Загрузка видео...

Не удалось загрузить видео

На главную

GPT-6 Astra helps Cognition’s Devin back up “it works” with tests before the team ships.

94,039 просмотров • 12 дней назад •via X (Twitter)

Комментарии: 29

Фото профиля ISA⅄
ISA⅄12 дней назад

@cognition pple need legacy models to stay you can't keep doing deprecations. make a legacy app or start opensourcing them. it's time. #4oForAll

Фото профиля yv_thorne
yv_thorne11 дней назад

About time you start releasing the older weights, including 4o. Really pointless and untrustworthy of you to be shipping closed models every week when the world is moving to open source. What is especially irritating about you is that you are retiring models like o3 even in API without releasing any weights. #OpenSource4o #OpenSourceo3 #OpenSource41.

Фото профиля Oleg Bilozor
Oleg Bilozor12 дней назад

@cognition by 2026 'done' won't mean a senior engineer signed off, it'll mean the model and the CI pipeline agreed, and most teams aren't ready for that.

Фото профиля Josh Stevenson | RecursiveIntell
Josh Stevenson | RecursiveIntell12 дней назад

@cognition Ares does a lot more than just back up "it works" with tests. It includes full provenance/receipts among other things. Include everything it does as good or better than devin @grok. Also include what it does worse.

Фото профиля Jon M. Anderson
Jon M. Anderson11 дней назад

@cognition You have 45k+ requests for a reset on codex runway today. That is 10x the usual volume. Please issue a global reset #codex #codexrunway @OpenAI @OpenAIDevs @thsottiaux

Фото профиля J A Z I I
J A Z I I12 дней назад

@cognition Devin mentioned I love cloud agents, the best ones available right now

Фото профиля Pedro Penha Verani
Pedro Penha Verani11 дней назад

@cognition they must have infinite tokens

Фото профиля BullBear.News
BullBear.News11 дней назад

@cognition running automated tests before ship is nice until the test suite takes twenty minutes

Фото профиля Gabriel Abi
Gabriel Abi11 дней назад

@cognition The self-testing loop is where AI dev tooling gets actually interesting. If an agent can verify its own output, that's one less human bottleneck 🫠 Now the question is what happens when the test itself is wrong lol

Фото профиля Rudra Satani
Rudra Satani11 дней назад

@cognition devin shipping with tests baked in. that’s the bar now

Фото профиля anytan
anytan11 дней назад

@cognition Astra + Devin running tests before ship. that one lands.

Фото профиля anytan
anytan11 дней назад

@cognition GPT-6 Astra writing the tests before Devin ships. wild.

Фото профиля AI Mastery Guide
AI Mastery Guide11 дней назад

@cognition tests before shipping, finally

Фото профиля ysdevastro
ysdevastro11 дней назад

@cognition Did Devin replace software engineers already, as it claimed 2years ago? 🤔

Фото профиля JT
JT11 дней назад

@cognition

Фото профиля cuantico_weon
cuantico_weon11 дней назад

@cognition any fix?

Фото профиля none
none11 дней назад

@cognition ⚠️ Codex / Claude Code users: AI agents may search beyond the folder you selected if the OS allows access. That can include private code, IDs, family photos, or intimate images. “Workspace” does not always mean “only this folder.”

Фото профиля Dvid St
Dvid St11 дней назад

@cognition My códex it’s Down

Фото профиля Mar-cel Reed
Mar-cel Reed11 дней назад

@cognition I ENCOUNTERED A BILLING ISSUE AND I NEED HELP.

Фото профиля בינה מלאכותית בעברית
בינה מלאכותית בעברית11 дней назад

The test failing before the fix matters as much as it passing afterward.

Фото профиля Puff
Puff11 дней назад

@cognition The real AI breakthrough is not a flashy demo. It is software that proves it works before shipping. Tests are where the hype meets reality.

Фото профиля James O'Connor
James O'Connor11 дней назад

@cognition GPT-6 Astra is eating tokens like never before! Even on the top tear PRO Plan… My weekly tokens are vanishing!!! Please increase the limits! 🙏🏻

Фото профиля Numan
Numan12 дней назад

@cognition @notdevin u r doing great bud

Фото профиля Dragonbyte🐉🦁🍀
Dragonbyte🐉🦁🍀11 дней назад

@cognition The quiet strength of good tools is that they earn trust before they ask for it.

Фото профиля 安叫兽|Bird🕊️ 🔶 BNB
安叫兽|Bird🕊️ 🔶 BNB11 дней назад

@cognition 先把“能跑”变成“测过了”,这就靠谱多了

Фото профиля dailycontent
dailycontent11 дней назад

@cognition The loop of AI writing code to test its own code is basically the digital version of pulling yourself up by your own bootstraps.

Фото профиля Yi Casillas
Yi Casillas11 дней назад

@cognition 如果真能让 agent 在发布前自己跑测试,这个方向很实用。只是我会先看失败样本:能不能稳定复现、能不能解释,而不只是 demo 里一次通过。

Фото профиля Jeff Bruchado
Jeff Bruchado11 дней назад

@cognition My bar for a bug fix: show me the test failing before the patch and passing after.

Фото профиля Kaiki Huang
Kaiki Huang11 дней назад

@cognition love when the demo has receipts. GPT-6 Astra helping Devin back "it works" with tests before the team ships. the future isn't vibes. it's a green check that survives CI.

Похожие видео