"everything Trump touches dies" (the title of a Republican Strategist's book) seems more appropriate.
Apart from literal deaths, this has torched American military and diplomatic credibility across the globe. It was basically guaranteed to, with the only potential slim upside for America being a demonstration that their military might when applied ruthlessly might dramatically punish their victims as a warning to others. And it has so far failed at that.
He’s objectively terrible at making deals, though. He’s apparently incapable of win-win scenarios. His ego demands that he win while the other party loses, where “winning” is defined as “personally stroking his own ego” and “lining his pockets.” His only negotiation tactic is threats and bullying.
Although, in this case, given recent news about prediction market plays, I wouldn’t be surprised to learn that the whole farce of a “ceasefire” was just prediction market manipulation. (Well, that and TACO Tuesday so Trump could get out of following through on his threat of genocide. One spot of sanity, if you can call it that, in a shit sandwich of the stupidest US foreign policy blunder since the war in Vietnam.)
Some say the stupidest US foreign policy blunder ever, perhaps even the greatest in all history by any leader, dumber even than invading Russia in winter.
The stupidest US foreign policy blunder... so far. Invading Cuba, invading Greenland and dropping out of NATO are all on deck, so let's not pick a winner just yet.
This reminds me of the various visualizations in WinAmp, and there was no shortage of creativity there! Geiss (sp?) anyone? It really whips the llama's ass!
MilkDrop has been dropping new versions since WinAmp stopped, and it runs without WinAmp (though WinAmp + all of the visualizers also still work on the newest Windows): https://www.milkdrop3.com/
I wouldn't say it's gentle but it certainly is a great book. Great exercise problems. Some of the proofs are so elegantly done, especially the way calculus of variations is avoided.
David Mackay's book hand holds a little more than Cover and Thomas, although it's remit is more than just information theory.
I've never seen it mentioned anywhere in their histories but I always suspected the messaging apps Slack and Discord were references to Church of Subgenius and Discordianism respectively
Alternatively, ensuring you have enough slack in the schedule is, at least for some tech leads and project managers, an essential tool to enable meeting deadlines.
(So, I suppose using "slack" in a positive sense by project management, while probably still being considered a pejorative thing by non technical management or beancounters...)
yep, having some slack is the only way for someone / something to able to respond to uncertainty. technically having firefighter on standby and policemen on patrol are a form of slacking, and we (should) have no problem with that.
and Bob with his Billard pipe, now as you brought these up!
My father did not smoke, but many of his colleagues did which some did look 60's bit like Bob. For some odd reason I still kind of remember what tobacco and pipe smell felt in room when I begin to think of it, like now in this occasion.
I recently (~6 mo ago) made it a goal to understand and implement a useful Kalman filter, but I realized that they are very tightly coupled to their domain and application. I got about half as far as I wanted, and took a pause. I expect your work here will get me to the finish line, so I am psyched! Thank you!
Thanks for your feedback! Actually the KF concept is generic, but as mentioned above:
"The state transition and measurement equations belong to the system model. They describe the physics of the system and can vary from one application to another."
So it is right to say that the implementation of the KF is tightly coupled to the system. Getting that part right is usually the hardest step.
I am on their "Coding Lite" plan, which I got a lot of use out of for a few months, but it has been seriously gimped now. Obvious quantization issues, going in circles, flipping from X to !X, injecting chinese characters. It is useless now for any serious coding work.
I'm on their pro plan and I respectfully disagree - it's genuinely excellent with GLM 5.1 so long as you remember to /compact once it hits around 100k tokens. At that point it's pretty much broken and entirely unusable, but if you keep context under about 100k it's genuinely on par with Opus for me, and in some ways it's arguably better.
Seconded. I'm getting used to the changes that happen in the conversation now, and can work out when it's time for my little coding buddy to have a nap.
And Opus is absolutely terrible at guessing how many tokens it's used. Having that as a number that the model can access itself would be a real boon.
The Dumb Zone for Opus has always started at 80-100k tokens. The 1M token window just made the dumb zone bigger. Probably fine if the work isn't complicated but really I never want an Opus session to go much beyond 100k.
The cost per message increases with context while quality decreases so it’s still generally good to practice strategic context engineering. Even with cross-repo changes on enterprise systems, it’s uncommon to need more than 100k (unless I’m using playwright mcp for testing).
I had thought this, but my experience initially was that performance degradation began getting noticeable not long after crossing the old 250k barrier.
So, it has been convenient to not have hard stops / allow for extra but I still try to /clear at an actual 25% of the 1M anyhow.
This is in contrast to my use of the 1M opus model this past fall over the API, which seemed to perform more steadily.
I’m genuinely surprised. I use copilot at work which is capped at 128K regardless of model and it’s a monorepo. Admittedly I know our code base really well so I can point towards different things quickly directly but I don’t think I ever needed compacting more than a handful in the past year. Let alone 1M tokens.
The context windows of these Chinese open-source subscriptions (GLM, Minimax, Kimi) is too small and I'm guessing it's because they are trying to keep them cheap to run. Fine for openclaw, not so much for coding.
I haven't screenshotted to alas, but it goes from being a perfectly reasonable chatty LLM, to suddenly spewing words and nonsense characters around this threshold, at least for me as a z.ai pro (mid tier) user.
