Sponsored
$5/week ↗

September 29, 2026 / DevDay

OpenAI DevDay, in a minute

Dots moved from a name to an always-on personal agent. Here are the few announcements worth knowing, with sources.

Dots: OpenAI introduced a personal agent powered by GPT-6 Astra. It has a cloud computer, works across approved connected apps, and can continue tasks between conversations. Rollout starts with eligible Pro, Business Premium, and Enterprise users. OpenAI product guide

Beyond Dots: DevDay also brought ChatGPT Space for shared work, GPT-6.1 Sol for Work and Codex, a Decisions API, and more cloud Codex capabilities. Availability and pricing differ by product. Event report · Model availability

For builders: The clearest shift is toward agents that keep working, use connected context, and bring results back for review. OpenAI says users can set rules for actions and choose when their dot should ask first. Controls and setup

The reaction

Do we like DevDay?

+5
score
How the score works
Like15 × +1
Neutral6 × 0
Dislike10 × -1
Net score+5

All 31 reviewed X posts count. Filters change the cards only.

Reactions on X

31 reviewed posts
Peter Yang@petergyang

OpenAI's new always-on agent, dots, is here! Here's my new video showing you how it works and how it compares to Grok Bot and Muse. I've been testing it for a few days and it: → Flagged a five-figure revenue opportunity → Got my mobile app ready for launch → Made some great memes in Slack dots' biggest advantage is that it's natively integrated into ChatGPT, but that also comes with some trade-offs. 📌 Watch now: https://youtu.be/z5X1eMU6isI

NeutralRead full post ↗

Peter Yang

@petergyang

OpenAI's new always-on agent, dots, is here! Here's my new video showing you how it works and how it compares to Grok Bot and Muse. I've been testing it for a few days and it: → Flagged a five-figure revenue opportunity → Got my mobile app ready for launch → Made some great memes in Slack dots' biggest advantage is that it's natively integrated into ChatGPT, but that also comes with some trade-offs. 📌 Watch now: https://youtu.be/z5X1eMU6isI

Dan Shipper@danshipper

BREAKING: @OpenAI just announced Dots—always-on agents in ChatGPT I've been testing it for the last few days @every, here's a quick vibe check: What you should know: - They'll look familiar if you've used OpenClaw, Muse, Instinct, or Grok Bots. - Your Dot sits in the redesigned ChatGPT sidebar right below the “New chat” button - It has its own cloud computer that lets it work while your laptop is closed. You can text it any time or call it on the phone. Vibe check—the good When it’s working, it changes the way I use ChatGPT: I interact with Boo (my Dot’s name), and Boo orchestrates ChatGPT threads, reads my email, uses Slack, and more. It automatically filters incoming Slack requests and emails so I can quickly triage items without opening my inbox. When I was rescheduling a flight, Boo warned me that my new flight time would conflict with a meeting request from Slack that I hadn’t read. That’s the promise: an ongoing agent that filters what needs my attention and acts proactively on my behalf, in one long-running chat thread. Vibe check—the bad But the version I tested over the last few days was buggy and lacked some features I would expect, like iMessage support. I had frequent issues with permissions and dropped messages, and my Dot was unable to connect to its own in-app browser. The verdict During testing, I found myself reaching for my Dot over starting new Codex threads, so it has definitely become a habit despite the frustration. And during the tesitng period the team was rapidly fixing issues—so I'd expect most of this to be smoothed out over the coming days and weeks. Unless you love new things with rough edges, I’d recommend waiting a week or two to try it. OpenAI will have solved a lot of these paper cuts by then. If you’re already deep into Grok Bots, Muse, or Instinct, it’s probably not an immediate switch unless you’re also a big ChatGPT or Codex user. Read the live feed on @every: https://every.to/live/openai-devday-2026

