dexterlagan

I agree. I wonder if there's an easy-to-use DNS resolver one can install everywhere. Any recommendations for win/mac?

I can't believe Windows is the most popular OS in the world. I can't believe people like ChatGPT. I can't believe LLMs are getting smarter. I can't believe some software is actually good. I can't believe a corporation can make a good product. Surprise! We're all just humans trying to be useful and happy, even CEOs!

It's like OpenAI and Anthropic engineers never learned about how bad/dangerous modal interfaces are.

Wrong company - toxic culture. It's completely possible to use LLMs for development and loving it. Focus on innovation and quality, less on shipping. That's the execs' fault. I'd quit and go somewhere people care about what they're doing.

Seems to be written by somebody who has never worked within a team, never published a commercial piece of software (with the said team), and never used an LLM to write code. How is that possible? I love Common List and Racket. Love them to bits. I'd use them all day every day if it weren’t for that pesky LISP curse and the fact that nobody would want to work with me. LLMs, until recently were consistently forgetting parens, couldn't close functions properly. Somehow LLMs can't really count in their head, so it makes for a really... fun time with LISPs.

Finally somebody who gets it. Today the definition of Content is view-optimized, click-bait, gapping mouth YT trash. I can't stand it anymore. I want real video of real people saying real, interesting things.

When I found out Brave was just as sold as all the others (their track record is sad), I found Waterfox. What a breath of fresh air. Great adblocker, works on YT, no commercial BS. I hope they keep it that way.

Notwithstanding the political drama surrounding AI, this is the best model Anthropic has produced so far, and I've tried them all - as well as every competitor's. After a couple of 14-hours days spent with it, I'd say it's on par with GPT-6, but at much lower cost. I have $20 subs for both OAI and Claude, and GPT-6 Astra burns my 5-hour credits in an hour or so, where Opus 5.5 lasts nearly all day, as long as I take a proper lunch break. Combined with the I-have-ADHD skill, it's my new daily driver. Opus 5.5 found a lot of major problems Opus 5 had left in my codebase, some of them critical (username and path leaks).

I wouldn't trust Meta - period. The fact that this agent is made by Meta is reason enough to completely ignore it :)

Agreed, alignment is an inside joke. The fact that they admit that it's done by... AI is quite revealing. About the job losses however, either that tech isn't as useful as it's hyped to be, or it's so useful that it's creating new jobs. Just saw this: https://www.newyorker.com/news/the-financial-page/has-the-ai...

I'm still here, nearly 50 years and counting. If you had asked me what I imagined AGI would look like back in the 90's, I would have told you "A system that can do everything we can: see, hear, think, do.". If you had shown me GPT-6 back then, I would have said "It looks like a really powerful program, but that's not really what I had in mind.". That's AI, but it's not quite general.

Oh God, that "a dead drag handle during a booked half-day you do not get back" got me. I saw this pattern in Claude's 'explanations' so many times. It's trying to say that it did something significant, and that you'd only have found out much later, at higher cost (or something). That annoys me to no end.

I use Claude Code (both Desktop and CLI) all day every day (as well as OpenCode with DeepSeek V4 among others). For non-mission-critical stuff (small internal tools, anything that doesn't touch the client and doesn't handle critical data or infra), I'm on Auto (sandboxed in the working directory). For everything else I approve every change, meaning I review every code change the model proposes. Plan mode is great to write the architecture as well, as it doesn't touch any file, doesn't write anything, and lets me iterate until the arch is perfect and the proposed high-level code (modules etc) is solid. I haven't used an editor in over 4 years, apart from writing specs.

Ornith 1.5 35B MoE is very close in most benchmarks, but runs at 100 tk/s where Qwen3.8 27B runs at 30 tk/s (MBP M5 Max 48GB). It's now my go-to model for quick inquiries. Ornith 1.0 had problems with world knowledge, but 1.5 seems very solid on that front. I'll be running some agentic tests today.

Ornith 1.5 35B is so fast that my CPU doesn't even have time to heat up, where Qwen3.8 would turn my laptop into a toaster within a few minutes. I hope agentic tasks will hold up!

I ended up getting an M5 Max MBP with 48GB and it runs Qwen3.8 in Q4. I developed 3 apps so far, medium complexity, with no issue using OpenCode. This is probably the minimum setup for comfortable local agentic coding in my book.

They haven't communicated well the fact that the default model should be Sonnet 5, which should give you unlimited use for common coding tasks (say with occasional subagents use) on the Pro plan. Instead they're pushing Opus and even Fable, to try and get people addicted to the higher tier, without realizing that nearly everybody has a Sonnet for peanuts via DeepSeek V4 on OpenRouter, or completely free through Qwen 3.8 locally. I predict major trouble for Anthropic, now that OpenAI's models are closing in, are cheaper for daily use and don't have those silly 5 hours limits - and that Chinese models are getting really good and are even cheaper.

