#canitbedone — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #canitbedone, aggregated by home.social.
-
My another #canitbedone #software #project. #bash #AI #coding assistant. Very hacky combination of bash, sed, awk, wc, grep, jq and of course #curl glued together in about 3k lines of bash source code. As #LLM it is using local instance of #modelGemma4 running in #llamacpp. Surprisingly it works better than expected, have less miss edits than GitHub copilot on the same task. Except these #linux command line tools it has zero dependency on any AI frameworks.
-
My another #canitbedone #software #project. #bash #AI #coding assistant. Very hacky combination of bash, sed, awk, wc, grep, jq and of course #curl glued together in about 3k lines of bash source code. As #LLM it is using local instance of #modelGemma4 running in #llamacpp. Surprisingly it works better than expected, have less miss edits than GitHub copilot on the same task. Except these #linux command line tools it has zero dependency on any AI frameworks.
-
My another #canitbedone #software #project. #bash #AI #coding assistant. Very hacky combination of bash, sed, awk, wc, grep, jq and of course #curl glued together in about 3k lines of bash source code. As #LLM it is using local instance of #modelGemma4 running in #llamacpp. Surprisingly it works better than expected, have less miss edits than GitHub copilot on the same task. Except these #linux command line tools it has zero dependency on any AI frameworks.
-
My another #canitbedone #software #project. #bash #AI #coding assistant. Very hacky combination of bash, sed, awk, wc, grep, jq and of course #curl glued together in about 3k lines of bash source code. As #LLM it is using local instance of #modelGemma4 running in #llamacpp. Surprisingly it works better than expected, have less miss edits than GitHub copilot on the same task. Except these #linux command line tools it has zero dependency on any AI frameworks.
-
My another #canitbedone #software #project. #bash #AI #coding assistant. Very hacky combination of bash, sed, awk, wc, grep, jq and of course #curl glued together in about 3k lines of bash source code. As #LLM it is using local instance of #modelGemma4 running in #llamacpp. Surprisingly it works better than expected, have less miss edits than GitHub copilot on the same task. Except these #linux command line tools it has zero dependency on any AI frameworks.