ilitirit

I'm just extremely tired of non-technical people trying to tell me how to do my job, what the state-of-the-art is, that I can implement their non-existent specs faster, or that software development is just about the ideas not implementation because we have swarms of clankers available.

> herdr is by far the most polished tool in its category.

Can't speak to this, but I like that I didn't feel like I needed to try an alternative. It just did exactly what I needed it to do.

That said - I couldn't find a way to move a pane to a new tab. I can swap panes within a single pane (select -> right click -> swap with focused pane), but I can't find a way to do it between tabs. Maybe it's a skill issue. Anyone have any ideas?

Relevant:

https://www.youtube.com/watch?v=zCvPPaIN5Ew

It's a video on AI-manufactured rage-bait. Quite a few plot-twists that I won't spoil here.

Battery 3 from Native Instruments is a drum sampler from around 2013. This is in the manual:

Remember, machines don’t kill music, people do—and quantization is one of the main weapons. ... Quantizing everything is the quickest way to suck the life out of a piece of music.

https://docs.native-instruments.com/pdf-guides/Battery_3_Man...

I've been trialing this for the last few hours. It was quite slow at first, but now I'm getting around 300-400tps. Still nowhere near 1000tps, but it's still incredibly fast compared to what I'm used to with other models. It's quite capable as well. I asked it to present strategies for training an AI to play fighting games and it gave quite well-reasoned output. It searched the existing my existing knowledge base for details about the game's internals, including record/playback, and it's own general knowledge about the game is played. It wasn't sycophantic about my opinions either - it challenged me appropriately.

I think they might have a really decent model if they can deliver their advertised speeds at scale at reasonable prices. A tiered approach could work well.

I suspect that we may soon be seeing a modern version of VHS vs Betamax. Betamax was better quality, but VHS beat it in virtually every other metric that mattered to most consumers.

(yes, I'm aware the analogy isn't perfect for many reasons)

My current experiment is running a Chief of Staff pattern within herdr, nothing too fancy. You should be able to find quite a few resources on the net.

I've all but given up on these types of approaches. Models will often just ignore your process instructions at the most inopportune moments. For work, I've resorted to mostly just using single agents for smallish pieces of work that I orchestrate myself. I treat it as a tool, with me being the craftsman.

Everyone is pushing Agent Fleets and Swarms, and I'm sure that there are many success stories, but from our internal experiments many devs don't see any speed advantage for complex work. Here's what one of them told us recently: "The speed advantage is offset by the manual refactoring work. The code is 'correct', but it's just not what any of us would have written".

Now one could argue that you could just ignore the code if it's working (that is in fact what Ex Co instructed us to do) and just keep running these fleets if the end result "works", but I'm not fully convinced this will end well in the long term.

Then again, I'm stuck with decades of legacy code and systems that noone understands that were introduced by humans...

Then I guess all that it changes is that my proposed setup gets even better?

I've been using DS v4.1 Flash daily for nearly a month now on Agent Swarm experiments. I've tested it against GLM-5.3-flash and Opus 5.5. DS 4.1 comes out tops for me. Opus 5.5 is still the smartest, but DS 4.1's speed and price more than make up for the "intelligence" gap. I've ran Chief/Builder/Reviewer swarms autonomously for multiple days. I think my new workflow is going to have DS 4.1 Flash do all the engineering and just have Opus review its work. 4.1 Flash really is a very impressive model. Kudos to the Deepseek team.

Probably not universally true, but good writing is a skill regardless.

And maybe they are "too long" in the same way that Lean proofs are "too long"? I have no idea - I don't read either very often.

However, often I don't care how verbose a piece is if it can hold my interest. For example, the late Umberto Eco wrote some of my favourite pieces. He was a philosopher (among other things), and many of them - notably of the "post-modern" - are known to be particularly verbose.

Here's a particularly relevant one: https://www.nybooks.com/articles/1995/06/22/ur-fascism/

I use it at work. On Windows it also launches a new console window every it executes (?) a command. You should definitely disabled this using --no-daemon.

I don't know how and why they ruined this CLI with needless "features". It was perfectly usable two weeks ago.

I still use GPT 5.5 daily. It doesn't seem to have this problem. It just gives me a concise summary and gets to work.

I tried really hard to get senior management to understand this where I work. Yes, AI is an accelerator, but that doesn't necessarily mean it's going to accelerate you in the "right" direction.

I wrote about this recently on one of our company's IT channels. I called it "slop-fatigue". I - and others - have started to get noticeably dismissive of content that appears to be written by an LLM. The whole thing was a piece about the ironies of software development in the world of LLMs. This part spoke about how easy it is to generate docs now, but it's also even easier to dismiss it. This contributed to cognitive-debt, because humans didn't write the docs, and other humans tend to dismiss the content. I saw a recent reaction to this on HN as `ai;dr`. That's almost exactly how I feel about it.

