Reading up on developer-tools

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

Announcing d1 with vision. 👁️👁️ Our first decision model now supports images, text or both as inputs. We tested d1 against GPT-6.1 Sol and Claude Opus 5.5 on six real applications, from filtering support tickets to inspecting circuit boards. d1 matches or beats GPT-6.1 Sol on four of them. It costs 19x to 200x less than both models and answers significantly faster on every task. > probabilities for yes/no, choice, or score questions > one forward pass, without generating tokens > text decisions in 200 to 300 ms > Liquid API:

@liquidai

Wow, @steipete delivers a new-to-me YOLO/skip permissions gem for computer use: What it unlocks: "per-app limits get lifted. Today those stop me from clicking or typing in browsers and from typing in terminals and IDEs. That would let me type into Chrome or cmux directly"

@mvanhorn

Introducing gdp-ts: Ghosts of Departed Proofs for TypeScript. gdp-ts is a library, linter and AI skill for safer API design. Under this contract, sensitive functions require 'proofs' that the caller performed an authorization check. The typechecker verifies these proofs at compile time, preventing your team and agents from shipping catastrophic security (and other kinds of) bugs. While these patterns have existed for quite some time, especially in ecosystems like Haskell, ① human code review and ② cognitive and syntactic overhead made these solutions niche. The situation is now inverted. Agents are writing more code than we can review, and they *thrive* in tight loops with hard constraints that would frustrate us. We see this with the rise of Rust, borrow checker, code aesthetics debate and all. The README and examples model a real-world Vercel API product constraint: changing the password on a Project requires a proof of a certain role + a certain entitlement. Thanks to Matt Noonan and Ollie Charles for their research in this space.

@rauchg

Just launched the highest ROI tools for SEO ever made. https://ian.is/tools try not to bankrupt me....

@iannuttall

Muse, dots, Instinct, and the question every agent will be asked

@worldnetwork

BREAKING NEWS: @rauchg , CEO of Vercel, has just published his first public skill Which tech CEO will be next to skill-ify themselves? https://www.skills.sh/rauchg/skills/ui-recording-timeline

@andrewqu

Excited to open source the Muse Gadgets SDK today! You can connect your DIY electronics like ESP32 boards and Raspberry Pi to Muse. Build an e-ink morning briefing, a push-to-talk pocket device, a sysadmin for your homelab, and much more. Details at https://gadgets.muse.ai

@dps

This is cool as hell

@theo

なんと、Cloudflareがすでに作っている https://github.com/cloudflare/ci

@R0u9h

Cloudflare have integrated Pi Durable in the agents SDK. Really happy how it turned out. Props to @mattzcarey et al. for getting this done on such short notice. It "just works" :) https://github.com/cloudflare/agents/blob/df9c0ef6c4541c5552b5ce4d6ba292162dbd0908/packages/agents/src/harness/pi/harness.ts

@badlogicgames

You told us Cloudflare can feel like a black box. Today, we’re taking eight major steps to change that. Just ask your agent to query your observability data with cf, our agent-first CLI for the Cloudflare API. https://cfl.re/3VECjml https://x.com/Cloudflare/status/2106007550248325543

@CloudflareDev

We're adding a new plugin to Claude Code: You should Know. It scans Claude's output for important information you might miss to help keep you in the loop. Enable it with: /plugin enable cc-plugin-you-should-know@builtin

@ClaudeDevs

We’ve been improving Loops a lot to automate work that should be automated In @slack or @linear just tell the agent you want to make a loop for something. The loop can auto pick models, connect to external services through MCP, can be triggered or scheduled. Some example loops from our team: * Investigate incoming bugs and propose fixes with browser tests * Find new Sentry errors and open fix PRs * Turn meeting action items into issues * Monitor engineering alerts and unusual cost spikes * Surface untracked container vulnerabilities * Scan and remove old feature flags * Watch feedback on workflows or product areas and keep an running document, slack or other sources

@karrisaarinen

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

Excited to release the @github async merge API today! If you (or your agents) are merging PRs programmatically, this is for you 🧵 https://github.blog/changelog/2026-10-01-github-async-merge-api-generally-available/

@sameenkarim

This goes for makers of all shapes.

@dhh

Veeeery excited about mods, it’s basically middleware for Claude Code! You can create a TypeScript function that intercepts CC's internal events (tool calls, prompts, model requests and renders) and change what actually happens. You can also add your own UI and commands!

@lydiahallie

Get your Apple Reminders in Claude Code. RemCTL 2.1.0 now ships with a Claude Code plugin and mod, so you can always see what's left to do today, or in a specific list. There's even a sidebar! Get the update here: https://github.com/viticci/remctl @amorriscode

@viticci

Who knew that 22 years ago when we launched Basecamp we'd have built the absolute best framework to work with humans and agents in the same place. Here's @bitsweat talking to Clawdito (an agent) in Basecamp, assigning it work, getting responses, asking it to follow up, creating PRs, the whole thing. And here's @jasonzimdars working with Marie (an agent) and JZ bot (another agent, his agent) in a comment thread on a message board. Can do this anywhere in Basecamp... on a to-do, card, file, document, photo, anywhere you can talk to humans async or real time, you can talk with your agents the same way. And they can respond the same way humans do, right in line, right where you'd expect, with all the context in the thread. We've been running and refining this in our account for a while now. Anyone can do this today using the CLI. But we're also making it easier for people to create agent-users within Basecamp. Stay tuned for a lot more on this front.

@jasonfried

One tool you'd happily pay double for. Go 👇

@ProductHunt

Like Jev? You'll love Clef and Clef-flash, which are smarter, faster, and fully Jev-API compatible. https://x.com/Cloudflare/status/2105747536510099540

@CloudflareDev

The agents that run my LinkedIn outreach are currently getting a 55% reply rate on cold outreach and are generating hundreds of signups for me completely on autopilot. I packaged the exact system into a skill that works for any harness so you can copy it for yourself.

@speedrunjaen

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

@karpathy

We just launched a feature we began exploring a decade+ ago, but never released it. It was originally destined for Campfire, our chat tool. The feature is called Bonfire. Now that Campfire is built into Basecamp, Bonfire belongs there. And today it's live for all Basecamp 5 customers. What's Bonfire? I put together a short video to show you what it is and how it works:

@jasonfried