
Founder @MoveAgent_UK AI Software • @GetcraftedNow @Craftwrks
Beverley
Joined September 2009
- Tweets8.1K
- Following626
- Followers2.3K
- Likes13.7K
Pinned Tweet
Fourth Plinth School Award 2017 #Haringey borough winner is #CrouchEnd Rokesly Junior School year 6 student 'Otto Iborra' 👏🏻👏🏻👏🏻
Rosana ☀️ retweeted
this might be my last normal tweet before biotech goes vertical
i'm not a whistleblower. I don't work at Lilly, Novo or any of the big labs
but there is a massive shift happening in human biology right now.
it's sitting in press releases and almost nobody reads them
the last 6 months alone:
- a once-daily pill roughly doubled median survival in metastatic pancreatic cancer (13.2 vs 6.6 months)
- a one-time gene editing infusion cut hereditary angioedema attacks 87%, and 62% of patients stayed attack-free and off all other prevention for 6 months
- a one-time gene edit for cholesterol dropped LDL up to 62%, and it held for over a year
- a personalized mrna vaccine beat keytruda alone in a 1,137 patient melanoma phase 3
- retatrutide hit ~28% weight loss in a phase 3
- an ai-designed drug entered phase 3
- a pill that regrows hair passed its second phase 3
- an immunotherapy that could let some rectal cancer patients skip surgery, chemo and radiation just got fda approved
- a man lived 271 days off dialysis on a pig kidney
- human cells were caught passing chromosome-sized chunks of DNA to their neighbors, and it changes how the neighbors behave
we are on the verge of an era where the human body is a software problem and the update cycle gets shorter everyday
stick around, it's going to get weird
bio/acc
Rosana ☀️ retweeted
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.
Rosana ☀️ retweeted
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
Rosana ☀️ retweeted
We believe that the future is code + AI, so made workflow evals to reflect that
Jev costs: $42 / BILLION input tokens ($0.042 / MTok) and output tokens are free (forever - they’re too cheap to meter with our new architecture)
Jev is named after Jevons paradox and off the intelligence per $ charts
Rosana ☀️ retweeted
Get more out of GPT-6 Astra by revisiting your skills, AGENTS.md, and task prompts.
Make skill triggers specific, load guidance when it's relevant, and define what done looks like.
developers.openai.com/blog/r…
Rosana ☀️ retweeted
5. Change what you pay attention to.
Your brain strengthens what you repeatedly notice.
Look deliberately for:
Safety.
Possibility.
Beauty.
Progress.
🤖 𝐀𝐈 𝐬𝐡𝐨𝐮𝐥𝐝 𝐡𝐞𝐥𝐩 𝐲𝐨𝐮 𝐟𝐢𝐧𝐢𝐬𝐡 𝐰𝐨𝐫𝐤 𝐨𝐧 𝐭𝐢𝐦𝐞.
One figure in the Self-Storage Association UK’s 2026 Annual Industry Report caught my attention: just 2.6 staff per store.
A small team juggling enquiries, bookings, payments and customers who may be moving home, downsizing or dealing with something difficult.
For me, this is where AI should make a difference.
Less copying information between systems. Less chasing routine updates. Fewer unfinished tasks hanging over your evening.
More time to help customers, improve the business and enjoy life outside work.
That belief shapes what we’re building at @MoveAgent_UK, and it’s why I wrote this article.
We keep talking about how much more AI can do.
𝐇𝐨𝐰 𝐦𝐮𝐜𝐡 𝐭𝐢𝐦𝐞 𝐢𝐬 𝐢𝐭 𝐚𝐜𝐭𝐮𝐚𝐥𝐥𝐲 𝐠𝐢𝐯𝐢𝐧𝐠 𝐮𝐬 𝐛𝐚𝐜𝐤?
👉 Read my take on the 2026 UK Self-Storage Report: moveagent.co.uk/news/what-20…
#SelfStorage #AI #MoveAgent – at Beverley, England
Rosana ☀️ retweeted
We are progressing through the rollout of Astra. Pro and Business subscriptions get it first, some of you should start seeing it across ChatGPT Work and Codex.