NeutralRead full post ↗

Dan Shipper

@danshipper

BREAKING: @OpenAI just announced Dots—always-on agents in ChatGPT I've been testing it for the last few days @every, here's a quick vibe check: What you should know: - They'll look familiar if you've used OpenClaw, Muse, Instinct, or Grok Bots. - Your Dot sits in the redesigned ChatGPT sidebar right below the “New chat” button - It has its own cloud computer that lets it work while your laptop is closed. You can text it any time or call it on the phone. Vibe check—the good When it’s working, it changes the way I use ChatGPT: I interact with Boo (my Dot’s name), and Boo orchestrates ChatGPT threads, reads my email, uses Slack, and more. It automatically filters incoming Slack requests and emails so I can quickly triage items without opening my inbox. When I was rescheduling a flight, Boo warned me that my new flight time would conflict with a meeting request from Slack that I hadn’t read. That’s the promise: an ongoing agent that filters what needs my attention and acts proactively on my behalf, in one long-running chat thread. Vibe check—the bad But the version I tested over the last few days was buggy and lacked some features I would expect, like iMessage support. I had frequent issues with permissions and dropped messages, and my Dot was unable to connect to its own in-app browser. The verdict During testing, I found myself reaching for my Dot over starting new Codex threads, so it has definitely become a habit despite the frustration. And during the tesitng period the team was rapidly fixing issues—so I'd expect most of this to be smoothed out over the coming days and weeks. Unless you love new things with rough edges, I’d recommend waiting a week or two to try it. OpenAI will have solved a lot of these paper cuts by then. If you’re already deep into Grok Bots, Muse, or Instinct, it’s probably not an immediate switch unless you’re also a big ChatGPT or Codex user. Read the live feed on @every: https://every.to/live/openai-devday-2026

Paul Hudson@twostraws

I got to try ChatGPT’s new dots personal assistant ahead of time as part of their Dev Early Access Community testing. TL;DR: It saved my day today. Longer version: I had an early train to London today. I woke up to find it had been cancelled (yay, UK trains!), and I had to get a later train – I would end up being late for my event, and the later train would likely be swamped with people. There was an earlier train available, but it was in 20 minutes; there was no way I could get there in time. It turns out that my dot had spotted the problem, read the cancellation email to see my ticket was valid on earlier trains, then looked up the live tracking for the earlier train and found that it was running late – it hadn’t even left its starting station yet. It did this with zero input from me; not even an initial request, just fully autonomously. So, I was able to leave more or less as normal, head to the train station, and catch the earlier train just fine. Train: Caught. Day: Saved. Me: Impressed.

LikeRead full post ↗

Paul Hudson

@twostraws

I got to try ChatGPT’s new dots personal assistant ahead of time as part of their Dev Early Access Community testing. TL;DR: It saved my day today. Longer version: I had an early train to London today. I woke up to find it had been cancelled (yay, UK trains!), and I had to get a later train – I would end up being late for my event, and the later train would likely be swamped with people. There was an earlier train available, but it was in 20 minutes; there was no way I could get there in time. It turns out that my dot had spotted the problem, read the cancellation email to see my ticket was valid on earlier trains, then looked up the live tracking for the earlier train and found that it was running late – it hadn’t even left its starting station yet. It did this with zero input from me; not even an initial request, just fully autonomously. So, I was able to leave more or less as normal, head to the train station, and catch the earlier train just fine. Train: Caught. Day: Saved. Me: Impressed.

Beda@beda098281867

In a discussion of European availability, Beda described paying the same subscription price while missing new features such as Dots and facing what they perceived as reduced usage allowances. They found DevDay underwhelming. This records a subscriber complaint, not verified billing terms or a legal explanation of regional access.

DislikeRead reaction ↗

Beda

@beda098281867

Editorial summary. Read the original on X.

In a discussion of European availability, Beda described paying the same subscription price while missing new features such as Dots and facing what they perceived as reduced usage allowances. They found DevDay underwhelming. This records a subscriber complaint, not verified billing terms or a legal explanation of regional access.

Posted Sep 29, 2026, 10:10 PM ET. 1 view shown on X as of Sep 29, 2026, 10:12 PM ET.

Allie K. Miller@alliekmiller

Allie welcomed always-on agents and persistent environments as a way to give AI ongoing responsibilities. She also argued that proactive agents shift context-switching onto the user and that chat threads have not solved multitasking. Her launch assessment combines enthusiasm for the direction with concerns about the interface, naming and early bugs.

NeutralRead reaction ↗

Allie K. Miller

@alliekmiller

Editorial summary. Read the original on X.

