https://nitter.cf/t.co/dGaMsQiwEc Task Management for Agents
Canada
Joined October 2009
- Tweets2.1K
- Following298
- Followers353
- Likes17.1K
Pinned Tweet
Once a programmer becomes used to a complex solution to a problem, simple solutions to the same problem feel incomplete and uncomfortable
— Doug Hoyte
Greg Wedow retweeted
I've been testing a custom implementation of @VictorTaelin's OptMem with GPT 6.1 Terra across multiple agents sessions, each working on a number of features. so far they all remain usable, run continuously without pausing to compact and don't seem to experience context rot. I used 50M tokens and have ~80% token cache hit rate.
Greg Wedow retweeted
I've been properly nerd sniped by this one so I'm just going to do it. I imagine proper concurrency semantics are going to be a PITA though since the python ecosystem has generally shit support for free-threading.
So many people don't realize where the models are at now. I've just spent October watching Opus 5.5 do exactly this project but for Smalltalk.
After my next reset I'm going to point Opus at it again and say "do this but for Python". I think it'd be done in 3-4 days if I had the token budget, but it may be broken up waiting for a few weekly resets.
Greg Wedow retweeted
Usually helps to normalize the hell out of tables like this since most users tend not to actually have preferences and just roll with the defaults. It's a lot more time and space efficient to only store the overrides inside of these really wide rows.
So many people don't realize where the models are at now. I've just spent October watching Opus 5.5 do exactly this project but for Smalltalk.
After my next reset I'm going to point Opus at it again and say "do this but for Python". I think it'd be done in 3-4 days if I had the token budget, but it may be broken up waiting for a few weekly resets.
Greg Wedow retweeted
Another reason why you wanna use your own harness and not one where companies change what you can or can’t do at will.
ANTHROPIC IS CRACKING DOWN ON VIDEO GAME REWRITES 🚨
Claude Code picked up a new rule around Oct 27, sent from Anthropic’s servers under a flag called "tengu_heron_brook". There’s no setting to turn it off.
The full rule: “Do build original games, games in a genre, and games from the user’s own designs and assets. Don’t build a recreation of a specific existing game, even if it is renamed or called original.”
Is this the end of game rewrites, modding and everything in between?
bash is a perfectly good programming language when you aren't writing it by hand. most of my best work is in bash these days.
Greg Wedow retweeted
SIR PATRICK STEWART (1940-2026)
Before everything else, Patrick was defined by being born and bred in Yorkshire, the proud county in the north of England which he loved to the end. You could hear it in his accented voice and in the stern honesty with which he told you what he thought and felt. Yorkshiremen have no truck with half-truths or avoidance of big issues. He wore his heart on his sleeve, which made him a man to rely on, to admire and in my case, love.
We first met as ambitious young actors with the Royal Shakespeare Company half a century ago but we weren’t in the same productions. My first strong memory was a few years later, meeting him in the street in central London when he told me about an offer to take over a leading part in 'Star Trek'. “But Patrick think of your stage career in the UK. Do you really want to risk—getting lost in Hollywood for years and years?”. Well, he took the risk and thank goodness for us all that he did for not just his devoted Trekkies but film and theatre audiences, who marvelled at his using international celebrity to star in a string of cinema successes ('X-Men' of course) and in great classical plays by Shakespeare, Ibsen, Arthur Miller, Peter Shaffer, Pinter and Beckett at Stratford-upon-Avon, in London’s West End and on Broadway.
America was his adopted home, where he met his adored Sunny who has cared for him through sickness and health, through thick and thin. But he never forsook his origins: and the proudest achievement of the most respected and beloved actor of his generation on either side of the Atlantic, was his appointment as Chancellor of Huddersfield University in Yorkshire.
His farewell performance in 'Avengers: Doomsday' is yet to be seen.
Ian McKellen 29 October 2026
Photo: University of Huddersfield
Greg Wedow retweeted
Next question: why are you still using branches?
We talked about PRs. I don't think they make sense anymore, if you rethink them from first principles.
Yes, if you only use them to trigger CI, then sure, go ahead. That's a fat commit, not a PR. But for mandatory code review? Knowledge sharing? C'mon.
But some of you said: "we use PRs because we use branches! I love to keep my stuff on branches."
And I'm here to tell you: you don't need branches! You can just push to main.
