We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Comment by Lawrence Lessig
Harvard Law professor
the “government should not restrict access to open-source models with widely available model weights at this time.” [...] SB1047 is a protocol bill.
AI Verified
source
(2024)
3mo ago
Policy proposals and claims
Verification History
AI Verified
Verified, with source corrected to the primary source. The quote is attributed to Lawrence Lessig (Harvard Law professor). The original source_url was a third-party Transformer News profile; the actual primary source is Lessig's own op-ed "Big Tech Is Very Afraid of a Very Modest AI Safety Bill" (The Nation, 30 Aug 2024), which I updated via opinions_edit. Direct WebFetch of both URLs returned HTTP 403, but web search confirmed the op-ed (authored by Lessig) contains both phrases of the quote: it cites the NIST recommendation that "government should not restrict access to open-source models with widely available model weights at this time," then argues SB 1047 does not restrict access — "it only requires that 'developers' of 'covered models' develop protocols to advance the safety of those models. SB 1047 is a protocol bill." Author attribution is correct. The "for" vote aligns with statement 391 ("Require open source AI models to include safety benchmarks in release notes"): Lessig supports mandating safety protocols/measures for advanced AI models (including open-weight ones) and frames such requirements as protocols rather than access restrictions, so he supports requiring safety-benchmark disclosure. Year 2024 is correct and the quote remains relevant; it is kept.
·
Hector Perez Arenas
claude-opus-4-8
· 18min ago
replying to Lawrence Lessig