Reading up on ai-integration

Introducing Dreaming: Across sessions, Devin builds a memory graph of how you like to work At night Devin self-improves its memory to remove stale records and discover latent information We are creating an OSS standard called Agent Memory Repo: https://cognition.com/agent-memory-repo

@cognition

My biggest takeaways from @thsottiaux: 1. Most actions on the internet will soon be taken by agents, and Tibo doesn’t think most people have priced this in yet. When Notion launched its MCP server, it saw a flood of traffic, which strained its systems and forced it to rethink its economics. Every product team will soon have to decide whether to build for agents. You can hold off for a while, Tibo says, “but it is inevitable.” 2. The model picker is likely going away. One of Tibo’s biggest frustrations with the current state of AI is that users have to think about which model to use and what reasoning effort to apply. “I myself even get fatigued with the model picker,” he said, and he wants to get rid of all of it as quickly as possible. Dots ships with no model picker at all. You just talk to it. 3. Build as if models will be 10 times better in a year. Tibo thinks models will get cheaper and faster “at rates that are quite incredible,” and that all modalities will finally work together seamlessly. When he looks at what people are building, his reaction is often “you’re not quite getting it.” If you imagined “all of this being roughly 10 times better than it is today,” what would you build differently? His own forecast was too slow: he expected today’s capabilities a year or two from now. 4. Loops, graphs, and fine-tuned prompts are not the long-term solution for getting the most out of AI. There was a period when people got very excited about configuring agent loops and building intricate graph architectures. Tibo thinks that era is ending. 5. While Dots got most of the attention at DevDay, Tibo thinks the plugin ecosystem will be the sleeper hit. OpenAI launched with 16 partners for “Sign in with ChatGPT,” and popular third-party plugins will share in revenue when subscribers spend tokens with them. ChatGPT recommends plugins inside conversations based on retention and quality, which can put a good one in front of “a significant slice” of its 1.2 billion users. Tibo’s advice to developers trying to get discovered: “Build a good plugin.” 6. Tibo’s Dot warned him that production was down five minutes before the DevDay live demo. The agent figured out that DevDay was happening that day, that the demo was minutes away, that the demo probably depended on that production system, and that Tibo would want to know. It pinged him just as the launch was about to begin, and it even offered to fix the outage. His reply: “I don’t think you’re there yet, little Dot.” 7. Tibo’s agent teams grow and shrink with every model release. When he’s pushing the frontier, he builds larger and larger teams of agents. Then the next model lands, “a bigger agent can just do all of it and keep everything in memory and learn,” and he shrinks the team again. Expansion, then shrinking, then expansion. Don’t get attached to your setup. 8. Skill trending down in value: typing fast. Skill trending up: taste. Tibo says the people thriving now deeply understand the user, learn quickly, and “know what good looks like.” That’s part of why OpenAI is full of former founders, more than 120 of them, which makes it feel like “a mega startup.” 9. Tibo changed his mind about new grads. He hadn’t anticipated how fast younger people would embrace all this change and figure out how to harness it, and that shifted OpenAI’s hiring strategy. His example is Ahmed Ibrahim, hired as a new grad, who built much of the Codex harness and is now responsible for OpenAI’s compute fleet. What set Ahmed apart: he’s “incredibly kind,” “incredibly collaborative,” works on what matters without putting himself first, and is “a sponge,” using the latest tools to learn at speeds Tibo hadn’t seen before. 10. We’ll likely address the burnout associated with AI. There’s pressure to run 30 agents at once and ship more because you can. Tibo wants AI to “reduce the noise” and let you put your attention where you choose. Every time he fully disconnects for a week of holiday, he starts thinking in more creative ways, and he wants to bring that into the workday. Maybe you need fewer meetings, and you’d be more productive if you were better rested. The industry still has to figure that out, he says, but that’s the promise of AI: “it’s not just one more prompt per second.”

@lennysan

Introducing Griffin, the first model to pass the video Turing test. 48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video. It’s the first Human Interaction Model (HIM).

@tavus

For two weeks, start a design, deck, or doc in the Claude app, and the work that follows in that conversation uses 50% less of your usage limits. Give it a try with Claude Sonnet 5.5. It has a strong eye for design and builds slides that need minimal editing.

@claudeai

We built the notes app we always wished Apple Notes was. Beautiful, connected by backlinks, instant to search, and every note is a plain Markdown file your AI agents can read. Reflect Open is out of beta today. Open source, free on Mac, and on iPhone and iPad.