Allie welcomed always-on agents and persistent environments as a way to give AI ongoing responsibilities. She also argued that proactive agents shift context-switching onto the user and that chat threads have not solved multitasking. Her launch assessment combines enthusiasm for the direction with concerns about the interface, naming and early bugs.

Posted Sep 29, 2026, 9:12 PM ET. 3,000 views shown on X as of Sep 29, 2026, 10:12 PM ET.

Marc@MarcDagatan

Marc initially dismissed GPT-6.1 Sol while watching DevDay and reading the release benchmarks. After trying it, he found it capable and efficient. He explicitly qualified this as an impression from use rather than a measured evaluation.

LikeRead reaction ↗

Marc

@MarcDagatan

Editorial summary. Read the original on X.

Marc initially dismissed GPT-6.1 Sol while watching DevDay and reading the release benchmarks. After trying it, he found it capable and efficient. He explicitly qualified this as an impression from use rather than a measured evaluation.

Posted Sep 29, 2026, 8:34 PM ET. 94 views shown on X as of Sep 29, 2026, 9:24 PM ET.

Josh Robertson@josh_rob04

Josh reported that after a call with his Dots agent, Codex was operating his computer autonomously and the agent was expected to call back when finished. The post describes work in progress; it does not confirm completion or give an explicit overall verdict.

NeutralRead reaction ↗

Josh Robertson

@josh_rob04

Editorial summary. Read the original on X.

Josh reported that after a call with his Dots agent, Codex was operating his computer autonomously and the agent was expected to call back when finished. The post describes work in progress; it does not confirm completion or give an explicit overall verdict.

Posted Sep 29, 2026, 8:29 PM ET. 16 views shown on X as of Sep 29, 2026, 9:24 PM ET.

Joel Castillo@joeldev_

Joel reported asking Dots to find 100 items. According to his post, it found 20, acknowledged that 80 remained and then stopped. He found it unreliable for longer tasks and said he would keep using Muse. This is one user report, not a reproduced reliability test.

DislikeRead reaction ↗

Joel Castillo

@joeldev_

Editorial summary. Read the original on X.

Joel reported asking Dots to find 100 items. According to his post, it found 20, acknowledged that 80 remained and then stopped. He found it unreliable for longer tasks and said he would keep using Muse. This is one user report, not a reproduced reliability test.

Posted Sep 29, 2026, 8:25 PM ET. 18 views shown on X as of Sep 29, 2026, 9:24 PM ET.

bitslix@bitslix

Replying to another user enjoying Sol 6.1, bitslix said it was not available in their Codex experience and described DevDay as a mess. They later identified their Pro plan and acknowledged that access might depend on the plan. Other replies suggested updating the app; this is a report of launch frustration, not verified universal unavailability.

DislikeRead reaction ↗

bitslix

@bitslix

Editorial summary. Read the original on X.

Replying to another user enjoying Sol 6.1, bitslix said it was not available in their Codex experience and described DevDay as a mess. They later identified their Pro plan and acknowledged that access might depend on the plan. Other replies suggested updating the app; this is a report of launch frustration, not verified universal unavailability.

Posted Sep 29, 2026, 6:59 PM ET. 1,521 views shown on X as of Sep 29, 2026, 11:14 PM ET.

Stefano@StefanoGPT

Stefano found the long pauses during a DevDay demonstration uncomfortable to watch and expressed sympathy for the presenter. He also acknowledged that this is a risk of doing a live keynote. The criticism concerns the presentation, not a measured product failure rate.

DislikeRead reaction ↗

Stefano

@StefanoGPT

Editorial summary. Read the original on X.

Stefano found the long pauses during a DevDay demonstration uncomfortable to watch and expressed sympathy for the presenter. He also acknowledged that this is a risk of doing a live keynote. The criticism concerns the presentation, not a measured product failure rate.

Posted Sep 29, 2026, 6:46 PM ET. 2,319 views shown on X as of Sep 29, 2026, 9:23 PM ET.

Bhavy☄️@Bhavani_00007

Responding to Harshith's cyclist-animation comparison, Bhavy saw an improvement in the new Sol but thought it still fell short of Astra. The reply offers a mixed assessment of the shared example, not an independent benchmark.

