Claude Sonnet 5

Post by sanderjd » Tue, Jun 30, 2026, 7:08 PM UTC

whateveracct wrote: post #175

microtonal wrote: post #31

Claude Sonnet 5 is built to be the most agentic Sonnet model yet. It can make plans, use tools like browsers and terminals, and run autonomously at a level that, just a few months ago, required larger and more expensive models. I have been using Sonnet 4.6 more than Opus, because I'm mostly doing agent-assisted development and not fully agent-driven development. This announcement does not make me positive, I have fou…

agent-assisted development uses orders of magnitude fewer tokens than agent-driven development the incentives aren't there sadly

Post by overgard » Tue, Jun 30, 2026, 7:10 PM UTC

everforward wrote: post #159

Brendinooo wrote: post #129

Earlier quoted context omitted.

Yeah, there's a real opportunity for one of these companies to invest time in a model that's tuned for, to use your term, agent-assisted developement. Trouble is, everyone inside their buildings seems to believe that no one will be working like that in a year or two.

There’s no way to justify their valuations if they get downgraded to a pair programming tool. They need fully agentic stuff to work and replace human engineers to even come close. Offhand, I’m not even certain whether a model like that could justify the constant retraining we’re doing on the agentic models. It doesn’t make a lot of sense to spend millions or billions on training to reduce hallucinations by 0.3% if yo…

Post by sanderjd » Tue, Jun 30, 2026, 7:11 PM UTC

AquinasCoder wrote: post #138

doctoboggan wrote: post #29

The cost per task chart is telling me that I should _never_ use Sonnet 5 above medium effort level - Opus always performs better for a given cost. So I guess the takeaway is that if Sonnet 5 medium isn't good enough for you, switch models, not effort levels.

While I appreciate, they publish this information, it's increasingly hard to keep track of it all. I've lost the mental model of how different models at different effort levels perform and what tasks they are good at. In practice, I tend to just use the default on Claude Code that works well enough. But I wonder to what degree other users really play around with these settings to optimize for their project.

Post by user43928 » Tue, Jun 30, 2026, 7:12 PM UTC

mwigdahl wrote: post #71

theLiminator wrote: post #28

Seems like the way to go for any smaller models is to only use the low reasoning levels, and for anything where you'd want it to reason harder, to just use a larger model. In effect, high reasoning only makes sense when you're using the frontier model and need extra performance (higher levels of reasoning are never pareto optimal unless you're at the largest model size).

Not to sound like an LLM, but that seems exactly right to me. Use it as a cheaper, high-functioning task subagent and lower reasoning for a master Opus session. As long as not every portion of your task requires maximum intelligence, you should come out ahead.

Post by manojlds » Tue, Jun 30, 2026, 7:13 PM UTC

doctoboggan wrote: post #29

The cost per task chart is telling me that I should _never_ use Sonnet 5 above medium effort level - Opus always performs better for a given cost. So I guess the takeaway is that if Sonnet 5 medium isn't good enough for you, switch models, not effort levels.