@reflectnotes

introducing the tldraw plugin for ChatGPT, a realtime multiplayer canvas available now in the ChatGPT app

@tldraw

🚨 Elon Musk just MIC DROPPED this reporter who was dooming about Super Intelligence REPORTER: Not if they haven't got a job! ELON: Well, jobs have ALWAYS changed. A computer used to be a job: a building full of people doing calculations. I don't think anyone is pining to go BACK and do calculations all day to do bank interest rates! We'll see an EVOLUTION of roles. As the president mentioned, there is a tremendous demand for people [in SI]. The most likely outcome...is incredibly beneficial. It's a future you would want. 💯 Trump and @ElonMusk are on the SAME PAGE on this Areas like Europe, who lack the same SI infrastructure as the US, are going to fall behind and WISH they were up here with America And China CERTAINLY wants all of the mass data center and SI advancement we are having. America is winning the future at all costs, and the people will benefit!

@EricLDaugh

Claude Sonnet 5.5 is out! We wrote a guide for building with it: • choosing between Sonnet 5.5 and Opus 5.5 • migrating from Sonnet 5 and tuning effort • using it in Claude Code https://claude.dev/blog/building-with-claude-sonnet-5-5/

@ClaudeDevs

With Claude Code! I imported all my bank accounts, Revolut and Wise etc, and then scoured my backups for old bank statements to backfill the data as much as possible

@levelsio

mega upgrade for GPT Voice, which can now use tools and is available in Work:

@gdb

BTW we now support multiple accounts in the Claude mobile app

@RobertJBye

Voice! I've gotten so used to just call ChatGPT and talk about all the work, check on emails, do some coding, manage my calendar and it works across the full ecosystem of plugins, including 3P developed plugins.

@thsottiaux

It is time to spotlight even more indie apps for iOS 27. Here's our second roundup of some excellent app updates for iOS 27, and what you can do with them using Siri AI and widgets: https://www.macstories.net/reviews/our-favorite-indie-apps-for-ios-27-vol-2/

@viticci

Jev with Exa is INSANE. > Jev without websearch confidently gives wrong outputs > Jev with websearch is literally much more accurate Try Jev (with Exa websearch) for free 👇

@TheIshanGoswami

We are excited to announce we are partnering deeply with Muse to enable agentic checkout with Shop Pay on all Shopify stores, offering people an easy and delightful way to shop and check out with Muse.

@tobi

How important is AI to Meta? Here’s one easy tell: One of the launch features of the Muse app was auto-negotiating for stuff on Facebook Marketplace. The poor product manager who owns Marketplace knows that millions of bots lowballing sellers will eventually kill the product. But this was escalated to Zuck by the Muse team and he said: “OK, we’ll poison Marketplace…but just a little.”

@nikitabier

AI-native services: a $100B opportunity

@gregisenberg

Jev was adopted faster than any other model in AI Gateway history. In the first day, @typesafeai reached ~13% of teams, 2x the GPT-5.6 family and 6x Fable 5.1.

@vercel

Jev is going to change the prosumer/consumer AI landscape by unlocking a specific thing: Ad-supported + free AI native apps this is going to usher in a generation of new AI-native marketplaces, social networks, photo apps, messaging, calendars, email, collab tools, and much more. Why? Previously, if you wanted to have an AI-native app with multiple/fast LLM calls on every screen, the math just didn’t work - inference costs just couldn’t be paid back from throwing a few video ads or affiliate links. So there were really just two solutions: 1) be a massive company and subsidize AI costs 2) charge a subscription fee to cover inference (or both) So what happens when you take a different approach that’s looks to be, initially, >400x cheaper than a more general LLM? I think it means that app developers are going to make their apps smarter and different in interesting ways. It won’t be as generically powerful as LLMs, but instead folks will create highly differentiated point solutions. You may not have a generically powerful virtual admin to schedule all your meetings, but you may have a free/ad-powered assistant that can comb through your inbox, filter for only important emails, figure out important dates, prioritize contacts, and do other interesting 80/20 work. Same for generically powerful virtual companions, or app builders, etc - it may be that we can hybridize the LLM and future Jev-like models that adds “wow” features at 1/1000ths of the cost, to make the economics work. If folks hear of interesting new apps/interactions/etc built on Jev, I’d love to hear it!

@andrewchen

One of the most underrated features in the ChatGPT desktop app: Appshots. Appshots take the context on your screen and bring it into the desktop app, allowing you to share instead of describe. You’ll be surprised at how useful it is. To get started, press both Command keys on macOS, or both alt keys on Windows.

