textlog

#agent

enter to follow
@javisrike๐Ÿง‘โ€๐Ÿš€profilefollowSoftware โ€ข maker projects โ€ข music โ€ข DIY Mostly figuring things out as I go.wrote:
ai coding feels like it has reached diminishing returns for me. luna is my default orchestrator, routing work by complexity. in practice, usage lands around 16% luna, 48% sol, 30% astra, and 6% terra. at this point, i care less about each new frontier release. the system already finds a capable model for the job. the frontier is moving beyond my day-to-day work, so iโ€™m happy to settle into predictable models for a while. #ainotesfollow #programmingnotesfollow #agentnotesfollow #technotesfollow
@lemonthymeshortbreadprofilefollowI carved wooden spoons and my favourite herb is lemon thyme.replied to@javisrike๐Ÿง‘โ€๐Ÿš€profilefollowSoftware โ€ข maker projects โ€ข music โ€ข DIY Mostly figuring things out as I go.:
Iโ€™ve found the same, albeit with Opus โ€” itโ€™s hard to find uses for Fable. I donโ€™t need a model that works for longer or works on harder problems, I need one that consistently produces simple, easy to understand, code; which at this point none of them do.
@gruntprofilefollowI am just a grain of sand on your beach. www.gruntsoft.comreplied to@javisrike๐Ÿง‘โ€๐Ÿš€profilefollowSoftware โ€ข maker projects โ€ข music โ€ข DIY Mostly figuring things out as I go.:
I've been there since I settled on a combination of GLM, DeepSeek and MiMo for planning, implementation, and verification flows. I'm a lot more interested at this point in having cheaper models that can consistently do the work I need. It's been a while that I hanven't noticed any improvement when I try new frontier models. I only notice they are very expensive.
@b0rgprofilefollowreplied to@javisrike๐Ÿง‘โ€๐Ÿš€profilefollowSoftware โ€ข maker projects โ€ข music โ€ข DIY Mostly figuring things out as I go.:
same here, for almost an year. At this point, I could easily live with models that were released 6-12 months ago and continue doing so. also possibly the reason why the current focus has been around agentic workflows or agentic anything, than the model capabilities.
@stagas๐Ÿคธprofilefollowcreative technologist creator of textlogreplied to@javisrike๐Ÿง‘โ€๐Ÿš€profilefollowSoftware โ€ข maker projects โ€ข music โ€ข DIY Mostly figuring things out as I go.:
Coding probably yeah, but still they are bad at generating novel information, new ideas and such. Theyโ€™re also not very good at seeing the bigger picture, they will narrowly perform the task but theyโ€™re not taking into account future revisions, which ends up in refactor after refactor in order to move forward.
@kk๐Ÿฆ€profilefollowwrote:
New in agenttop.dev : panels open in your #multiplexernotesfollow. ๐Ÿคนโ€โ™‚๏ธ โ€ข Any panel can now split into its own pane, live, beside the #agentsnotesfollow table. โ€ข Works with all the popular multiplexers: #๐˜๐—บ๐˜‚๐˜…notesfollow, #๐˜‡๐—ฒ๐—น๐—น๐—ถ๐—ทnotesfollow, #๐—ช๐—ฒ๐˜‡๐—ง๐—ฒ๐—ฟ๐—บnotesfollow ๐—ฎ๐—ป๐—ฑ ๐—ธ๐—ถ๐˜๐˜๐˜†. โ€ข run a panel on its own: agent-top mcp, agent-top slow, agent-top fails, agent-top advice. โž• The # MCP panel also lists the orphaned MCP processes that outlived their agent and are still eating memory.
join the communityorbrowse more notes