Jonathan Rudderham

2.8K posts

Jonathan Rudderham

@codeRunnerUK

Writing meets AI. Two hobbies combined. Oh, and a bit of running. And sometimes some coding. https://t.co/RWc3xfnLNG

Kent, UK انضم Şubat 2009

110 يتبع184 المتابعون

Jonathan Rudderham@codeRunnerUK·1h

I stopped using Grok when I realised it had been corrupted to appease governments. The last straw was when I wanted it to generate a video of a scene from my story - the heroine sitting at the foot of a tree in a forest. I gave it no prompt, just the image. The image was AI-generated. No real person involved. I had to fight tooth and nail to get Grok to admit that it won’t generate photorealistic humans in case the human looks like one of the 8 billion real people on Earth. They’ve made it completely pointless.

English

National Conservative@NatCon2022·19h

Grok goes fully woke. This is what $33 per month (billed annually) premium Grok gets you now. No longer are you allowed to make artistic renderings of at-large crime suspects.

English

199

134

2.3K

183.8K

Jonathan Rudderham@codeRunnerUK·4h

@tim_cook Given the millions of YouTube influencers extolling “adequate MacBook Neo” as “the second coming”, I’m not at all surprised. Why have a launch event when YouTube is full of people who are salesmen in the guise of reviewers?

English

Tim Cook@tim_cook·5h

Mac just had its best launch week ever for first-time Mac customers. We love seeing the enthusiasm!

English

979

965

20.1K

2.4M

Jonathan Rudderham@codeRunnerUK·8h

@geekedout__ @LeakerApple And, yet, if I mention that it’s wrong for Apple to not “give a charger” at all when you spend almost £7,000 in Europe, I get piled on by Apple’s acolytes from the US for daring to mention it…

English

Dipayan Ray@geekedout__·12h

@LeakerApple it's a crime to give a 30W charger in a $1100 laptop 😭

English

2.7K

AppleLeaker@LeakerApple·13h

The included 30W charger with my M4 MacBook Air is SLOOOOOOW.

English

776

81.4K

Jonathan Rudderham@codeRunnerUK·18h

@ravikiran_dev7 Some days, 128GB is not enough. And I’m not really a developer. I just do my own thing.

English

Ray🫧@ravikiran_dev7·1d

As a Developer, how much RAM is enough for you? 1. 8 GB 2. 16 GB 3. 24 GB 4. 32 GB 5. 64 GB 6. 128 GB+

English

258

603

52.8K

Jonathan Rudderham@codeRunnerUK·20h

@jondelarroz I was kind of “meh…” and then … “Frank Castle! Yay, I’m watching this!” Would have been fantastic if DareDevil was to turn up given Matt Murdock’s previous cameo.

English

110

Jon Del Arroz | Pop Culture & Gaming 🎮@jondelarroz·20h

Why is Spider-Man: Brand New Day successful as a trailer? Simple: the audience is starved for a white, male lead as a superhero after all of the MCU replacements.

Jon Del Arroz | Pop Culture & Gaming 🎮 tweet media

English

1.8K

Jonathan Rudderham@codeRunnerUK·20h

@ivanfioravanti @UnslothAI Definitely excited for MLX training.

English

Ivan Fioravanti ᯅ@ivanfioravanti·1d

Love Unsloth Studio and I bet that when MLX training will be added it will be a super hit! Well done @UnslothAI

English

2.5K

Jonathan Rudderham@codeRunnerUK·20h

I think people need to look at their use case, then do some testing on what they want it to do, and then decide. I don’t think anyone can decide for them, because we don’t all do the same thing. For me, 27B looks very promising, from 4bit to bf16. But I suspect, as I use them more, I’ll find bf16 works best for my use case (creative writing).

English

118

Lotto@LottoLabs·21h

99% of people would be fine w/ qwen 27b and Hermes agent The 1% can offload work to sota

First Squawk@FirstSquawk

GOOGLE HAS BEGUN TESTING A DEDICATED GEMINI APP FOR MAC TO COMPETE WITH CHATGPT AND CLAUDE, OFFERING FEATURES LIKE CONTENT GENERATION, WEB SEARCH, AND PERSONALIZATION.

English

269

15.5K

Jonathan Rudderham@codeRunnerUK·20h

@LLMJunky @TheAhmadOsman @0xSero @ivanfioravanti @ZenMagnets @NVIDIAAI It would take me more than 6 months to pay off the first one! 😂

English

am.will@LLMJunky·21h

Finally proud to announce that I've joined the GPU Minor Leagues. 2 x RTX 6000 Pro. I have six months to pay off the second GPU lol. You are all TERRIBLE influences.

English

111

802

40.9K

Jonathan Rudderham@codeRunnerUK·1d

I’ve been doing long context coherence tests on local LLM and there’s one thing I’ve learned - not all long context is the same. Some that claim to have 512K or 1M content window are just rubbish. Some models are doing well with 256K content window (the heavier Qwen3.5 models), but not all do.

English

Matt Pocock@mattpocockuk·1d

Doing some experiments today with Opus 4.6's 1M context window. Trying to push coding sessions deep into what I would consider the 'dumb zone' of SOTA models: >100K tokens. The drop-off in quality is really noticeable. Dumber decisions, worse code, worse instruction-following. Don't treat 1M context window any differently. It's still 100K of smart, and 900K of dumb.

