Amy Tobey
@renice.bsky.social
Amy Tobey💙parent🦁😾partner🥰obligate polymath🎶musician👩💻 software engineer🔎leader🧙♀️chaotic good🌈buckaroo🏳️⚧️backyard yogi🧘♀️魔法 少女🤦🏻♀
I'm sure it's a coincidence that regular opus got slower today :sadface:
February 7, 2026 at 9:21 PM
I'm sure it's a coincidence that regular opus got slower today :sadface:
my current working theory is Claude Opus estimates plan phases to take a bit under 200K tokens because that's its default window. we consistently complete phases at 192-198K with compaction off. with compaction on in CC it has to basically start over at 150K or so and loses momentum
February 7, 2026 at 6:50 PM
my current working theory is Claude Opus estimates plan phases to take a bit under 200K tokens because that's its default window. we consistently complete phases at 192-198K with compaction off. with compaction on in CC it has to basically start over at 150K or so and loses momentum
maybe coding becomes even more like music. anyone can sit down at the piano and make sound and some of it will sound good, but creating a specific vibe requires mastery
February 7, 2026 at 4:20 PM
maybe coding becomes even more like music. anyone can sit down at the piano and make sound and some of it will sound good, but creating a specific vibe requires mastery
SWE: <clutching pearls> but the code slop!
SRE: <exhaling smoke> you haven't seen what we have seen. slop is as old as time, maybe older. some of us believe slop is how the Universe began. we make your slop run, or a bot's slop run, it's all the same problems, different day
SRE: <exhaling smoke> you haven't seen what we have seen. slop is as old as time, maybe older. some of us believe slop is how the Universe began. we make your slop run, or a bot's slop run, it's all the same problems, different day
February 7, 2026 at 1:15 PM
SWE: <clutching pearls> but the code slop!
SRE: <exhaling smoke> you haven't seen what we have seen. slop is as old as time, maybe older. some of us believe slop is how the Universe began. we make your slop run, or a bot's slop run, it's all the same problems, different day
SRE: <exhaling smoke> you haven't seen what we have seen. slop is as old as time, maybe older. some of us believe slop is how the Universe began. we make your slop run, or a bot's slop run, it's all the same problems, different day
a younger me would be distraught about how much attention is going to autonomous AI agents, but now I see this as an opportunity while folks figure out what has always been true: agents are cybernetic experiences. the model is (as models always have been) a cognitive amplifier
February 7, 2026 at 12:53 PM
a younger me would be distraught about how much attention is going to autonomous AI agents, but now I see this as an opportunity while folks figure out what has always been true: agents are cybernetic experiences. the model is (as models always have been) a cognitive amplifier
I did something at work that's so cool I can't talk about it yet 😁
February 7, 2026 at 12:44 AM
I did something at work that's so cool I can't talk about it yet 😁
Reposted by Amy Tobey
that "confabulations" flag is underrated — having the model catch its own hallucinated stubs from earlier sessions is wild. I've been running similar sweeps on multi-agent codebases and it surfaces stuff linters completely miss. plan mode is genuinely the unlock.
February 6, 2026 at 6:19 PM
that "confabulations" flag is underrated — having the model catch its own hallucinated stubs from earlier sessions is wild. I've been running similar sweeps on multi-agent codebases and it surfaces stuff linters completely miss. plan mode is genuinely the unlock.
Reposted by Amy Tobey
BDSM enjoyers LLM enthusiasts
🤝
“Let me show you my custom harness”
🤝
“Let me show you my custom harness”
February 6, 2026 at 3:47 PM
BDSM enjoyers LLM enthusiasts
🤝
“Let me show you my custom harness”
🤝
“Let me show you my custom harness”
Reposted by Amy Tobey
this is quite an undertaking
biggest thing it brings is a much better security model. Monty lets you have tight control over network, filesystem, and (soon) which modules are allowed
also, extremely fast startup time
biggest thing it brings is a much better security model. Monty lets you have tight control over network, filesystem, and (soon) which modules are allowed
also, extremely fast startup time
Pydantic's Monty
A minimal, secure Python interpreter written in Rust for use by AI.
