@coyotespike added a Bash utility (a wrapper on subprocess) He then also added a chain to convert natural language to a bash command. Very useful for interacting with the terminal! See the example here: https://
langchain.readthedocs.io/en/latest/exam
ples/chains/llm_bash.html
…
LLMS
-
LangChain Adds Bash Utility and Natural Language to Command Chain
By
–
-
LangChain 0.0.31 Release: New Agents, Bash, and Chains
By
–
LangChain version 0.0.31 @johnvmcdonnell fixed how Agents handle a missing tool (so no longer errors) Bash utility and a LLMBashChain (
@coyotespike
) a generic transformation chain (
@AkashSamant4
) a requests chain (
@BruceHammer
) on these additions: -
Agents Now Self-Correct When Selecting Non-Existent Tools
By
–
Previously, if an LLM chose to use a tool that did not exist the Agent would throw an error @johnvmcdonnell changed it so now we tell the agent that tool does not exist and let it self correct… just one step towards making them smarter
-
Seeking thoughts on LLM applications and similar features
By
–
I’d love to hear other people’s thoughts on this—and whether there are other applications of large language models that have similar features.
-
LaTeX notation request substantially improves math reasoning
By
–
Anecdotally, its math reasoning (excl. arithmetic calculation) improves substantially when you request LaTeX notation.
-
Large Language Models in Drug Industry: Measurable Benefits and Regulation
By
–
This is what I like about this particular application of large language models. The drug industry is highly regulated, and there are clear ways to measure whether the output of a protein-language model is doing more harm than good.
-
Protein-Language Models Accelerate Drug Discovery for Difficult Diseases
By
–
Protein-language models can be used to find them faster: either by enhancing existing molecules with targeted edits or by generating entirely new ones that could provide new hope for diseases like pancreatic cancer and ALS, for which more effective drugs have been elusive.
-
AI behavior with l33tsp34k, hyphens, Zalgo text, and Base64
By
–
Less protocol-complaint but likely also dumber. You see a similar phenomenon if you ask it to speak in l33t5p34k, or with hyphens between all letters, or especially with Zalgo text. Base64 is interesting though because it probably sees a *lot* of translation pairs in pre-train.
-
text-davinci-002 lacks RLHF; ChatGPT belongs to 002 line
By
–
We now know that text-davinci-002 doesn’t use RLHF either, and based on the model names used in API calls ChatGPT appears to be part of the 002 line, rather than 003 which uses RLHF.