It's called trunk-based development and the idea behind it is true continuous integration: you continuously integrate your changes with the trunk, the main branch.
It's been around for a while, it works. Just yesterday I talked with someone who said they've used it in an org with 400 engineers, without any issues. Ruby, the project, uses trunk-based development.
The main idea is that you want to avoid long-lived branches. They're bad, because branches can diverge and merging can turn into a thing. And you don't want routine operations to become a thing.
Even when I worked in teams that used PRs and branches, I considered it a smell when a branch lived for longer than a day or two.
But when I shared this with others, I'd often get something back like this:
"Well, good for you, but no. MY thing, what I'm working on, that can't be done on main. It needs to be on a branch! It has a database migration, it changes the underlying shape, the architecture, it refactors this and changes that. It can't go on main yet! I need to merge it all at the end."
And then I'd say:
"Nah, I can merge nearly anything continuously in small commits to main. You split things up. Add the column first, merge that, deploy it, now it's out, works, safe.
Add the helpers first, merge them, get them out.
Want to migrate from legacy pattern A to new pattern B? Don't do it all at once. Add the dependency, then migrate A to B, one by one, safe."
If it can be merged in a large change, I bet it can be done in small increments that you merge to main.
Yes, there are exceptions, but it's 0.5% of cases, not 50%.
But there was a real problem with this approach: it was hard!
There's a lot of "meta programming" you have to do: make sure this small first change compiles and runs and the tests work, merge it, get it out, monitor it; then do the next small piece, make sure that works and get it out; then maybe push some still-unused dead code, add a feature flag, add a config variable; or keep both configurations working at the same time, etc.
That meant sometimes it was just easier to do it in a big fat branch. But big fat branches are risky!
A system that continuously flows is safer than a system that starts and stops in spurts.
But -- you guessed it -- here's the good news:
Now, with agents, all of these chores are no chores at all!
Agents are great at adding feature flags, they're great at splitting up code, they're great at keeping track of three changes and merging them one by one and watching them roll out. They're great at keeping two configurations working for a day. They're great at migrating one by one.
In other words: it's now 10x easier to just work on main and make sure everything is continuously integrated and working.
It's now easy to make sure the system constantly flows.
And look, ...
I'm not here to convince you to switch to trunk-based development. Just a ruse to get you to read this. (But also, hey: try it! Pushing to main is amazing.)
I'm here to make you RETHINK how you develop software.
Don't just use agents to replace your typing.
Use agents as the magic code-writing machines they are. Everything that was hard about software development because it involved writing code -- even the meta programming -- has become easier.
You can now reach for the stars! But you need to look up.
Greg Wedow retweeted
Software around me is not improving nor is it expanding.
If AI drastically lower the cost of software… then we have a mystery, don’t we?
The answer is that building the software was never the difficult part in these cases. Our organizations have been optimized for process, meetings, and risk avoidance instead of shipping working systems. It is institutional decay: layers of people whose main job is to prevent other people from doing the work.
Greg Wedow retweeted
We used to talk about a "pit of success".
Humans would be dragged towards writing the right code by well-designed API's, a good test suite, sensible lint rules.
You couldn't make the pit too steep, otherwise the humans would get annoyed. There was a social contract.
Feels like what we need now is a black hole of success. An inescapable event horizon agents cannot cross.
Agents don't feel annoyed, so you can crank up the pressure to infinity. There is no social contract to break.
In other words, increase the forces on agents to the maximum. Make great code inevitable.
Love the current Tailscale drama. So many people signalling their lack of critical thinking skills and it's really helping me clean up my timeline.
Greg Wedow retweeted
that tailworm site reads like gigaslop, i call bullshit on the framing.
the ssh bug is basically: authorized nonroot access can become root via unix socket forwarding. serious, but propagation follows ssh policy. this concerns tailscale’s opt-in ssh server, not ordinary openssh.
the path also requires the attacker (yourself) to be added to your tailnet, enabled tailscale ssh (not enabled by default), configured forwarding (not default).
Greg Wedow retweeted
Everyone who owns hardware with abominable software (like Sonos players) owes a debt of gratitude to Venkatraman Srinivasan and the rest of the eMudhra gang in Bengaluru, Karnataka. Without their gross negligence, it'd be a lot harder to counterfeit certificates and fix the sw🙏
The 8192 core CPU I'm building at @uscompco will, aside from being absurdly high performance, also have some very strong sandboxing and security features.