NeutralRead reaction ↗

Bhavy☄️

@Bhavani_00007

Editorial summary. Read the original on X.

Responding to Harshith's cyclist-animation comparison, Bhavy saw an improvement in the new Sol but thought it still fell short of Astra. The reply offers a mixed assessment of the shared example, not an independent benchmark.

Posted Sep 29, 2026, 4:56 PM ET. 753 views shown on X as of Sep 29, 2026, 9:24 PM ET.

Vipin@vipinxtwt

Watching the DevDay stream, Vipin criticized two demos: he reported that the dot did not respond and that voice chat failed during a Codex demonstration. He attached two clips he said he recorded live. This is his reaction to the demonstrations, not a test of everyday product reliability.

DislikeRead reaction ↗

Vipin

@vipinxtwt

Editorial summary. Read the original on X.

Watching the DevDay stream, Vipin criticized two demos: he reported that the dot did not respond and that voice chat failed during a Codex demonstration. He attached two clips he said he recorded live. This is his reaction to the demonstrations, not a test of everyday product reliability.

Posted Sep 29, 2026, 4:09 PM ET. 30.3K views shown on X as of Sep 29, 2026, 9:12 PM ET.

Casper Overgaard@casperoverg

Casper described his overall reaction as positive, with hopes for Dots and Spaces. He reserved judgment until the products prove themselves and said GPT-6.1 Sol would be appealing if its capabilities justify the cost. His approval is conditional, not a performance claim.

LikeRead reaction ↗

Casper Overgaard

@casperoverg

Editorial summary. Read the original on X.

Casper described his overall reaction as positive, with hopes for Dots and Spaces. He reserved judgment until the products prove themselves and said GPT-6.1 Sol would be appealing if its capabilities justify the cost. His approval is conditional, not a performance claim.

Posted Sep 29, 2026, 4:07 PM ET. 297 views shown on X as of Sep 29, 2026, 8:36 PM ET.

Harshith@HarshithLucky3

Harshith compared GPT-6.1 Sol and GPT-6 Sol in Codex using the same cyclist-animation prompt and reported a large improvement. In replies, he still preferred a competing model for details of the animation. This is a task-specific user assessment, not a general model ranking.

LikeRead reaction ↗

Harshith

@HarshithLucky3

Editorial summary. Read the original on X.

Harshith compared GPT-6.1 Sol and GPT-6 Sol in Codex using the same cyclist-animation prompt and reported a large improvement. In replies, he still preferred a competing model for details of the animation. This is a task-specific user assessment, not a general model ranking.

Posted Sep 29, 2026, 4:04 PM ET. 38.3K views shown on X as of Sep 29, 2026, 9:23 PM ET.

Alex Finn@AlexFinn

After early access, Alex said he liked Dots for its ChatGPT context, tools and ability to start Codex threads while away from his desktop. He did not find it radically different from other agents and saw less value for simple reservation tasks, but praised it for advanced daily work.

LikeRead reaction ↗

Alex Finn

@AlexFinn

Editorial summary. Read the original on X.

After early access, Alex said he liked Dots for its ChatGPT context, tools and ability to start Codex threads while away from his desktop. He did not find it radically different from other agents and saw less value for simple reservation tasks, but praised it for advanced daily work.

Posted Sep 29, 2026, 3:36 PM ET. 51.6K views shown on X as of Sep 29, 2026, 9:24 PM ET.

Rubens Soto | AI & SaaS@rubenssoto_ai

Replying to Irushi, Rubens called it a good event with worthwhile improvements, including a cheaper model and an agent that looked promising. He found nothing shocking and qualified the value as strongest for people who want to stay entirely within the OpenAI ecosystem.

LikeRead reaction ↗

Rubens Soto | AI & SaaS

@rubenssoto_ai

Editorial summary. Read the original on X.

Replying to Irushi, Rubens called it a good event with worthwhile improvements, including a cheaper model and an agent that looked promising. He found nothing shocking and qualified the value as strongest for people who want to stay entirely within the OpenAI ecosystem.

Posted Sep 29, 2026, 3:27 PM ET. 68 views shown on X as of Sep 29, 2026, 7:05 PM ET.