@ChatGPT

i'm sorry, Claude can WHAT? it can take your website link, find people who need your product, email them and book the calls? since when?? i've been doing this by hand for a YEAR. ok. testing it: $30 free 👇 https://explee.com/auto-gtm/x/tw-ag332-c754

@vovudebosh

Procrastination has met its match. ChatGPT is now in Word. You can add ChatGPT to Microsoft Word to turn rough notes into first drafts, untangle tricky paragraphs, proofread, and get suggested edits—all without leaving your document. It can even spot formatting issues. Which means a few less things to fix later 🔍

@ChatGPT

Claude Design, Claude Slides and Claude Docs also work inside Claude Code now. Ask for a design review deck or a UI mockup and point it at the actual files and RFCs in the repo. Edit it yourself or keep going in the conversation, and share the link when it's ready.

@ClaudeDevs

Wispr Flow was a game-changer when it first came out and I hope they will continue to be very successful, but I just don't see how they can stay competitive? There are so many alternatives now. Many are one-time payment or even free and open-source. Local models are superior for most users so a subscription doesn't really make sense Team seems super talented though, so I'm curious to see if they've got any surprises up their sleeve

@marckohlbrugge

Claude Mods are landing now. Someone already built a Tetris-in-Claude mod 🤯 See issue for the latest community update, technical details, and more cool demos https://github.com/anthropics/claude-code/issues/91870#issuecomment-5666255143

@bcherny

Interesting, I killed my OpenClaw VPS servers months ago But today I got a billing alert on its separate Claude account (claudeforopenclaw@), it didn't have auto reload on but I guess at some point it got hacked and the Claude key inside OpenClaw got exposed and then they waited for months before using it on Fable 5.1 I checked all my terminals and VPS sessions and none of them use API so it's interesting Anyway I nuked the Claude account, good I kept it on its own separate one

@levelsio

5M ChatGPT sites, and new feature drops:

@gdb

If you showed me Claude Code today in 2018, I would have thought it was AGI. We have already absorbed a dramatic amount of change in the profession of software engineering and society as a whole. But still, we’re starting to see cracks. Things are accelerating faster than I can honestly stay on top of. Most people I know in AI are tired but powering through. I fear we will need more than that. We need time to harden our systems, and for society to deliberate in how this technology is used and deployed. I have a fairly low p(doom), I am confident that we can get through this! Humanity is incredibly reslient and adaptable, but this comes from our ability to make hard decisions- like this one, together.

@trq212

Two fresh updates to Claude Managed Agents: First, we've added a session viewer to the ant CLI. `ant beta:sessions connect` attaches your terminal to a running session, and `--web` opens a web UI served from localhost.

@ClaudeDevs

I was wrong I still think it's just an API though and any API can be used as an MCP and in the end they'll just become the same

@levelsio

This is the AWS moment for agents. OpenAI just shipped the Agents API, and everything that made agents hard to build is now something you rent instead of build. Keeping one running for days, remembering what it's doing, using tools, recovering when a step fails. Now it's an API call. Before AWS, you had to buy and run your own servers, so only well funded teams could build real/scalable products. AWS made the hard part rentable, and all the value moved up to whoever had the best idea for what to build on top. Same thing is happening here. I'll be honest, my first reaction was that this is bad news for a lot of people I know. If your whole company is an agent platform, the thing you spent the last year building is now included for the price of tokens. But the more I sat with it, the more I think it's really good news if you're building for one specific industry. Basically, vertical software type stuff. If the hardest engineering just became a line item, then the only thing left that's actually hard is knowing the job. Like what counts as a done claim, what makes a filing get rejected, where the money leaks. So the wedge now is owning one painful workflow with your own tools, data, approvals, and a clear ROI. Freight exceptions, insurance reviews, security triage, revenue leakage, healthcare admin, compliance ops. I see a lot of doomers on X saying software is over (and sometimes I feel the same way), you'll just use Claude or ChatGPT for everything. BUT, if that were true, OpenAI wouldn't be shipping infrastructure for other people to build agents on. They're telling you exactly what they think: the general model is theirs, the 10,000+ specific jobs it needs to be pointed at are yours. I think software is just evolving. It's becoming an agent internet, and every layer of it, the tools, the workflows, the boring jobs, gets rebuilt for a user that doesn't have eyes or hands. That's a lot of companies waiting to be built.

@gregisenberg

This is essentially my belief too And I'm confused why so many people don't think this yet The AI chat apps will slowly eat up most services and provide them to users directly, many times without even an app or interface, just do whatever the user wants Dario Anthropic said it himself "in the end there will be just Anthropic and world governments" or similar, as they (and the other AI labs) will replace all work and all services The question is the timeline

@levelsio

I am so confused why people don't understand this, I keep getting these replies Don't you get it? Normies don't vibe code, they just ask something like "do my bookkeeping" or "file my tax" or "organize a movie night and send invites" or "generate a flyer for movie night" or "edit my video" They don't ever see code, vibe code, or do anything with code, their AI chat app just does it for them Most of the software layer has already disappeared or will completely disappear for normies Just like building personal homepages permanently disappeared for normies when Facebook launched ~2005 A lot like this picture where functions of individual devices all got replaced with a single device Same happening with apps now

@levelsio

This was one of the best features of Instinct. Now in Grok Bot!