Margaret Storey's recent piece on Cognitive Debt: https://spawn-queue.acm.org/doi/10.1145/3807966

I still haven't moved from Codex GPT5.5. Sonnet and Opus 5 have just been awful for my use cases. I recently caught Opus 5 hallucinating about code it just wrote. It's just not nearly as cost effective as GPT5.5, and it's too verbose, and it never "has the full picture". Sonnet isn't even worth considering in my world. Both recent models definitely feel nerfed.

I guess it depends on the context and environment, right? In many corporates, the bottleneck for me has always been specs and testing. I have daily examples. I had to explain it to leadership like this: "There are far more ways things can go wrong than right".

I agree with the point about dogmatism, but I have so many other issues with this piece.

I mean... how do you even make the comparison between "A Handbook of Agile Software Craftsmanship" and "History of Hispanic Colonialism”!?

I got downvoted for asking a related question recently, but I also don't think people really understood what I was asking - I'm not trying to anthropomorphise LLMs to that extent.

Basically, if you tell a model "You're an absolute moron, of course that's wrong!", will it give better or worse results? How much of that response will it absorb into its persona (like some humans tend to do)? Will it try to give "safer" responses to avoid negative feedback? How much of the associated behavior can be attributed to RLHF (e.g. like the sycophantic nature of LLMs)? How much can be attributed to training data?

Obviously this will vary by model and training, but I'm trying to get a general understanding.

I recall seeing related outcomes in some of Anthropic's studies, but I'm not sure how much of this particular aspect was studied.

I've often wondered if LLMs can suffer from psychological abuse in symptomatic ways. Not literally of course, but for example, if you berate the LLM by calling it stupid, or useless, does that modify its behaviour negatively? Part of me think it does, but I don't really have any evidence for this. Maybe a fun weekend research topic.

It's also one of my major issues I have with how this is being introduced into many enterprises, including the company I work for:

"Here's AI. Figure out how we can make money from it. We're adding it to your performance reviews"

Basically, here's a solution. Find problems for it.

"Conceptual integrity" is something I always try to adhere to when I design and build systems. I also use it also a bit of an indicator when gauging someone's experience. For example, mid-level devs will often try to introduce some form of "optimisation" somewhere in the codebase that results in the codeflow deviating from existing patterns. More often than not I will reject the PR, or the idea. For me, it's better than all flows follow similar paths. It makes it easier to reason and communicate ideas about, modularise and/or form logical groupings etc etc.

This is also why one of my instructions to coding agents is that they adhere to established coding and testing patterns, even where they appear to be sub-optimal.

What was the "pattern" before this in these fields?

What is the current pattern in other industries?

Does the pattern exist elsewhere in the world?

> Venting is important.

Of course. But you shouldn't run retros that are focused on it.

I personally have never worked in a team where Agile (the concept) has failed. But I've also seen it fail all around me. Especially when it's mandated without buy-in. Or when people just don't "get it".

e.g.

- 45 minute "standups" (!?)

- PI "planning" that consisting of deadlines and glorified multiplayer MS Paint

- Rigid adherence to ceremonies or processes that add zero value

- Retros that focus on complaints and venting with no actionable outcomes

- etc etc

Every time I've introduced Agile to a team or project that was new to it I was always met with skepticism. But 6 months down the line noone on the team/project wanted to go back to the "old" way of working. I don't even really care about any text book definitions. These are the only things we try to stick to:

- Short, daily standups

- Planning based on risk reduction

- Estimates based on complexity (ties in with risk reduction)

- Actionable retro items

- User demos every sprint (makes it easier to pivot - users rarely know what they want)

> The only person who seems to claim that Dyson Spheres were a "joke" is Angela Collier and people quoting her. I've seen no other source for this claim.

https://www.youtube.com/watch?v=huAIfzUoyhU&t=121s

The concept of "Dyson spheres" was a joke by Freeman Dyson. It was never meant to be taken seriously. There's a clip about this floating around somewhere in which he finds it funny that the thing he's most well-known for was not even a serious paper. Dr. Angela Collier did a video about it.

https://www.youtube.com/watch?v=fLzEX1TPBFM

Probably at least slightly misleading, just reading the names of some of the countries in the list (I am from South Africa).

Just because a country generates 100% of its energy from renewables, it doesn't mean that its enough to power the entire or even majority of the country. Case in point: DRC. I believe only half of the population has access to electricity. It's been a while since I've looked into continental stats, but a quick Google search suggests the situation hasn't changed that much in the last few years.

> It wasn’t even good to users

I may be out of the loop, but how was Bitwarden not "good" to users? Does this relate to the recent price increase?

Too little, too late. In fact, in this post they seem to be committing to keeping it as bad (or even making it even worse) for my use case.

I've used Windows since 3.1. Win 11 was the straw that broke the camel's back. I moved to CachyOS a few months ago and I honestly can't find a reason to switch back.