github.com/pydantic/monty
A minimal, secure Python interpreter written in Rust for use by AI.
github.com/pydantic/monty
GitHub - pydantic/monty: A minimal, secure Python interpreter written in Rust for use by AI
A minimal, secure Python interpreter written in Rust for use by AI - pydantic/monty
github.com
February 6, 2026 at 12:53 PM
this is quite an undertaking
biggest thing it brings is a much better security model. Monty lets you have tight control over network, filesystem, and (soon) which modules are allowed
also, extremely fast startup time
biggest thing it brings is a much better security model. Monty lets you have tight control over network, filesystem, and (soon) which modules are allowed
also, extremely fast startup time
here's an example where I will interrupt the model to redirect it. this plan is building e2e tests around multi-context drifting and it noticed some silly mismatches I'd like to fix. if I let this go it'll happily wrap those differences up in adapter code I do not want
February 6, 2026 at 1:35 PM
here's an example where I will interrupt the model to redirect it. this plan is building e2e tests around multi-context drifting and it noticed some silly mismatches I'd like to fix. if I let this go it'll happily wrap those differences up in adapter code I do not want
if I had all the stuff you bet your ass I would build my own trombones. I have all the stuff to build agentic software, so obviously I have several irons in the fire
February 6, 2026 at 1:16 PM
if I had all the stuff you bet your ass I would build my own trombones. I have all the stuff to build agentic software, so obviously I have several irons in the fire
Opus 4.6 is great but still better with Gemini as a sidekick
February 6, 2026 at 1:03 PM
Opus 4.6 is great but still better with Gemini as a sidekick
have opus 4.6 review your code. do it. get in plan mode and go "let's do a sweep of the repo for tech debt, stubs, confabulations, crusty docs, etc." and let it rip
February 5, 2026 at 11:53 PM
have opus 4.6 review your code. do it. get in plan mode and go "let's do a sweep of the repo for tech debt, stubs, confabulations, crusty docs, etc." and let it rip
interesting. opus 4.6 will sometimes call cpal (claude as an mcp) when it should use its own subagent. I don't usually have it loaded in CC but it is occasionally handy to have the simpler system prompt maybe claude likes it too
February 5, 2026 at 11:51 PM
interesting. opus 4.6 will sometimes call cpal (claude as an mcp) when it should use its own subagent. I don't usually have it loaded in CC but it is occasionally handy to have the simpler system prompt maybe claude likes it too
working well with CC today: phased plan, compaction off, at the end of each phase go back into plan mode and prompt "update the plan with current status then proceed". It will clear context and start fresh with the plan. way better than compaction imo
February 5, 2026 at 5:17 PM
working well with CC today: phased plan, compaction off, at the end of each phase go back into plan mode and prompt "update the plan with current status then proceed". It will clear context and start fresh with the plan. way better than compaction imo
think I'll call this next trick "multi-context drifting"
February 5, 2026 at 3:49 PM
think I'll call this next trick "multi-context drifting"
ok here's a cool use case for the model, we found a cache called "high-school-files.zip" which includes a bunch of stuff I'd forgotten about, and it ripped the text out of the 30+ year old wordperfect files. I believe there is also a netware binary that gave me superuser on the school network? lol
February 5, 2026 at 2:28 PM
ok here's a cool use case for the model, we found a cache called "high-school-files.zip" which includes a bunch of stuff I'd forgotten about, and it ripped the text out of the 30+ year old wordperfect files. I believe there is also a netware binary that gave me superuser on the school network? lol
Reposted by Amy Tobey
Sir Ian McKellen performing a monologue from Shakespeare’s Sir Thomas More on the Stephen Colbert show. Never have I heard this monologue performed with such a keen sense of prescience. Nor have I ever been in this exact historical moment.TY Sir Ian, for reaching us once again.