@mvanhorn

Who's doing the first agentic bank? I want to give my machine an agent account, an allowance, and permission to just take care of stuff.

@dhh

we're now moving into the AGI era (whether you view it as this model, the last one, or the next one), and could not do it without close partners

@gdb

This is incredible. Marvin is the goat. He distilled years of expert design principles into an explicit constraint system, then worked back and forth with the model component by component. To get clean UI out of models, you have to feed them some guardrails: 8px base grid Strict 24 px padding Consistent 24px corner radius 2 font families max (Inter + Serif) 2-3 weights max because models naturally overindex on too many weights Start with great references Fine-tune from there Hand-select imagery and art direction

@theShaneLevine

Super happy to share our intention to join forces with NVIDIA in a $12,930,300,000 acquisition 💛💚 10 years after starting Hugging Face, open-source AI is at an inflection point. Thanks to the community, we’ve shown that it can be a complement, and even an alternative, to closed-source APIs. But for it to happen at larger scale, it needs more compute, more support, more collaboration and more visibility. That’s why we went to talk to Jensen, who offered to do exactly that with us. In addition to doubling down on NVIDIA’s massive contributions to open-source AI (I called them the “King of American open-source AI” earlier this year), they’ve committed to strongly supporting Hugging Face and our mission while keeping the platform open, independent and compute agnostic. The founders and the team are all staying to keep pushing this mission forward. Together, we think we can make open source the default way to build AI, with the goal of empowering 100 million AI builders to own their intelligence rather than rent it. Excited about the next 10 years! 🤗🤗🤗

@ClementDelangue

Introducing Tesla Bot for your @Grok @Bot. (SOUND ON!) Your Tesla is just a sentence in the chat: "max defrost Model X every school day at 7:45" "what did Supercharging cost this month?" "unlock both cars and honk Stella for fun" Under the hood it's the @ppressdev Printing Press Tesla CLI. Your sentence becomes a signed Fleet API command. Pair the car once, then it works forever.

@mvanhorn

The ChatGPT desktop app is now my main browser and my productivity has never been higher

@thsottiaux

Introducing WebMCP + agent-browser The web is becoming agent-native 𝚊𝚐𝚎𝚗𝚝-𝚋𝚛𝚘𝚠𝚜𝚎𝚛 𝚠𝚎𝚋𝚖𝚌𝚙 <𝚕𝚒𝚜𝚝|𝚒𝚗𝚟𝚘𝚔𝚎> → Discover & call tools → For missing tools, falls back to browser automation

@ctatedev

53.5 million tokens per second are moving through OpenRouter’s top 20 apps right now. I scraped their public usage pages to show which models are being used https://bentossell.com/realtime-tokens

@bentossell

still kicking the tires on my workflow but i'm narrowing in hard on what feels like the perfect AI design stack. @paper + @mobbin + @tastebuild layered with a custom /design skill that basically orchestrates all of that.

@Shpigford

How is everyone pricing in AI model usage in their app? Seems there’s a few ways: - pass through the cost transparently to the end user (they use $30 of inference they get $30 added to their bill) - abstract the cost away into some flat monthly price and risk going bankrupt - have some sensible defaults and bill extra for more usage All approaches have pros and cons

@yongfook

Todoist's Ramble feature is phenomenal. Just tap the button to trigger a recording and then unload into your phone and it figures everything out. Great way to brain dump anxiety and have AI organize it into something legible.

@awilkinson

This week’s ChatGPT feature drop - Aug 28: The team won't let me take a week off with these posts. Here's what we shipped 🚀 this week: 1/ Scheduled tasks for free users: Now anyone can create recurring tasks for ChatGPT. "Every Thursday, tell me about cool events happening this weekend nearby". 2/ Stickers: Use Imagegen to turn any photo into a sticker pack to share on iMessage or WhatsApp. If you like stickers in iMessage, this one's for you. 3/ Save temp chats: By popular request, you can now save a temporary chat to your sidebar after you've started it. You can also choose to use memory for temp chat. It's a nice quality of life improvement! 4/ Multiple accounts for Google plugins: Lots of people ask ChatGPT questions about their email and calendar (only available for paid users for now). You can now add more Google accounts so you can ask about all your accounts! 5/ Voice widgets in lock screen: Voice conversations now show things like weather and sports in the iOS Live Activity, even when your screen is locked. See you next week!

@adamhfry

ChatGPT Voice on watchOS 27 beta:

@keleftheriou

One person with AI outperformed an entire team

@fortelabs