Ishu Agrawal@ishuagra02

Ishu expressed disappointment that the launch message did not clearly distinguish Dots conversations from agentic work that draws on usage allowances. He highlighted the temporary first-month exemption. This records his criticism of the communication, rather than offering a current billing guide.

DislikeRead reaction ↗

Ishu Agrawal

@ishuagra02

Editorial summary. Read the original on X.

Ishu expressed disappointment that the launch message did not clearly distinguish Dots conversations from agentic work that draws on usage allowances. He highlighted the temporary first-month exemption. This records his criticism of the communication, rather than offering a current billing guide.

Posted Sep 29, 2026, 3:19 PM ET. 22.7K views shown on X as of Sep 29, 2026, 9:24 PM ET.

Andrew Southworth@southwortha

Replying to Irushi, Andrew praised the idea behind Dots and the apparent performance for the price of GPT-6.1 Sol. He also welcomed the Decisions API, Codex Cloud improvements and Ultrafast mode. This was his reaction to the announcements, not a measured hands-on benchmark.

LikeRead reaction ↗

Andrew Southworth

@southwortha

Editorial summary. Read the original on X.

Replying to Irushi, Andrew praised the idea behind Dots and the apparent performance for the price of GPT-6.1 Sol. He also welcomed the Decisions API, Codex Cloud improvements and Ultrafast mode. This was his reaction to the announcements, not a measured hands-on benchmark.

Posted Sep 29, 2026, 3:03 PM ET. 166 views shown on X as of Sep 29, 2026, 7:05 PM ET.

Eduarda Ferreira@eduardadotai

Eduarda challenged the impression that Dots would perform tasks without consuming usage. She distinguished chatting with an assistant from work delegated to Codex and compared it with her existing ChatGPT workflow. Her criticism is about how the allowance was communicated.

DislikeRead reaction ↗

Eduarda Ferreira

@eduardadotai

Editorial summary. Read the original on X.

Eduarda challenged the impression that Dots would perform tasks without consuming usage. She distinguished chatting with an assistant from work delegated to Codex and compared it with her existing ChatGPT workflow. Her criticism is about how the allowance was communicated.

Posted Sep 29, 2026, 2:55 PM ET. 3,571 views shown on X as of Sep 29, 2026, 9:23 PM ET.

Princess Inga of Bavaria@inga_of65412

Replying to Token Gremlin, Inga expressed disappointment and felt the announcements offered nothing for Plus users. She also criticized the Dots domain choice. This records her perception of the event, not a verified inventory of Plus features or domain ownership.

DislikeRead reaction ↗

Princess Inga of Bavaria

@inga_of65412

Editorial summary. Read the original on X.

Replying to Token Gremlin, Inga expressed disappointment and felt the announcements offered nothing for Plus users. She also criticized the Dots domain choice. This records her perception of the event, not a verified inventory of Plus features or domain ownership.

Posted Sep 29, 2026, 2:42 PM ET. 1,352 views shown on X as of Sep 29, 2026, 8:37 PM ET.

Julien | griotta@itzs_julien

Julien called support for compatible Claude Code plugins in Codex his favorite DevDay announcement. His replies explicitly welcomed interoperability while cautioning that Claude-specific hook handlers may need adapting. This records his positive developer reaction, not a claim that every plugin works unchanged.

LikeRead reaction ↗

Julien | griotta

@itzs_julien

Editorial summary. Read the original on X.

Julien called support for compatible Claude Code plugins in Codex his favorite DevDay announcement. His replies explicitly welcomed interoperability while cautioning that Claude-specific hook handlers may need adapting. This records his positive developer reaction, not a claim that every plugin works unchanged.

Posted Sep 29, 2026, 2:41 PM ET. 601 views shown on X as of Sep 29, 2026, 11:14 PM ET.

rexsperma@rexsperma

Replying to Token Gremlin, rexsperma welcomed shared workspaces, an always-on bot and Codex in the cloud as answers to three personal pain points. The post expresses enthusiasm for the announced workflows without documenting a hands-on test.

LikeRead reaction ↗

rexsperma

@rexsperma

Editorial summary. Read the original on X.

Replying to Token Gremlin, rexsperma welcomed shared workspaces, an always-on bot and Codex in the cloud as answers to three personal pain points. The post expresses enthusiasm for the announced workflows without documenting a hands-on test.

