Claude

“we use Claude Opus 5.5 for particular tasks that justifies its cost... Opus 5.5 is still a great workhorse as of today.”

“claude can fully drive the ui and testing on the phones via adb as an example”

“I haven't seen any increase in safeguards triggering or any negative effects in how quickly agents are able to make progress”

“I've been using Claude on a very large Java protocol proxy product and it's been able to do amazingly useful things for me.”

“For Claude it took 10 minutes to solve it.”

“anthropics' models outperform the output consistently but for 20x or more of the price of Mistral”

“This has been working very well mainly thanks to the prompts and docs we made it read”

“I've spent more money on Claude this year than I've given to a lot of other tech companies, combined.”

“The flexibility of being able to change anything at any time so I can see what I want to see is really nice.”

“Claude has also been helping a lot with Windows, sifting through voluminous system logs”

“Deepseek can do 90% of the job but a claude reviwer/spec writer is a brutal improvement.”

“AI has been a big help to me in writing it”

“Claude was able to troubleshoot it all. Would have taken me a bunch of time to untangle it myself.”

“The value Anthropic's Team Premium seat (which we use) provides is so disproportionate to its cost that I don't understand why they don't raise the price.”

“In my company using Codex and Claude help us a lot with our software.”

“This is one place where LLMs have truly helped out with testing.”

“A year and a half ago it took our dev maybe six weeks of struggling with LangChain to approximate what Claude + MCP server can do today.”

“If it wasn't for Claude assistance I probably would have given up on it by now.”

“We use a Claude for planning and generation... Our metrics say we are about 2x. Productive, at a cost of about $300 per dev per month.”

“We use a Claude for planning and generation, sol for adversarial review. Our metrics say we are about 2x. Productive”

“Preference is Claude Opus and Codex whatever the latest model is.”

“I saturated 7 accounts the last 2h alone, it's because they haven't entirely rethought their workflows yet”

“Claude recommended this once and it worked great.”

“I have now used Claude - still using it sparingly - to implement features in much less time than I'd need myself”

“I've been using sqlx + postgres very successfully with claude in the last couple of months.”

“I have been using Claude Opus 4.5, and it's the best out of the models I have tried.”

“I've been very impressed with Claude 4.5 and have been using it daily at work.”

“Since I've been using Claude I've learned a lot about Rust by having it build things for me”

“I've been using Claude and Codex to create bespoke systemd services for my random tools”

“I've been using a simple Claude prompt to review team PRs... it's been really solid so far.”

“I was willing to pay the $20 out of my own pocket to keep using it for work tasks. That forced me to rethink my stance.”

“It has worked out splendidly so far, my regrettable dumping of that huge PR on OCaml maintainers notwithstanding.”

“We run all our PRs through automated (claude) reviews automatically, and it helps a LOT.”

“Claude 3.7 not only found the correct issue with first answer (after thinking 39 seconds)”

“I switch between Claude and Gemini Flash, using Claude for more complicated tasks.”

“For my team which is software development, we favour Claude. It's obviously rather anecdotal but it has been much better at Go than ChatGPT.”

“With Claude on Bedrock I can use LLMs in production without sending customer data to the US.”

“Also, Claude is magnitudes superior to ChatGPT anything.”

“I found Anthropic's Claude quite useful (Sonnet 3.5) when I had to work on a legacy code base”

“have happily been using Claude Instant in production for a couple of months now”