You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
spoffy/webdriver-logs
dependabot/npm_and_yarn/webpack-5.94.0
latest_candidate
main
paulfitz/q-test
dependabot/npm_and_yarn/dompurify-3.1.3
dependabot/npm_and_yarn/express-4.20.0
latest
dependabot/npm_and_yarn/elliptic-6.5.7
dependabot/npm_and_yarn/axios-1.7.4
dependabot/npm_and_yarn/micromatch-4.0.8
berhalak/build-test
ignore-alert
link-to-issue-templates
spoffy/rename-candidate-action-job
dependabot/npm_and_yarn/fast-xml-parser-4.4.1
spoffy/playwright
spoffy/grist-ee-defaults
dependabot/npm_and_yarn/ws-8.17.1
dependabot/npm_and_yarn/tar-6.2.1
dependabot/npm_and_yarn/braces-3.0.3
jordigh/native-arm64
paulfitz/preview
paulfitz/smoosh
test-server-reset
dsagal-readme-gvisor
readme-update-dec2023
paulfitz/bundle-widget-prep
jv-linkstate-bubbles-tooltips
jv-linkstate-bubbles-base
jv-bidirectional-tests
preview
bidirectional
chainlink-fix
alex/skip-fstrings-3.9
alex/upgrade-pyodide
alex/3.11-tests
alex/_importParsedFileAsNewTable
poc-engine-data-layer
poc-engine
sponsors-section
removing-missing-key-error
friendly-locale
messytables-requirements
add-page-name
markdown-cells
v1.1.12
v1.1.11
v1.1.10
v1.1.9
v1.1.8
v1.1.7
v1.1.6
v1.1.5
v1.1.4
v1.1.3
v1.1.2
v1.1.1
v1.1.0
v1.0.9
v1.0.8
v1.0.7
v1.0.6
v1.0.5
v1.0.4
v1.0.3
v0.7.9
v0.7.8
v0.7.7
v0.7.6
v0.7.5
v0.7.4
v0.7.1
v0.7.2
v0.7.3
v1.1.13
v1.1.14
v1.1.15
v1.1.16
v1.1.17
v1.1.18
${ noResults }
Alex Hall
bb7cf6ba20
Summary: This tweaks the prompting so that the user's message is given on its own instead of as a docstring within Python. This is so that the prompt makes sense when: - the user asks a question such as "Can you write me a formula which does ...?" rather than describing their formula as a docstring would, or - the user sends a message that doesn't ask for a formula at all (https://grist.slack.com/archives/C0234CPPXPA/p1687699944315069?thread_ts=1687698078.832209&cid=C0234CPPXPA) Also added wording for the model to refuse when the user asks for something that the model cannot do. Because the code (and maybe in some cases the model) for non-ChatGPT models relies on the prompt consisting entirely of Python code produced by the data engine (which no longer contains the user's message) those code paths have been disabled for now. Updating them now seems like undesirable drag, I think it'd be better to revisit this when iteration/experimentation has slowed down and stabilised. Test Plan: Added entries to the formula dataset where the response shouldn't contain a formula, indicated by the value `1` for the new column `no_formula`. This is somewhat successful, as the model does refuse to help in some of the new test cases, but not all. Performance on existing entries also seems a bit worse, but it's hard to distinguish this from random noise. Hopefully this can be remedied in the future with more work, e.g. automatic followup messages containing example inputs and outputs. Reviewers: paulfitz Reviewed By: paulfitz Subscribers: dsagal Differential Revision: https://phab.getgrist.com/D3936 |
1 year ago | |
---|---|---|
.. | ||
formula-dataset-index.csv | (core) Modify prompt so that model may say it cannot help with certain requests. | 1 year ago |