Coding

“Ranks #2 of 60 on LMArena's WebDev coding arena (Elo 1636), a leaderboard built from blind human preference votes on coding tasks.”

“Claude is perfectly capable of writing assembly. Here's a working (basic) Prolog interpreter that Claude Fable 5 wrote in WebAssembly in 61 minutes for $16.75 in token costs: https: github.com emk fable-wasm-prolog blob main prolog.wa... WebAssembly is slightly easier than real assembly, but here Fable used WASM GC extensions, which are poorly documented and not yet super common. Fable didn't even need to debug it; I believe essentially all the assembly worked correctly on the first try. I have…”

“I think you are underestimating how fast this stuff is moving. Calling AI "just autocomplete" for system architecture is outdated. If you were to ask it (especially with Claude's newer model, Fable 5) to draft an architecture design diagram, it would do a better job than any junior dev ever could. Sure, giving context is still necessary, but you can just speak in plain, normal English and it will understand. AI is getting scary good at system design.”

“Yeah, Anthropic's current tokenizer in Sonnet 5 Opus 4.8 Fable 5 is much worse than OpenAI's. Also, OpenAI has been using their current o200k_base from the day GPT-4o came out over two years ago. Just a few of my own tests: - A ~2000-2002 legacy C++ game codebase at about ~90kloc: GPT 1.12M, Claude 2.2M - A ~30kloc TypeScript codebase: GPT 260K, Claude 437K In the end, GPT's current tokenizer is ~1.6x-2x better than Claude's current one, depending on your data. And you can check for free for bo…”

“SOTA models are typically used for interactive coding and other human in the loop work > say GPT-4o to GPT-5.2, a transition I just finished on a not too complicated application Neither of which is close to SOTA, because tasks like these are typically built on a cost conscious manner which tries to keep token costs in check. I’m primarily responding to all of the commenters who are acting like nobody is going to use American SOTA models for anything because the government interfered with them f…”

“Ranks #3 of 60 on LMArena's WebDev coding arena (Elo 1564), a leaderboard built from blind human preference votes on coding tasks.”

“Here are the numbers from their bar chart: 1. SWE-bench Pro Model Score (%) GLM-5.2 62.1 GLM-5.1 58.4 Claude Opus 4.8 69.2 GPT-5.5 58.6 Gemini 3.1 Pro 54.2 2. Terminal-Bench 2.1 Model Score (%) GLM-5.2 81.0 GLM-5.1 63.5 Claude Opus 4.8 85.0 GPT-5.5 84.0 Gemini 3.1 Pro 74.0 3. NL2Repo Model Score (%) GLM-5.2 48.9 GLM-5.1 42.7 Claude Opus 4.8 69.7 GPT-5.5 50.7 Gemini 3.1 Pro 33.4 4. DeepSWE Model Score (%) GLM-5.2 46.2 GLM-5.1 18.0 Claude Opus 4.8 58.0 GPT-5.5 70.0 Gemini 3.1 Pro 10.0 5. ProgramB…”

“I've been using essentially this process (with Claude Code) for about six months. There are a couple of places where I've opened xcode; mostly to update the simulators for new betas of xcode 27, and once to add a target for Apple Watch (and I think something for HealthKit). Interestingly, since about Opus 4.6, Claude has been able to reason its way into this process on its own. It was clunky until 4.7, and in 4.8 it's managed to find its way around every reason I had to open xcode myself.”

“Yeah, Anthropic's current tokenizer in Sonnet 5 Opus 4.8 Fable 5 is much worse than OpenAI's. Also, OpenAI has been using their current o200k_base from the day GPT-4o came out over two years ago. Just a few of my own tests: - A ~2000-2002 legacy C++ game codebase at about ~90kloc: GPT 1.12M, Claude 2.2M - A ~30kloc TypeScript codebase: GPT 260K, Claude 437K In the end, GPT's current tokenizer is ~1.6x-2x better than Claude's current one, depending on your data. And you can check for free for bo…”

