels like Opus 5.5 has pretty much broken the entire model landscape

At this point for a model to be interesting it has to do something novel and different, the "15% worse but way cheaper!" thing just doesn't work anymore (not that it ever really did, but I think 5.5 has made it way worse since it's so good on every metric)

It's why I liked/defended muse wonder full and am still using it a ton. The thing it has that's novel is it's "voice". It's close enough to frontier to be usable, but unlike the other stuff in this bucket it doesn't feel like a watered down Claude and as such I actually kept using it

In order for a model to matter outside of OpenAI and Anthropic at this point it has to have some novel capability. And I think in order for it to get large scale attention it has to be something easily showcase-able similar to the 3D stuff from Astra.

The "voice" of muse wonder full is something you can't really show in a catchy way on here and only matters when you feel it which requires getting a $50/mo. Meta sub which no one is going to do thus no one cares about the model. Which sucks because I like it, but also they did this to themselves. The wonder drop was really screwed up: horrible names for the model, limited to the sub for the good model, etc.

[Token Gremlin @TokenGremlin]

It's not that GPT-6.1 Sol is bad. It's an excellent model, and you can do a ton of things with it.

But Opus 5.5 is simply on another level. A whole tier above.

[Claudio @kazzkiq]

Opus 5.5 é um milestone. Esse modelo deveria ser gravado em hardware e vendido em chips com inferência 10-100x mais rápida. Já ia atender 99,99% da população e dos casos de uso

[Addy Osmani @addyosmani]

Give your agent a way to verify its work. This can dramatically improve the quality of output.

With this process in place, Claude Code was able to write 90%+ of its code itself. When generating software at a faster rate than you can review it, the bottleneck shifts to proving that it works. @bcherny and team invested enough in verification, we've been able to move fast while maintaining stability.

Code reviews aren't going away, but you need to think of it differently. One human reading through line-by-line is no longer going to work as a gate, it needs to evolve into a multi-layered verification system, built with fast deterministic feedback loops for your agents.

This is where e2e tests, feature maps (as @poteto has been advocating), property tests and multi-agent adversarial reviews come in. These all provide opportunities to catch errors early and fix them before things get out of hand.

You don't have enough eyeballs for the amount of code being written so your focus needs to be on product intent, risk assessment and evaluating evidence rather than reviewing code. Delegate the code checking work to your automated tests, scale your approvals based on risk, and turn your test failures into living evaluations. This approach helps maintain speed without losing reliability.

Let the agents do what they do best and let you focus on what makes you irreplaceable: judgement, direction, and ownership. We tried to capture how we handle code review and verification in this writeup. Hopefully it's helpful.

[Twilight @BitesDev]

WRITE ALL PUBLIC FACING TEXT YOURSELF

[† lucia scarlet 🩸 @luciascarlet]

software engineers will vibe code better software than people without development experience because they’ll already have an idea of what they want and how they want it to work