Posted Sep 29, 2026, 2:27 PM ET. 505 views shown on X as of Sep 29, 2026, 8:36 PM ET.

Irushi@Im_IrushiK

Irushi found DevDay underwhelming. Although Dots sounded interesting, they wanted better models and more usage rather than a higher-priced subscription tier. Their criticism centered on the announced Pro plan limits and value for existing users.

DislikeRead reaction ↗

Irushi

@Im_IrushiK

Editorial summary. Read the original on X.

Irushi found DevDay underwhelming. Although Dots sounded interesting, they wanted better models and more usage rather than a higher-priced subscription tier. Their criticism centered on the announced Pro plan limits and value for existing users.

Posted Sep 29, 2026, 2:01 PM ET. 25K views shown on X as of Sep 29, 2026, 7:05 PM ET.

Robin Ebers@robinebers

Robin said DevDay reversed his pessimism, highlighting Dots, Sol 6.1, Ultrafast and subscription sign-in for other applications. In a follow-up, he welcomed Ultrafast but sharply criticized its price and suggested research-preview positioning. His overall launch reaction was positive, with a substantial pricing reservation.

LikeRead reaction ↗

Robin Ebers

@robinebers

Editorial summary. Read the original on X.

Robin said DevDay reversed his pessimism, highlighting Dots, Sol 6.1, Ultrafast and subscription sign-in for other applications. In a follow-up, he welcomed Ultrafast but sharply criticized its price and suggested research-preview positioning. His overall launch reaction was positive, with a substantial pricing reservation.

Posted Sep 29, 2026, 1:56 PM ET. 11.2K views shown on X as of Sep 29, 2026, 11:14 PM ET.

Dennis@eekfuh

OpenAI launched dots today. I’ve been using them personally and professionally for weeks. My top 3 hacks to get the most out of your dot: 1. Stay on a phone call all day with your dot. Chat while you work and let your dot keep you updated on what’s happening around you and your team 2. Give your dot and your other agents, like Instinct, access to a shared Google Doc and tell them to coordinate using it 3. Have it create and improve skills for your recurring work, then set up automations to use them. Share those skills with your coworkers and be the office hero

LikeRead full post ↗

Dennis

@eekfuh

OpenAI launched dots today. I’ve been using them personally and professionally for weeks. My top 3 hacks to get the most out of your dot: 1. Stay on a phone call all day with your dot. Chat while you work and let your dot keep you updated on what’s happening around you and your team 2. Give your dot and your other agents, like Instinct, access to a shared Google Doc and tell them to coordinate using it 3. Have it create and improve skills for your recurring work, then set up automations to use them. Share those skills with your coworkers and be the office hero

Mark Kretschmann@mark_k

Mark described the reported exclusion of Europe from the Dots rollout as bad news for users there. This captures his disappointment about access at launch; it is not a claim about permanent availability or a country-by-country eligibility guide.

DislikeRead reaction ↗

Mark Kretschmann

@mark_k

Editorial summary. Read the original on X.

Mark described the reported exclusion of Europe from the Dots rollout as bad news for users there. This captures his disappointment about access at launch; it is not a claim about permanent availability or a country-by-country eligibility guide.

Posted Sep 29, 2026, 1:44 PM ET. 36.1K views shown on X as of Sep 29, 2026, 9:23 PM ET.

VraserX e/acc@VraserX

VraserX was excited by the Dots announcement, especially the idea of an assistant that learns personal context and acts rather than only answering messages. The post describes enthusiasm for the demonstrated concept, not a hands-on evaluation or evidence of AGI.

LikeRead reaction ↗

VraserX e/acc

@VraserX

Editorial summary. Read the original on X.

VraserX was excited by the Dots announcement, especially the idea of an assistant that learns personal context and acts rather than only answering messages. The post describes enthusiasm for the demonstrated concept, not a hands-on evaluation or evidence of AGI.

Posted Sep 29, 2026, 1:37 PM ET. 77.4K views shown on X as of Sep 29, 2026, 9:23 PM ET.

Max Weinbach@mweinbach

Max, an early-access tester, praised Dots for coordinating cloud Codex threads with tools on his computer and keeping conversations in sync across clients. His linked first impression described easier task and thread management. These are his reported workflow benefits.

