We’ve been researching new ways for ChatGPT memory to carry context across conversations and keep it useful over time.
Today, that work is rolling out as a more capable memory system in ChatGPT. https://t.co/0MyFKCe2Mu
Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors.
Available today at the same price.
🚀 Introducing SkillOpt — an optimizer for agent skills.
Instead of finetuning model weights, we treat a natural-language skill as a trainable external parameter.
Think of it as deep learning for the frontier-model + agent era: learning rate, LR schedule, mini-batch, batch size, epoch, momentum — all in text-space optimization.
SkillOpt enables stable, controllable skill updates through bounded edits, allowing the optimizer to summarize “gradient directions” from agent experience and continuously improve procedural capability.
We evaluate SkillOpt across 6 benchmarks and 7 models, under both direct model calls and real agent execution loops with Codex + Claude Code. SkillOpt achieves best or tied-best results in 52/52 settings.
Train the skill, not the model. 🛠️🤖
🌐 https://t.co/zinqcX2wfQ
📄 https://t.co/pCI4VWdpih
Today, we’re open-sourcing the draft specification for DESIGN.md, so it can be used across any tool or platform. We’re also adding new capabilities.
DESIGN.md lets you easily export and import your design rules from project to project. Instead of guessing intent, agents know exactly what a color is for and can even validate their choices against WCAG accessibility rules.
Watch David East break down this shared visual language in action👇. New capabilities and links in 🧵
We built Upright to replace Pingdom at 37signals for monitoring all our services, and now we've open-sourced it too. Global checks, playwright smoke tests (with video recording!), detailed uptime tracking, and feeding into Prometheus + Grafana. Enjoy! https://t.co/QUVv0SyBuI
I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit.
My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently.
So, here goes.
🚨 Presisential level news.
I have four Sora 2 invite codes. I will be giving them away at the end of today to four followers selected at random.
To be eligible:
> Comment
> Like
> Repost
> Bookmark
This tweet. And you must be following me. Selection at 8pm ET.
To move out of S3 and onto our own Pure Storage, @bitsweat built a little app called Nostos to manage the transition. We've been using S3 in some form for over 15 years, so there were a lot of old buckets in the attic to inspect! But well worth the effort to save nearly $1m/year.
The time has come for enterprises to trade the compromises and risks of legacy silos for the clarity and control of the cloud. Meet the #EnterpriseDataCloud, a new storage and data management #cloud architecture. Learn more: https://t.co/lVBYhgd04g
#StoragePlatform#DataStorage
Just used @OpenAI’s 🎙️ 𝗥𝗘𝗖𝗢𝗥𝗗 𝗠𝗢𝗗𝗘 in ChatGPT for a meeting. Wow, total game changer; it transcribed everything, provided a summary, pulled action items, and I didn’t take a single note. 🤯 now using it for dumping random thoughts when out walking. 🚀👇
@AllynPaul@Jables77@Delta That sucks Allyn, good luck with everything. Ps - haven’t seen your recent stuff just cuz other life things but thanks for all your content in the past, hope you’ve been well. Safe travels