Older U.S. taxpayers approaching retirement will bristle at word combinations such as "entitlements to retirees" as they have put enormous capital, which can clearly be summed from their large stack of W2s, into Social Security. Also, there are large segments of "retirement age" people who simply can't afford to retire.
My comment is a completely unsubstantiated conspiracy theory: the choice of model name, Mythos, seems out of character for Anthropic models, and one can easily wonder if the model truly exists as the name suggests. It could instead be a symbolic model used by colluding companies (and perhaps even governments) to establish a reference limit upon what models will be publicly accessible, period. Probably a terrible theory as it could spell doom for frontier model developing companies' business models -- setting the bar already would likely commodify LLMs via open source models quite quickly. But the name "Mythos" is such a strange choice for this model and the circumstances surrounding its release.
In my experience the plan is plastic and responsive to iteration through dialogue. I don't think too much structure here is going to be desired by all users. But the "sounds good, but needs these edits" option can save a small amount of interaction. I often use the tab command that exists to modify the yes and no options. If you tab modify "Yes", I believe the plan will be executed and addendums from your additional prompting will be made afterward. By using tab modified "No", you can be clear about what parts of the plan are to be kept and what is to be immediately adjusted. Tab modified "No", definitely works as the "sounds good" option, but perhaps requires slightly more typing than you would like. "No, use most of this, but change..." I don't think there is a glaring lack here at all.
I think the pipeline paradigm you speak of is powerful, and some of the clarity issues you claim can be improved through clear and consistent use of keyword destructuring in function signatures. Also by using function naming conventions ('add-service-handle' etc.) and grouping functions in threading forms which have additive dependencies, can also address these frustrations.
There are still Clojure remote positions. Thankfully, I have used Clojure professionally long enough that my core ability shouldn't atrophy too much now that we have moved away from it at my current position. I am looking forward to Jank actually.
There were multiple reasons at our company -- my particular team, all skilled Clojurists, decided to default to python last year for a variety of reasons including both AI code generation suitability and AI model utilization in our code bases; the latter is of high relevance for our particular work. While I find Clojure to be among the best languages for interacting with LLMs via API, it is awkward for interacting with local models directly. Of all on the team, I was probably most open to a polyglot approach.
Incidentally, I am having great success using AI with Clojure. In fact, from what I read online, better than most. I'm not sure if it's due to Clojure's terseness (and hence, token economy), or other reasons, but it works very, very well.
I am sure that RIAA lawyers would rofl at this yt-dlp labelling being an example of Google "... unethically misleading people and (committing) browser monopoly abuse". I want to live in that fantasy world with you though.
Come to our fantasy Linux land anytime you want. We circumvent all of the strange things both RIAA, MPAA, Google and many other companies do to attempt to lock information into a box with only one hole they allow you to look through.
Our fantasy land gets better every time your reality gets worse.
Agree with sibling comment as someone who used Zen for many months, maybe as long as a year or two. It constantly breaks and often stays broken in small but fundamentally important ways, to the point that I just switched back to FF last week and am glad to be off the roller coaster. Before Zen I had tried Arc and left for a lot of the same reasons.
For all of the (valid) criticism against FF, it's still the best available browser that's not just an experiment IMHO.
Edit to add: part of the switch back is that FF now supports, to some degree, all the features I was using Zen for: vertical tabs (needs customization but works well enough), custom search "engines" (ie, shortcuts), split view, not-Chrome
I daily drove Zen for months. The design and implementation are overall fantastic. Unfortunately it still has chronic performance issues, gobbling up CPU randomly - and they don't seem to be too focused on despite it being a commonly reported issue.
I don't want to burn out my battery quicker than usual, so I was forced to switch off. I'm currently trying Orion instead and have been loving it - aside from several poorly implemented websites just not working on it. And the Cloudflare false positives, but that's as much or more an issue on Zen.
Website compatibility is inconsistent, extension compatibility is a slog, the desktop UI is confusing and nonstandard, WebKit itself is woefully incomplete, and on non-Apple platforms WebKit barely works covers conformance tests even with hardware acceleration disabled.
I don't use macOS anymore, but when I did I used Firefox without missing out on anything Safari would have given me. Now that I've abandoned macOS I don't think I can name one advantage of installing a WebKit browser on my system versus something Chromium-based.
I think stories like these may make the host, Y Combinator, uneasy. They have invested in Dome, a prediction market startup, which was acquired by Polymarket last month. I had a comment to a previous story, https://news.ycombinator.com/item?id=47397822, critical of prediction markets which had acquired a fair amount of points and prominence, but ultimately was flagged and removed by moderators. It seemed over the top and I suspected that there might be a YC Polymarket connection, and subsequent searches revealed this to be the case (Dome as mentioned above). Perhaps this comment will be flagged too. Unfortunately, Hacker News might not be the best venue to discuss the dystopian possibilities of prediction markets.
reply