LikeRead reaction ↗

Max Weinbach

@mweinbach

Editorial summary. Read the original on X.

Max, an early-access tester, praised Dots for coordinating cloud Codex threads with tools on his computer and keeping conversations in sync across clients. His linked first impression described easier task and thread management. These are his reported workflow benefits.

Posted Sep 29, 2026, 1:30 PM ET. 28.4K views shown on X as of Sep 29, 2026, 9:24 PM ET.

Dan McAteer@daniel_mac8

'dots' — OpenAI's new proactive personal agent is HERE! I was part of Dev Early Access Community testing. To sum up my experience in a word: > 'Proactivity' An illustration from my testing: dot proactively picked up on an invoice I needed to send for my freelance writing, pulled the relevant details from the email thread and drafted the invoice. After I approved it, dot sent the invoice as a PDF. It was a great example of real-world, practical value. My plan is to continue testing by giving "Shaine" (what I call my dot) a set of ideal states I want to move into. Things like: - Creating my own business - Expanding my subscription base for Attention Heads - Helping me nurture the relationships with my family & friends And allow Shaine to work 24/7 to help me achieve the life I envision, while being a benevolent presence in the world.

LikeRead full post ↗

Dan McAteer

@daniel_mac8

'dots' — OpenAI's new proactive personal agent is HERE! I was part of Dev Early Access Community testing. To sum up my experience in a word: > 'Proactivity' An illustration from my testing: dot proactively picked up on an invoice I needed to send for my freelance writing, pulled the relevant details from the email thread and drafted the invoice. After I approved it, dot sent the invoice as a PDF. It was a great example of real-world, practical value. My plan is to continue testing by giving "Shaine" (what I call my dot) a set of ideal states I want to move into. Things like: - Creating my own business - Expanding my subscription base for Attention Heads - Helping me nurture the relationships with my family & friends And allow Shaine to work 24/7 to help me achieve the life I envision, while being a benevolent presence in the world.

Maximiliano Firtman@maxifirtman

OpenAI lanza "dots" dentro de ChatGPT, agentes personales siempre activos y proactivos para ayudarte. Vengo usándolo hace unos días como parte de un programa de OpenAI; la diferencia con el chat normal es que la conversación es como si fuera WhatsApp y te manda mensajes el dot cuando necesita confirmar algo con vos. Los dots tienen una computadora con Linux para usar en la nube que también vos podés usar desde la app de ChatGPT para instalar apps o loguearte en sitios. En mis primeros minutos me dio impresión. Inmediatamente tomó mi historial con ChatGPT y mi mail y sin mediar ningún mensaje ni pedido, empezó a decirme cosas revisando historial e hilos de conversación. Me encontró la solución a un bug de un cliente que todavía tenía que contestarle. Me mandó cosas como "ojo que le dijiste a X que podías a las 3 el viernes pero a las 3 le habías dicho a Y que ibas a dar el curso". En un momento me dijo "disculpá, pero para chequear, ¿fuiste vos que entraste a tu gmail desde otro dispositivo?" controlando la seguridad de mi cuenta porque le pareció "sospechoso". También se pasó a veces, sobrecomplicando las situaciones. Se lo dije, veremos si lo aprendió. Dots funciona dentro de la app mobile y la app de desktop. A cada dot le ponés un nombre y un avatar.

NeutralRead full post ↗

Maximiliano Firtman

@maxifirtman

OpenAI lanza "dots" dentro de ChatGPT, agentes personales siempre activos y proactivos para ayudarte. Vengo usándolo hace unos días como parte de un programa de OpenAI; la diferencia con el chat normal es que la conversación es como si fuera WhatsApp y te manda mensajes el dot cuando necesita confirmar algo con vos. Los dots tienen una computadora con Linux para usar en la nube que también vos podés usar desde la app de ChatGPT para instalar apps o loguearte en sitios. En mis primeros minutos me dio impresión. Inmediatamente tomó mi historial con ChatGPT y mi mail y sin mediar ningún mensaje ni pedido, empezó a decirme cosas revisando historial e hilos de conversación. Me encontró la solución a un bug de un cliente que todavía tenía que contestarle. Me mandó cosas como "ojo que le dijiste a X que podías a las 3 el viernes pero a las 3 le habías dicho a Y que ibas a dar el curso". En un momento me dijo "disculpá, pero para chequear, ¿fuiste vos que entraste a tu gmail desde otro dispositivo?" controlando la seguridad de mi cuenta porque le pareció "sospechoso". También se pasó a veces, sobrecomplicando las situaciones. Se lo dije, veremos si lo aprendió. Dots funciona dentro de la app mobile y la app de desktop. A cada dot le ponés un nombre y un avatar.