For around a month the limit seemed to be a little over 60k! I was despondent!!
What's worse is that when it launched it was stable across the context window. My (wild) guess is that the model is stable but z.ai is doing something wonky with infrastructure, that they are trying to move from one context window to another or have some kv cache issues or some such, and it doesn't really work. If you fork or cancel in OpenCode there's a chance you see the issue much earlier, which feels like some other kind of hint about kv caching, maybe it not porting well between different shaped systems.
More maliciously minded, this artificial limit also gives them an artificial way to dial in system load. Just not delivering the context window the model has reduces the work of what they have to host?
But to the question: yes compaction is absolutely required. The ai can't even speak it's just a jumbled stream of words and punctuation once this hits. Is manual compaction required? One could find a way to build this into the harness, so no, it's a limitation of our tooling that our tooling doesn't work around the stated context window being (effectively) a lie.
I'd really like to see this improved! At least it's not 60-65k anymore; those were soul crushing weeks, where I felt like my treasured celebrated joyful z.ai plan was now near worthless.
The question is: will this reproduce on other hosts, now that glm-5.1 is released? I expect the issue is going to be z.ai specific, given what I've seen (200k works -> 60k -> 100k context windows working on glm-5.1).
I have gone back to having it create a todo.md file and break it into very small tasks. Then i just loop over each task with a clear context, and it works fine. a design.md or similar also helps, but most of the time i just have that all in a README.md file. I was also suspicious around the 100k almost to the token for it to start doing loops etc.
I am on the mid tier Coding plan to trying it out for the sake of curiosity.
During off peak hour a simple 3 line CSS change took over 50 minutes and it routinely times out mid-tool and leaves dangling XML and tool uses everywhere, overwriting files badly or patching duplicate lines into files
Is there any advantage to their fixed payment plans at all vs just using this model via 3rd party providers via openrouter, given how relatively cheap they tend to be on a per-token basis?
That's more expensive than other models, but not terrible, and will go down over time, and is far far cheaper than Opus or Sonnet or GPT.
I haven't had any bad luck with DeepInfra in particular with quantization or rate limiting. But I've only heard bad things about people who used z.ai directly.
I use GLM 5 Turbo sporadically for a client, and my Openrouter expense might climb over a dollar per day if I insist. At about 20 work days per month it's an easy choice.
I'm not certain if you're saying it's an easy choice to go with or without the fixed cost coding plan.
I see it's $81/quarter, but it's also not clear to me from what I've seen from people's postings that it actually gives you immediate access to new models as they come and whether there's usage limits and such.
The other advantage of just using API is that one is free to use other less expensive, free, or local models for more routine grunt work stuff
For usage that's regular instead of bursty, I suppose the subscription is a no-brainer. Daily agents dev, -claw scenarios, etc.
My total usage might be about equivalent to the sub price, so what I get in return is the absence of quotas for the few periods I need GLM to be available without restriction.
In sporadic use, I wouldn't improve my spend by paying a subscription then also paying metered when I cross the hours/day/week quota, only to leave the rest of the sub unused most of the month.
My impression is that different users get vastly different service, possibly based on location. I live in Western Europe, and it works perfectly for me. Never had a single timeout or noticeable quality degradation. My brother lives in East Asia, and it's unusable for him. Some days, it just literally does not work, no API calls are successful. Other days, it's slow or seems dumber than it should be.
Their distribution operation is very bad right now. The model is pretty decent when it works but they have lots of issues serving the people. That being said, I have had the same problems with Gemini (even worse in the last two weeks) and Claude. So it seems to be the norm in the industry.
Starting an hour or two ago GLM's API endpoint is failing 7/8 times for me, my editor is retrying every request with backoff over a dozen times before it succeeds and wildly simple changes are taking over 30 minutes per step.
Every model seems that way, going back to even GPT 3 and 4, the company comes out with a very impressive model that then regresses over a few months as the company tries to rein in inference costs through quantization and other methods.
This is surprising to me. Maybe because I'm on Pro, and not Lite. I signed up last week and managed to get a ton of good work done with 5.1. I think I did run into the odd quantization quirk, but overall: $30 well spent
I have their most expensive plan and it's on-par and sometimes better than Claude although you have to keep context short. That being said, the quota is no longer generous. It's still priced below Claude but not by that much. (compared to a few months ago where your money gets you x10 in tokens)
I'm on their lite plan as well and I've been using it for my OpenClaw. It had some issues but it also one-shotted a very impressive dashboard for my Twitter bookmarks.
For the price this is a pretty damn impressive model.
I think what Anthropic is doing is more subtle. It's less about quantizing and more about depth of thinking. They control it on their end and they're dynamically fiddling with those knobs.
It has been useless for long time when compared to Opus or even something like Kimi. The saving grace was that it was dirt cheap but that doesn't matter if it can't do what I want even after many repeated tries and trying to push it to a correct solution.
I have been very disappointed in the Lite plan over the last few months. It started great, but they are obviously quantizing and cutting costs on the low end plans. The agents go into bad loops and contradict themselves, inject chinese characters, etc. There is obvious compression happening which makes it unreliable and unsuitable for serious work.
reply