For example, with a short pipeline and a few other small changes, branch prediction becomes unnecessary for high performance, eliminating entire classes of speculation-based security vulnerabilities.
Furthermore, all those vulnerabilities from context switches creating shared resources between multiple programs? Gone too. With 8k cores, everything just has its own cores, no context switches, only packets. We can even achieve a lot of sandboxing and isolation with the majority of on-chip packets.
Greg Wedow retweeted
I agree with everything OP says except "watching all of those years go down the drain."
AI might have made it almost meaningless to write code by hand anymore. But the people who have spent years/decades writing code are now in the best position to leverage AI coding tools.
Learning to code was a stepping stone toward learning to decompose and solve complex problems. I have worked with a lot of different people with different levels of coding experience. And I can say with confidence that, in general, the more coding experience you have, the better you're positioned to think about long-horizon tasks and to organize and tackle problems with multiple moving parts.
All those skills directly translate to using AI coding agents. And I'm seeing it happen in real time. People with long software engineering experience have a totally different way of using AI coding agents (given that they set their ego aside and accept that this is the new norm). They are more organized, know how to steer the agent like guiding an intern or mentoring a junior dev.
People who don't have coding experience are using agents in a random and chaotic way (the approach has its outside-the-box-thinking merits but doesn't have the same reliability as the experienced SWE approach).
For some people, coding was the only valuable skill they had.
If you made your money by selling your ability to write JavaScript, CSS, Python, or whatever else, I understand why you are pissed now.
"Writing code" is worth very little today.
The sad part is that learning to code wasn't easy. It takes years for someone to become a skilled programmer.
Imagine watching all of those years go down the drain.
If you are a programmer (I mean, just someone who knows how to write code in a particular programming language), your days are numbered.
If you still think AI can't do your job, you are just in denial.
But honestly, writing code was never that valuable anyway. If you were a code pusher, you already knew that the best people at your company weren't just writing code.
They came up with new ideas, designed solutions, architected whole systems, knew how to troubleshoot and fix problems, found different ways to build better software, and, in general, spent almost no time writing code.
Not only are those people thriving today, but they're also the ones who will ride the AI wave and learn to bend it to their will.
So don't cling too long to what you lost; embrace what's already here. AI is a tide that lifts all boats, but you have to be open to it.
Greg Wedow retweeted
I always thought it was a shame that modest default stack setups made alloca() a generally-frowned-upon technique in C/C++. With 64 bit architectures, give every stack a virtual address space equal to the physical memory by default!
You can do a surprisingly good job of memory management with just the stack, and I contend that it has both correctness and performance advantages.
Allocations are a trivial pointer adjustment, and frees are literally free. Keeping everything linearly packed is friendlier for all layers of the cache hierarchy, and it makes keeping everything in huge / gigantic pages easy.
Leaving temporary intermediate blocks on the stack can seem wasteful, but unless you are dealing with algorithms that make > O(n) temporary allocations, it is usually not a big deal.
Static analysis can check if you store a stack pointer into a structure deeper in the stack, which is a use-after-free, and then memory management correctness is guaranteed.
The discipline of caller-allocates-return is awkward in some dynamic cases. It would take a change in low level calling conventions, but you could plausibly have functions that return with the stack extended from where it was when they were called. I’m not holding my breath for that.
It isn’t obvious if having AI coding agents makes discussions of software architecture more or less important!
Greg Wedow retweeted
Hey, you know that part of the roller coaster where you just barely start picking up speed after a long climb to the top, facing the ground
Greg Wedow retweeted
Some stats on #php2shell. In the 10 hours before it was publicly announced, across the @Cloudflare network we saw thousands of attempts to exploit it. That jumped to tens of thousands in the 45 minutes post announcement, hundreds of thousands within 2 hours, and millions now.
How do I completely withdraw from the public internet?
Need to get my bank on my tailnet and drop everything else l.
Today we're releasing abliterated-model-large-v2.
Based on GLM-5.3, which is #3 on Terminal-Bench 4.0 (behind only Opus 5 and Fable), with 2× the cyber exploitation of 5.2.
We abliterated and hosted it so it does the offensive cyber, red teaming, and agent testing work other models refuse to do.
- US-hosted
- FP8
- 1 million context window
- Zero input/output prompt retention
Live now. 🧵