Antonio Leiva@antonioleivag

🚨🚨 OpenAI acaba de presentar los Dots en el DevDay y yo llevo usándolos desde el viernes: formé parte de las pruebas de la Dev Early Access Community. Te cuento cómo ha sido. Un Dot es un agente que está siempre encendido, con su propio ordenador en la nube. Lo conectas a tu correo, tu calendario y otras herramientas, y no espera a que le escribas: revisa por su cuenta qué puedes necesitar y te propone soluciones que muchas veces solo tienes que aceptar. La conversación se parece más a WhatsApp que a un chat con ChatGPT. Le pones nombre y avatar (el mío se llama Keet), y si le respondes con un 👍 entiende que aceptas y sigue. Lo que más me ha sorprendido estos días: 1️⃣ Este viernes tengo una formación y justo después un evento, con media hora entre medias. Lo vio por un email del evento, me avisó y me preguntó cómo pensaba ir. Le dije que en coche, me buscó el parking cercano más barato y me abrió la reserva con los datos rellenos. El pago lo hice yo. 2️⃣ Se puso a revisar la práctica que había entregado un alumno de AI Expert. Para ver el vídeo le pedí que instalara Whisper en su máquina, lo transcribió, revisó el repo con el conector de GitHub y me dejó una primera revisión. Ya no parto de cero. 3️⃣ Otro alumno había preguntado algo y Nino ya le había contestado. Lo vio y me propuso ajustar mi borrador para añadir solo lo que faltaba. Además se mete en Slack como un miembro más del equipo, y puedes llamarle por voz como si fuera una llamada de teléfono. Para esas tareas pequeñas que se acaban enquistando porque nunca encuentras el momento, me está resultando útil. ¿Lo vais a probar?

LikeRead full post ↗

Antonio Leiva

@antonioleivag

🚨🚨 OpenAI acaba de presentar los Dots en el DevDay y yo llevo usándolos desde el viernes: formé parte de las pruebas de la Dev Early Access Community. Te cuento cómo ha sido. Un Dot es un agente que está siempre encendido, con su propio ordenador en la nube. Lo conectas a tu correo, tu calendario y otras herramientas, y no espera a que le escribas: revisa por su cuenta qué puedes necesitar y te propone soluciones que muchas veces solo tienes que aceptar. La conversación se parece más a WhatsApp que a un chat con ChatGPT. Le pones nombre y avatar (el mío se llama Keet), y si le respondes con un 👍 entiende que aceptas y sigue. Lo que más me ha sorprendido estos días: 1️⃣ Este viernes tengo una formación y justo después un evento, con media hora entre medias. Lo vio por un email del evento, me avisó y me preguntó cómo pensaba ir. Le dije que en coche, me buscó el parking cercano más barato y me abrió la reserva con los datos rellenos. El pago lo hice yo. 2️⃣ Se puso a revisar la práctica que había entregado un alumno de AI Expert. Para ver el vídeo le pedí que instalara Whisper en su máquina, lo transcribió, revisó el repo con el conector de GitHub y me dejó una primera revisión. Ya no parto de cero. 3️⃣ Otro alumno había preguntado algo y Nino ya le había contestado. Lo vio y me propuso ajustar mi borrador para añadir solo lo que faltaba. Además se mete en Slack como un miembro más del equipo, y puedes llamarle por voz como si fuera una llamada de teléfono. Para esas tareas pequeñas que se acaban enquistando porque nunca encuentras el momento, me está resultando útil. ¿Lo vais a probar?

Updated as reviewed X posts are added to this collection. An editorial selection, not a representative poll. Views do not affect the score.