And then we will proceed with rollout to all of Plus as fast as we can.
Rosana ☀️ retweeted
We will give one banked reset for every day you don't have access to Astra on your paid ChatGPT plan, starting today. Team is moving mountains to give access as fast as we can.
First one will land in ~ 3 hours. There is still time to create your account if you don't have one.
🤖 𝐀𝐈 𝐬𝐡𝐨𝐮𝐥𝐝 𝐫𝐞𝐦𝐨𝐯𝐞 𝐭𝐡𝐞 𝐚𝐝𝐦𝐢𝐧, 𝐧𝐨𝐭 𝐭𝐡𝐞 𝐡𝐮𝐦𝐚𝐧.
I’ve spent a lot of time thinking about what “modernising” should actually mean for #removals companies.
⚡ Faster responses
📋 Less repetitive admin
🤖 Smarter use of AI
💬 Better communication
👤 A real person when it matters
Moving home is personal. Customers want speed and convenience, but they also want reassurance that someone is actually there when they need them.
The opportunity for technology isn’t to remove that relationship. It’s to give teams more time for it.
I wrote about where I think that balance sits, and how removals companies can modernise without losing the trust they’ve spent years building.
👉 Read the full guide: moveagent.co.uk/guides/moder…
Rosana ☀️ retweeted
this is a critically important moment for cyber defense with AI; there is not much time to act.
we are happy if you want to work with us or any of our competitors or partners, but please take this moment seriously.
only an urgent and intense collective response will work.
Rosana ☀️ retweeted
GPT-5.6 Sol 1M in Codex. This used to only work for API keys, but we just flipped the switch and works for usage through ChatGPT accounts now too.
The same warning applies, there is a reason the current context length is the default, we have tuned it to ~perfection. But you do you!
Here is how to enable a 1M-token context window in Codex for GPT-5.6 Sol.
Even though we have tuned the context limit in Codex to be set optimally when it comes to performance and cost, this is a common ask, so here it is documented.
A larger context window lets Codex retain more code, tool output, and conversation history before summarizing older material. You need a model that supports it. And GPT-5.6 Sol, for example, has a documented 1,050,000-token window.
Open ~/.codex/config.toml and add or update these settings at the top level, before any [section] headers:
```
model = "gpt-5.6-sol"
model_context_window = 1000000
model_auto_compact_token_limit = 900000
```
The first setting selects the model. The second tells Codex to use a one-million-token context budget. The third starts automatic history compaction around 900,000 tokens, leaving some headroom. Restart Codex client and start a new session after saving.
To try the configuration for a single CLI session without changing your defaults:
```
codex -m gpt-5.6-sol \
-c model_context_window=1000000 \
-c model_auto_compact_token_limit=900000
```
Have fun, but also know that we tuned the default carefully!
Rosana ☀️ retweeted
Pro tip:
Use chatGPT Work or Codex to fix your home network coverage
/goal make my WiFi coverage the best it can possibly be. Evaluate all APs, and their settings, use my laptop as necessary to check signal levels and build up your own internal map of
My house/office/apartment. Fix anything you find. Dont stop until coverage is ideal with the best performance.
Rosana ☀️ retweeted
More opensource goodness. We have just released a CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities in your code. Scan repositories, review changes, track findings over time, and run security checks in CI.
github.com/openai/codex-secu…
Rosana ☀️ retweeted
Replying to @nelthbase @Soycinac
Si saben de alguien que necesite ayuda en teleapoyovenezuela.org estamos para ustedes! Es gratis, creo que mucha gente tiene miedo de buscar apoyo pensando que tiene que pagar 🫂❤️🩹
Rosana ☀️ retweeted
Normalize outgrowing people, places, and patterns without feeling guilty for choosing yourself 💯
Rosana ☀️ retweeted
Replying to @elder_plinius
You can also read various prompts we use on the open source repo
github.com/openai/codex
Rosana ☀️ retweeted
Everything we call real is made of things that cannot be regarded as real.
If quantum mechanics hasn't profoundly shocked you, you haven't understood it yet.
— Niels Bohr





