Qwen 3.8 is excellent. With the right harness, it does about 95% of what Opus can do, in my case automation software development. Since 3.8 came out, I have significantly revised my expectations for a local model. Give it another year or two, and we'll be running fast and free local models for nearly everything that matters, and these costly subscriptions will be a thing of the past. I've always believed that AI should be free for everybody, like TV and radio. We're almost there.

For my own tools, some of them still in production at home and at work: https://github.com/DexterLagan?tab=repositories&language=rac...

Yet another LISP in disguise...

I needed another reason to cancel my Claude sub. Thanks Anthropic!

This is akin to adding a giant watermark on things one would made with a free product "Made with XXX". Except you're paying $200/month for it, and there's no way to disable that watermark.

I don't disagree with EU regulations, but I strongly believe the onus should be on the content publisher, not the toolmaker. If the toolmaker watermarks whatever his tool produces, it opens a giant can of worms that cannot be closed. That means anything and everything you make with this tool is no longer fully yours, it contaminates everything and makes your work traceable. Who wants that?

I was already annoyed by the fact that Claude marked everything it did on my repos under its own account (I didn't ask for any of this), but now everything is invisibly marked, even the code. Not that I care that my writing would be watermarked, since I'd rather write my stuff myself, but code? No thanks.

Meanwhile I'm running a DeepSeek V4 Flash or Pro, or a Qwen3.8, and it writes my code without a peep. Resulting repos are clean, just the way I want them. No 'Claude' account, no watermarking, nothing. I won't be looking back after having tried these new models. Whoever makes good models that don't broadcast their maker will get my business.

This watermarking will simply push people more towards Chinese models. Keep pushing in the wrong direction Anthropic. Doing this right before an IPO is a great idea.

Rhombus is what Racket should have been, back when it was the learning language at MIT, before it became Python. Had it been like this, maybe Python would have never gained traction within that community. The world would have been a very different place.

Rhombus' syntax is soooo beautiful. As a Racketeer, it's my dream language. All the power of Racket... without a Lots of Insipid, Stupid Parenthesis. Not that I don't like the parens, mind you, but Rhombus looks so much more... 2009. My only regret is that nobody will use Rhombus, except a few enthusiasts, for fun. In an AI age, new programming languages should really be LLM-first, sadly. But it makes me so happy that there are some people who still care about humans coding.

I run mine on an M5 Max with just 48GB of (V)RAM, and it fits nearly twice in Q4. Works perfectly. I'm kinda glad I didn't spend the extra $2400 to get 128. We don't really need more... and that's a good thing (tm). God knows I thought about it in store. But I thought... maybe this year will be the year of the local model? Maybe soon we won't need that much RAM? I was right.

The fact that it runs at 15tk/s in power saving mode, and 30 in perf. mode blows my mind. I can run the model in the background, coding something for me in OpenCode, hosted in LMStudio, while doing something else. What a world we live in.

Having something close to human intelligence (at least for reasoning and code), running on a laptop, is amazing.

Like most models it makes up things when it doesn't know. I had high hopes for Gemma4, which was said to having 'solved' this particular problem - it didn't. Gemma4 made less things up, did say it didn't know more, but it's still far from perfect. By comparison Qwen3.8 knows more, but still makes things up when it doesn't know. Coding abilities are very impressive however, and yeah these SVG tests do seem to 'scale' or generalize over its general reasoning+coding abilities - at least in JS and Rust. My next test will be to ask it to write some macros in Racket, just to see if it can balance parens. Most, if not all models cannot, no matter their size.

Meaningless yet fun fact: DeepSeek V4 Pro 0813 made a much worse icon for the same app, and only produced an SVG I had to convert manually to .png. Qwen3.8 made a perfect icon in .png. I don't yet know how it did it, but it did it.

Qwen3.8 also seems to know French quite a bit better than Copilot, at least on common expressions. I have yet to run more tests for languages, but I'm baffled by its finer accuracy on the few sentences I asked it to translate, which were botched by Copilot. Go figure.

It was in LMStudio (llama.cpp), Q4 by Unsloth. Applied the recommended defaults published by Unsloth.

100% agree, it's really just for kicks&giggles. The fact that the model answered correctly, unlike every other model of its size before it, still pleasantly surprised me.

Agreed. It's just to see how much knowledge the model still has for its size. For comparison, no other model of this size has ever given me the correct answer to the Keel question. Even GPT-OSS-120B got it wrong, but it's expected for its relative old age.