In Claude, I use Monitor often. Helps especially with with /goal
Claude loses track of subagents and especially subsubagents. Monitor keeps it automatically updating.
e.g., Reports go to the parent not the sub (so the sub stalls), or idle agents (doing shell work) are not updated.
def much faster lately, just great. thank you! speed matters so much on older hardware.
inspiring write-up. instruction count is a fun metric.
y'all are so fast, most of my nits go away by waiting. thanks for persistent What's New, and /output-styles !
one point: subagent messages are noisy, especially on mobile. collapsed like the TUI would be 👌
Today we announced the Claude-led discovery of a molecular machine that we suspect could represent a new gene editing mechanism. Its precise function, biotechnological utility (if any), or level of significance is not yet clear, but at minimum it is work I would have been proud to do as a PhD student. The work was done mostly, though not entirely, by Claude: our life sciences team suggested a broad area of research, Claude read through the literature and a bunch of genome data and discovered something interesting, then Claude proposed experiments to verify the discovery and our team carried them out.
It’s easy to dismiss this as a one-off or curiosity, but we’ve repeatedly seen a pattern where AI performance in new intellectual domains goes from weak to superhuman in a matter of a few years. In 2023 models struggled to do math at the level of an average high-school student. In 2024 they started to do well on math competitions for the best high-schoolers in the country, in 2025 they started to solve minor open problems, in early 2026 more significant open problems, and in late 2026 they are beginning to solve the top few open problems in all of mathematics. We believe AI for biology is on a similar exponential trend.
The main difference between biology and mathematics, of course, is that math can be done purely theoretically, while biology requires experimentation. Some have used this to draw the conclusion that AI’s utility in biology will be limited. We think this is wrong. As we’ve demonstrated today, humans can collaborate with AI to perform the experiments, validate key results in a few weeks and, if necessary, work with the AI to iterate on what they find. Eventually it may even be possible for Claude itself to safely perform the experiments by autonomously controlling lab equipment, with appropriate safeguards in place, but we aren’t doing that today (our lab is also a BSL1/BSL2 facility that doesn't handle materials dangerous to humans).
More broadly, biomedical advancement has many stages — from fundamental biology discoveries, to translational research, to drug discovery, clinical trials, and finally the actual delivery of medicines and health care to patients. We are also interested in these later stages, but even simply accelerating the first stage of fundamental biological discoveries has the potential to speed up and broaden the entire pipeline. Improving our understanding of biology and sharpening biologists’ tools can drive forward all of the later stages, for example by identifying new drug targets, finding new therapeutic modalities, allowing for more precise measurement, and speeding up the experimental loop which itself further accelerates our understanding of biology. This will not in itself speed up clinical trial times, but if it succeeds it could greatly increase the number of promising candidates that go into the pipeline — an increase in throughput even though latency remains.
In Machines of Loving Grace, I wrote about AI’s potential to “cure most diseases in 5-10 years” — a goal that sounds impossible, but one I believe is just barely possible if AI is applied to every stage of the pipeline. The first step is showing that AI can first help with, and then drive, biological discoveries.
Claude’s discovery is the latest in a line of related prior work that goes back decades, beginning with systems like CRISPR, and continuing with discoveries like the bridge recombinase and VIPR in the past few years. Recently, there has been heightened interest in systems based on reverse transcriptase (RT) enzymes, the enzyme underlying the system Claude identified. And most recently, a Stanford team working independently described a novel RT system with an associated non-coding array that is in some ways similar to the one Claude found, though they are distinct systems that evolved independently from each other. I believe that we’re at the very beginning of finding such systems and developing them into powerful tools for biotechnology.
I’m proud of the resources Anthropic has invested in accelerating the public benefits of AI through the life sciences, and we’re aiming both to grow our life sciences team and to work with other scientists to extend this approach to a broad range of problems. If you have a proposal for a research collaboration or are interested in joining our life sciences team, please reach out.
Claude has discovered a previously unknown enzyme system hidden in the DNA of bacteriophages. Beside the enzyme’s gene sits a long array of repeating DNA—a structure that looks somewhat similar to CRISPR.
We don’t yet understand what this system does, but only a handful of known systems share its features, and all of them are able to cut, copy, and paste DNA. Historically, the discovery of such programmable systems has helped revolutionize medicine. CRISPR, for instance, is now the foundation of genetic medicines. But it will take much more work to learn what this system does, and whether it can be put to similar use.
Read more: https://t.co/RuEosScSMb
👍 I was a die-hard, but gave it up awhile ago when auto-mode arrived and improved.
But I think keeping plan-mode *somehow* would be good.
It's an escape hatch for lack of confidence or risky operations.
And for beginners who are uncertain. Many are not living at the bleeding edge.
If you're tweaking effort UX, how about:
https://t.co/2UOqSWssMi
Opus 5.5 is doing quite well for me! 🙏
Since you recommend changing thinking, it would be helpful if Claude could launch subagents with different thinking mode.
Claude could then decide med/high/xhigh depending on the Task, I wouldnt need to twiddle.
YAML frontmatter can do so, why not Claude too?
Opus 5.5 is doing quite well for me! 🙏
Since you recommend changing thinking, it would be helpful if Claude could launch subagents with different thinking mode.
Claude could then decide med/high/xhigh depending on the Task, I wouldnt need to twiddle.
YAML frontmatter can do so, why not Claude too?
The Norwegian Consumer Council made a video about enshittification and got 2.5M views and 168K likes on IG. (If the style feels familiar, it was created by NewsLab, the same advertising agency that made the brilliant Visit Oslo video from a few years back.)
@amorriscode Nice. MCP all the things please :)
Claude Mobile too -- https://t.co/tCyvPKH2Dh MCP App was surprising when it popped up. Really handy while tripping.
Thanks @RobertJBye!
Thanks, I didn't know the catchall! I change models in subagent frontmatter.
But--
1. subagent CC banner does not show the correct model, and instead remains the parent / original model.
Confusing (and worrying with Fable parent 😅).
2. in a subagent, SHIFT-TAB between auto/manual doesn't seem to work.
I'm incredibly excited to announce the founding of the Mathematical AI safety Institute (MAISI) https://t.co/7h28dBocA6. AI safety needs more foundational theoretical development, and mathematicians have the skills and the mindset to help! MAISI is an independent institute with visiting positions ranging from 1 semester to 2 years. Our goal is to get mathematicians up to speed and working on research directions in AI safety as quickly as possible. There is important work to be done, and there is real progress to be made. YOU can help!
Applications are open now! MAISI is aiming to hire 10-30 mathematicians to join us in the Bay Area by January, and scale up to 30-100 for September 2027. If you're a mathematician interested in channeling your skills toward the most important problem of our time, please apply today! https://t.co/PTWQh0MK3T
For minor edits, agreed, just do it. Same situation as "allow maintainer edits".
For larger changes, since I've spent tokens on review and implementation, I send back a pr-review branch, which includes a kick-off prompt walking them through it. This is good for design-decisions, teaching/learning and building project context.
@trq212 Just used the SendFeedback tool, nice! 👌 Hope it's helping standardize on your side.
I reported the auto-mode classifier blocking all Bash and subagent calls in certain circumstances.