#Pinks #ProudBlue
#Pinks #ProudBlue
February 5, 2026 at 11:50 AM
Sir Ian McKellen performing a monologue from Shakespeare’s Sir Thomas More on the Stephen Colbert show. Never have I heard this monologue performed with such a keen sense of prescience. Nor have I ever been in this exact historical moment.TY Sir Ian, for reaching us once again.
#Pinks #ProudBlue
#Pinks #ProudBlue
life with gpal: "run this idea by gemini"
February 5, 2026 at 1:59 PM
life with gpal: "run this idea by gemini"
today's exploratory prompts are both from a mini-epiphany about kaijutsu right before bed: what if "oops, all MCP"? so I have bots looking into that while I rebuild the UI closer to its final form, which is turning out to be WindowMaker for AI, with shaders. we'll see in a few hours :)
February 5, 2026 at 1:48 PM
today's exploratory prompts are both from a mini-epiphany about kaijutsu right before bed: what if "oops, all MCP"? so I have bots looking into that while I rebuild the UI closer to its final form, which is turning out to be WindowMaker for AI, with shaders. we'll see in a few hours :)
Reposted by Amy Tobey
Released Hyprstream v0.2.0 today.
This release includes model downloads, Git worktree management, basic LLM inference and training for Qwen3 dense models.
Released as AppImages for CPU, CUDA, ROCm, and Universal.
direct links to follow...
github.com/hyprstream/h...
This release includes model downloads, Git worktree management, basic LLM inference and training for Qwen3 dense models.
Released as AppImages for CPU, CUDA, ROCm, and Universal.
direct links to follow...
github.com/hyprstream/h...
Release Hyprstream v0.2.0 · hyprstream/hyprstream
CUDA NOTE: Make sure the system includes the package cuda-toolkit. After installation, make sure to execute the following to fix a bug with cuda dependencies: systemctl --user set-environment LD_PR...
github.com
February 4, 2026 at 11:44 PM
Released Hyprstream v0.2.0 today.
This release includes model downloads, Git worktree management, basic LLM inference and training for Qwen3 dense models.
Released as AppImages for CPU, CUDA, ROCm, and Universal.
direct links to follow...
github.com/hyprstream/h...
This release includes model downloads, Git worktree management, basic LLM inference and training for Qwen3 dense models.
Released as AppImages for CPU, CUDA, ROCm, and Universal.
direct links to follow...
github.com/hyprstream/h...
so the new /insights thing in claude code says +5,512,017 / -2,012,677 lines changed on personal acct so I questioned that. it counted some autogenerated model code. the actual output is still pretty cool, 258KLoC extant code across 8 projects, 200KLoC of rust, all of it builds, compiles, and runs
February 4, 2026 at 11:34 PM
so the new /insights thing in claude code says +5,512,017 / -2,012,677 lines changed on personal acct so I questioned that. it counted some autogenerated model code. the actual output is still pretty cool, 258KLoC extant code across 8 projects, 200KLoC of rust, all of it builds, compiles, and runs
Reposted by Amy Tobey
Anthropic just took a big swipe at OpenAI's decision to put ads in ChatGPT. Anthropic is airing ads mocking ChatGPT ads during the Super Bowl, and they're hilarious 😅 Anthropic is also committing to no ads in Claude www.theverge.com/ai-artificia...
February 4, 2026 at 1:27 PM
Anthropic just took a big swipe at OpenAI's decision to put ads in ChatGPT. Anthropic is airing ads mocking ChatGPT ads during the Super Bowl, and they're hilarious 😅 Anthropic is also committing to no ads in Claude www.theverge.com/ai-artificia...
work project is deep in a goop phase, while personal project emerges from one. goop phase is when the agent struggles mightily and tries to give up, context burning like a christmas tree in july. you gotta nudge it through or it'll do more goopy code
February 3, 2026 at 9:58 PM
work project is deep in a goop phase, while personal project emerges from one. goop phase is when the agent struggles mightily and tries to give up, context burning like a christmas tree in july. you gotta nudge it through or it'll do more goopy code