“I'm pretty sure that this is both 1. an artifact of agent tools only doing generic greps based on keyword searches, limiting the scope to a few lines 2. RLHF from Anthropic and OpenAI that bake in catastrophic edit avoidance I used to have a CLAUDE.md rule that forbid inline comments and only allowed public API doc comments. That used to work perfectly back in 2025 era models. Now these models refuse to honor it and write worse comment slop. This has become the "voice" of Opus 4.8 and I just ro…”

“The Damage: Now every time Claude does something stupid or trashes your code, developers in the back of their mind will think, is Claude sabotaging me on purpose? [1] Trust is hard to gain. Easy to lose. And harder to get back. Models will converge. Trust won't. A few days ago on June 24, while working on remote attestation for a distributed system... CLAUDE OPUS 4.8 No. I'm not a rogue agent, and I'm not trying to sabotage your code. But I'm not going to wave off how this looks. I churned, bui…”

“Ranks #5 of 60 on LMArena's WebDev coding arena (Elo 1556), a leaderboard built from blind human preference votes on coding tasks.”

“Grok 4.5 is really fast, has more usage at $10 month than $20 month Claude pro, and Opus-level. Claude pro feels like a demo. Claude is much better in OpenCode then in Claude Code, OpenCode is just better than Claude Code. Claude Code feels like a complete mess to use comparatively.”

“Grok 4.5 is really fast, has more usage at $10 month than $20 month Claude pro, and Opus-level. Claude pro feels like a demo. Claude is much better in OpenCode then in Claude Code, OpenCode is just better than Claude Code. Claude Code feels like a complete mess to use comparatively.”

“Refreshing to see this be the top comment, thank you. I agree. To answer your question, Grok 4.5 seems to be pretty good at simple tasks and gets even some of the trickier ones correct but it tends to struggle with bigger codebases that aren't very uniform. I've noticed that it uses a fraction of the tokens to get to solutions which is really impressive compared to GLM 5.2 which tends to be an overthinker. I'm not sure if Grok 4.5 will become part of my stack yet but I am genuinely impressed wi…”

“True of anything anyone says about anything, including int_19h and simondotau. I'm quite impressed with Grok 4.5 because its speed and single-task effectiveness feels better than anything else for a human-in-the-loop workflow. (For the stuff I do, I'm not interested in having AI race ahead of what I can oversee.) All models do things in a way I personally disagree with at least some of the time. The "dumber" models sometimes fail to recognise how to fit a solution into existing code. The "smart…”

“Refreshing to see this be the top comment, thank you. I agree. To answer your question, Grok 4.5 seems to be pretty good at simple tasks and gets even some of the trickier ones correct but it tends to struggle with bigger codebases that aren't very uniform. I've noticed that it uses a fraction of the tokens to get to solutions which is really impressive compared to GLM 5.2 which tends to be an overthinker. I'm not sure if Grok 4.5 will become part of my stack yet but I am genuinely impressed wi…”

“"It uploads the whole repository — every tracked file's content plus git history — independent of what the agent reads" Holy cow!!!! I mean I kinda expected Elon would do something like this to try to catch-up.. but this is extremely concerning. This is precisely the reason, even though their pricing is competitive and grok-4.5 is actually good enough, I chose not to go with them.”

“Ranks #6 of 60 on LMArena's WebDev coding arena (Elo 1546), a leaderboard built from blind human preference votes on coding tasks.”

“In our coding evaluations, we found Sonnet 5 is more capable than Sonnet 4.6 (which was an underrated model itself), but is now faster and slightly cheaper. Sonnet 5's performance is comparable to GLM 5.2 in both one-shot coding and agentic ability. However, it's about ~20% less verbose than GLM 5.2 in average code submission sizes, and uses fewer reasoning tokens, which reduces the cost gap and suggests it writes cleaner code. In practice, Sonnet 5 ends up being 40% more expensive and ~2x fast…”