English

144

1.1K

143.2K

Jonathan Rudderham@codeRunnerUK·1d

Reading posts on X, it feels like people using OpenClaw/HermesAgent are doing nothing more than jumping from LLM to LLM every few hours. Does anyone actually get any work done? 😂

English

Jonathan Rudderham@codeRunnerUK·1d

@bindureddy Reading posts on X, it feels like people using OpenClaw/HermesAgent are doing nothing more than jumping from LLM to LLM every few hours. Does anyone actually get any work done? 😂

English

Bindu Reddy@bindureddy·1d

Open source continues to catch up with closed source MiniMax 2.7 just dropped and will likely become the most used LLM on Claw in days 🚀

English

337

86.4K

Jonathan Rudderham@codeRunnerUK·1d

@Bitcoin_Teddy I don’t have student debt because we couldn’t afford for me to continue education after school. I got a job as soon as I could - before I even left school. I’ve never had job security in my whole life.

English

Bitcoin Teddy@Bitcoin_Teddy·1d

Older generations say “we all struggled in our 20s.” No, you didn’t. You didn’t pay $3200 for rent and $10 for eggs. You didn’t graduate into $50K student debt and $0 job security. Gen Z isn’t dramatic. They’re drowning.

English

2.8K

26.1K

555.5K

Jonathan Rudderham@codeRunnerUK·1d

@4shpool I was not impressed with Nemotron-3-Super when I gave it my long context coherence test. It made me realise just how good the likes of Qwen-3.5 are (even though they’re not perfect).

English

ashpool@4shpool·1d

He said Quite literally "Use a lower quant" Q2 TRENCHERS REJOICE

Benjamin Marie@bnjmn_marie

Nemotron 3 Super GGUF evals: Q2 actually works. Model size goes from ~242 GB → ~53 GB, with only a tiny quality hit. Super impressive quantization robustness here, likely helped by NVFP4 pre-training, plus some very real Unsloth magic on top 🪄 Note: As usual, don't over interpret these results. +/- 10 points of relative error increase is not very meaningful. But above 10 points of increase, you can consider the model is bad.

English

249

Jonathan Rudderham@codeRunnerUK·1d

@4shpool In my long context coherence test, Qwen 3.5 - 27B dense beat 35b-a3b hands down. For MoE, the 122B model was pretty much on par with the 27B dense model. I’ve not tested shorter context so YMMV.

English

ashpool@4shpool·1d

I must say Qwen3.5-35-a3b (I use unsloth IQ4_NL) absolutely cooks on a MacBook M4 Best model in the 30B class that I've used (opinion). Prefer MoE to dense for speed, ofc

English

378

Jonathan Rudderham@codeRunnerUK·2d

@TommyFalkowski I found it to be hit-and-miss on my long context coherence test. Now that I've started testing non-Qwen3.5 models, it's showing how good Qwen3.5 is, but it's definitely a "your mileage may vary" model at 35B-A3B long context.

English

Tommy Falkowski@TommyFalkowski·2d

qwen3.5 35B-3A can actually do stuff. It's so weird and awesome to see a local model do useful things. Even with a pretty full context window it still seems usable.

English

6.3K

Jonathan Rudderham@codeRunnerUK·2d

@big_duca When I first heard "vibe coding", I had to look it up because I had no clue what it was. I code things that I want, not necessarily what other people want. They can code their own stuff. 🤣

English

Duca@big_duca·2d

I’ve noticed an interesting phenomenon: A lot of unemployed people are calling themselves vibe coders. And then build 100s of things that already exist. It’s intriguing behavior.

English

280

22.1K

Jonathan Rudderham@codeRunnerUK·2d

@LottoLabs There seems to be quite a few in the arcee family, but I keep seeing "max_position_embeddings": 131072 so I think I'll leave this for a future test, not my long-context coherence test.

English

Lotto@LottoLabs·2d

@codeRunnerUK I’ve heard good things of arcee

English

101

Lotto@LottoLabs·2d

So arcee, nemonano, qwen 122b, and more added to the test list for 3090 + Hermes agent

English

Jonathan Rudderham@codeRunnerUK·2d

@TheMekon_Venus I always loved the idea of a pocket size computer (even if it’s a phone with slide-out qwerty keyboard). I still have my Jornada 720 for that very reason. Don’t use it much. Just love the concept.

English

TheMekon_Venus@TheMekon_Venus·2d

I wouldn’t swap em for my smart phone., for practical reasons. But.. they were super exciting as they constantly seemed to be having new ideas… and worth the upgrade. And every new design and form factor brought something to the table.

naiive@naiivememe

How old are you? me:

English

277

Jonathan Rudderham@codeRunnerUK·2d

Definitely. I am using Claude to kick start my code, save me having to chew the gristly bits, but I’ll do things like “I want to add this feature. Don’t write it yourself, tell me what I should be changing and where.” This way helps me learn as I go. I use Git so I can roll back and compare what I’m changing. Using Git to track changes and compare revisions is gold.

English

Aanya@xoaanya·2d

Unpopular opinion: you’ll learn more by copy-pasting code, tweaking it, and creating files yourself than by dropping one giant prompt to generate the entire app

English

3.2K

اكتشف

@tim_cook @geekedout__ @LeakerApple @ravikiran_dev7 @jondelarroz @ivanfioravanti @UnslothAI @LLMJunky