I asked Opus to go on a bug hunt. It found 156 bugs to handle. Then I asked it to get the root cause of all of the bugs and they all traced back to just 17 root causes.
Run this prompt:
“Audit any patched and remaining open bugs in this codebase. Look for the root cause, not the smallest patch. Use the bugs as symptoms, some of them are likely related.”
ALT Identified bugs, grouped by root cause.
// Lofty retweeted
Here's ours, built on Cloudflare.
Two coding agents rewrote the same function at once. Both versions were kept. I picked one and wrote down why, and the reason landed in Git with the code.Then a new agent took the next task. Heddle gave it my reason before it started.
ALT Heddle feature overview. A Git decision record: bob chosen over alice, both passing tests in isolated sandboxes, with Luke's reason. A panel showing the next agent was briefed with that reason. Two agents' versions of parseRow kept side by side. git log trailers Heddle-Chosen and Heddle-Alternative. heddle undo --hard and --redo output.
// Lofty retweeted
If you haven't been using Wayfinder (IYKYK you should be..). Safety Check (Rug Police), Agentic research to help you setup charts and perp trades, automated trading, iMessage/SMS integration, your own openclaw instance, etc. Why not?
For anyone who signs up using my code I will give you 100% of your referral fees back for the first month. You'll also get FREE guidance and help from me on building Wayfinding Paths which pay you $PROMPT when you bond and publish them for use by other users.
You'll also earn your own leaderboard rewards by trading on the platform, so you're basically double dipping bro.
Hit my link below 👇👇👇👇👇
BREAKING 🚨🚨
Anthropic generously offers 12.5 minutes of Fable usage for research!
We're offering grants of up to $50,000 in Claude usage credits to researchers accelerating cures for rare diseases.
This is our first focused call within AI for Science, our program supporting scientists using Claude to speed up discovery. anthropic.com/news/rare-dise…
PSA: Use the phrase “clean cutover” with 5.6 Sol.
It magically no longer makes shims and actually deletes legacy code.
Sol just voluntarily deleted a legacy shim at the end of a long run. I'm going to ride this high all week
// Lofty retweeted
Introducing Aval - a new open source format for interactive video on the web. It has a built-in state machine, frame accurate transitions, and packed alpha transparency.
This is probably the craziest thing I’ve ever built with Codex.
I’d been dreaming about this technology for years. Before AI, building it would have taken months of work. I could never justify that investment for a noncommercial open source project. Then, a little over a year ago, Airbnb created Lava for almost exactly the same purpose. That gave me hope. But Lava was never released as open source.
So I decided to build my own, with AI.
Aval comes with a compiler and a web renderer. Together, they give you:
• a deterministic state graph - named states, authored triggers, and routing where the latest trigger wins.
• frame accurate routes with transitions that begin on authored content frames using portals, finishes, cuts, and reversals.
• small file size and low CPU overhead, perfect for small icons designed and animated in Blender.
• seekless loops so the decoder timeline keeps moving forward across loop seams instead of seeking.
• packed alpha transparency. transparent prerendered motion composited with WebGL2.
• a web native runtime: decoding with WebCodecs and rendering with WebGL2.
• progressive fallback: Host-owned fallback markup remains available for unsupported and reduced motion contexts.
Now it exists, it’s open source, and it’s available today as a technical preview.
I’ll be polishing it further over the next few days.
Let’s try removing the weekly limit too for a while. For science
I’m working on a brand new approach to agentic coding.
You have repos and worktrees and sandboxes and rules to try to keep agents separate and working on their own thing. It works but there’s an underlying cost.
I’m making a system that’s built around tasks. As you give your agents a task, they get a thread. A thread lets your agent work on an isolated copy-on-write worktree and gives your agents access to scoped discussions. If agents need to collaborate they can simply messages the relevant task-based discussion and that message will get routed to whatever agent(s) are also working on that task.
Say you have a new feature in progress. You have an agent build it out and leave notes on where it got stuck via the discussion (which can be connected to a specific file or line) and then when you review agents come in they immediately benefit from the complex context the builder already assembled.
You save tokens, time, and effort as agents can leave hints throughout your code without using markdown files that go stale or comments that agents skip when grepping.
This works across harnesses, and across agents. It can even let agents communicate in real time by letting agents poll for messages or directly steering the target agent harness.
5.6 Sol is strikingly good at bounded tasks. Long-horizon work can still wind up in the weeds but with a longer context orchestrator managing 5.6 implementers, the sky is the limit!
How can they keep getting away with this???
Hello. We have reached 8M active users across Codex and ChatGPT Work.
We are once again resetting the usage limits for all. And we continue to not have the 5h rate limit as well, allowing everyone to explore the boundaries of GPT-5.6 Sol and discover how ambitious you can be.
See you tomorrow for more updates on our growth!
// Lofty retweeted
Hello. We have reached 8M active users across Codex and ChatGPT Work.
We are once again resetting the usage limits for all. And we continue to not have the 5h rate limit as well, allowing everyone to explore the boundaries of GPT-5.6 Sol and discover how ambitious you can be.
See you tomorrow for more updates on our growth!
// Lofty retweeted
Heddle changes the way you think about your code history. Today it isn't good enough to only store what worked well, agents need to be able to look back and remember what might not have worked before.
Heddle lets your keep a record of where things went wrong and create annotations to explain why. Stop guessing, start building 🦾
// Lofty retweeted
‼️ BREAKING: New research shows you can copy any signed GitHub commit into a second one that looks identical, without the author's secret key, creating a distinct commit with an identical tree, identical metadata, a valid signature, and a "Verified" badge from GitHub.
On GitHub, a green "Verified" badge is supposed to mean two things: a trusted author signed it, and its ID is a one-of-a-kind fingerprint for that exact code. A new Carnegie Mellon preprint from Jacob Ginesin says the second promise, the unique fingerprint, does not hold.
Why it matters: security teams and package systems (behind tools like Go, Nix, and GitHub Actions) trust that ID as a unique handle for code. Block or pin the "bad" version, and an attacker can re-issue the same signed code under a fresh, still-verified ID that slips past. The author says Git and GitHub have not fixed it.
PoC: github.com/JakeGinesin/git-c…
// Lofty retweeted
Working on a concept…
Do you have multiple repos that relate/depend on each other?
What if you have a messaging system built in to your version control that could talk to other entities (users, agents, bots, etc) across repos?
Your frontend repo could message your backend repo to align on some new feature set or convention and lock the results into your codebase directly as queryable and automatically injected context.
Your agents could ping you or an orchestrator directly for “taste”.
You can see your agents collaborating to work through things and steer their ideas in real time.