“In our coding evaluations, we found Sonnet 5 is more capable than Sonnet 4.6 (which was an underrated model itself), but is now faster and slightly cheaper. Sonnet 5's performance is comparable to GLM 5.2 in both one-shot coding and agentic ability. However, it's about ~20% less verbose than GLM 5.2 in average code submission sizes, and uses fewer reasoning tokens, which reduces the cost gap and suggests it writes cleaner code. In practice, Sonnet 5 ends up being 40% more expensive and ~2x fast…”

“I have tried to rewrite an article with GLM-5.2 and with Sonnet 4.6. Completely different results as LLM is non-deterministic. But GLM-5.2 made a lot of subtle mistakes that needed to be corrected by hand. On the opposite, Sonnet found and corrected all mistakes in the second round. Similar situation was with planning and coding. GLM-5.2 seems to be good “on paper” but the real usage results was different. And I am not an attorney for Claude or GLM-5.2… :) But as I’ve been using LLM models dail…”

“I am another skilled senior, have been coding since I was 7, although you have a few more years of experience on me, and am commenting here just for the goldilocks moment, as I have read and reflected on both of your comments and find my reality is somewhere in the middle. On personal projects, where I am in charge of all the hats (product development, UI, UX, backend, security, server admin, etc) -- absolutely crazy force multiplier. You get a nice suite of backend and e2e tests running, with…”

“In our coding evaluations, we found Sonnet 5 is more capable than Sonnet 4.6 (which was an underrated model itself), but is now faster and slightly cheaper. Sonnet 5's performance is comparable to GLM 5.2 in both one-shot coding and agentic ability. However, it's about ~20% less verbose than GLM 5.2 in average code submission sizes, and uses fewer reasoning tokens, which reduces the cost gap and suggests it writes cleaner code. In practice, Sonnet 5 ends up being 40% more expensive and ~2x fast…”

“Yeah, Anthropic's current tokenizer in Sonnet 5 Opus 4.8 Fable 5 is much worse than OpenAI's. Also, OpenAI has been using their current o200k_base from the day GPT-4o came out over two years ago. Just a few of my own tests: - A ~2000-2002 legacy C++ game codebase at about ~90kloc: GPT 1.12M, Claude 2.2M - A ~30kloc TypeScript codebase: GPT 260K, Claude 437K In the end, GPT's current tokenizer is ~1.6x-2x better than Claude's current one, depending on your data. And you can check for free for bo…”

“Scores 84.9% on the Aider polyglot coding benchmark (#2 of 27), which tests editing real code across many languages.”

“Scores 84.9% on the Aider polyglot coding benchmark (#2 of 27), which tests editing real code across many languages.”

“Scores 84.9% on the Aider polyglot coding benchmark (#2 of 27), which tests editing real code across many languages.”

“Ranks #4 of 60 on LMArena's WebDev coding arena (Elo 1559), a leaderboard built from blind human preference votes on coding tasks.”

“We must be using different AI. Ever since Claude Opus 4.7 it's been helping me greatly ship around 3x to 5x faster, and it's good code if I tell it to follow my existing code's structures. Otherwise you have to create .md guideline files and it works. It's not perfect, but again, 3x to 5x (!!!)”

“The problem with models like Qwen 3.6 35B (which really is an excellent model) is that my expectations of what a model can do have gone SO high now. Here's a prompt I just ran against Claude Opus 4.7: > Use python3 to experiment with whether the SQLite3 authorizer mechanism can be used to detect an INSERT OR REPLACE based just on running an explain query without examining the SQL string itself Opus nailed it: https: claude.ai share c4212606-3fee-4b7c-bc97-505e0348ccac I tried the same thing aga…”

“I feel like Opus 4.5 was the peak in Claude Code usefulness. It was smart, it was interactive, it was precise. In 4.6 and 4.7, it spends a long time thinking and I don't know what's happening, often hits a dead-end and just continues. For a while I was setting Opus 4.5 in Claude Code, but it got reset often. I just canceled my Max plan, don't know where to look for alternatives.”

“I use Claude Opus 4.7 on max thinking inside Claude Code and I gotta tell you, as context of the project grows, it starts slipping. No amount of whipping and cursing has helped. Currently looking to start making my own hooks setup so it can be safer but nothing concrete yet.”